Compare commits
22 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 hetao
|
dcfa5e9dee | ||
|
Henry Li
|
8abfd2d9ae | ||
|
changqingla
|
c6bbc595c3 | ||
|
牧毅
|
ffe706d0df | ||
|
DanielWalnut
|
f7d79b6d83 | ||
|
cndoit18
|
d69128495b | ||
|
Willem Jiang
|
9dc78c3829 | ||
|
Ernâni de Britto Murtinho
|
96fb5d653b | ||
|
Wang Hao
|
e27c43f005 | ||
|
hao-cyber
|
c3886e635d | ||
|
Zhengbin Sun
|
c046d9cc34 | ||
|
XingLiu0923
|
9cff113862 | ||
|
Leo Hui
|
a43db94fb6 | ||
|
JeffJiang
|
8802eea0ba | ||
|
Leo Hui
|
1a59accb52 | ||
|
JeffJiang
|
86295ed195 | ||
|
JeffJiang
|
bf4820c68f | ||
|
Abeautifulsnow
|
25e7b86f02 | ||
|
Maxim Kot
|
0459e3c9f8 | ||
|
DanielWalnut
|
5cc0e61297 | ||
|
Henry Li
|
a220f4b6ea | ||
|
DanielWalnut
|
f73a7a229c |
@@ -26,6 +26,7 @@ wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
.venv/
|
||||
|
||||
# Web
|
||||
node_modules
|
||||
|
||||
@@ -5,6 +5,8 @@ APP_ENV=development
|
||||
# docker build args
|
||||
NEXT_PUBLIC_API_URL="http://localhost:8000/api"
|
||||
|
||||
AGENT_RECURSION_LIMIT=30
|
||||
|
||||
# Search Engine, Supported values: tavily (recommended), duckduckgo, brave_search, arxiv
|
||||
SEARCH_API=tavily
|
||||
TAVILY_API_KEY=tvly-xxx
|
||||
|
||||
@@ -23,7 +23,23 @@ jobs:
|
||||
uv pip install -e ".[dev]"
|
||||
uv pip install -e ".[test]"
|
||||
|
||||
- name: Run test cases
|
||||
- name: Run test cases with coverage
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
TAVILY_API_KEY=mock-key make test
|
||||
TAVILY_API_KEY=mock-key make coverage
|
||||
|
||||
- name: Generate HTML Coverage Report
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m coverage html -d coverage_html
|
||||
|
||||
- name: Upload Coverage Report
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: coverage-report
|
||||
path: coverage_html/
|
||||
|
||||
- name: Display Coverage Summary
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m coverage report
|
||||
@@ -21,3 +21,6 @@ conf.yaml
|
||||
.idea/
|
||||
.langgraph_api/
|
||||
|
||||
# coverage report
|
||||
coverage.xml
|
||||
coverage/
|
||||
|
||||
+9
-2
@@ -1,15 +1,22 @@
|
||||
FROM ghcr.io/astral-sh/uv:python3.12-bookworm
|
||||
FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
|
||||
|
||||
# Install uv.
|
||||
COPY --from=ghcr.io/astral-sh/uv:latest /uv /bin/uv
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Pre-cache the application dependencies.
|
||||
RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
--mount=type=bind,source=uv.lock,target=uv.lock \
|
||||
--mount=type=bind,source=pyproject.toml,target=pyproject.toml \
|
||||
uv sync --locked --no-install-project
|
||||
|
||||
# Copy the application into the container.
|
||||
COPY . /app
|
||||
|
||||
# Install the application dependencies.
|
||||
RUN uv sync --frozen --no-cache
|
||||
RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
uv sync --locked
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
|
||||
@@ -19,4 +19,4 @@ langgraph-dev:
|
||||
uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.12 langgraph dev --allow-blocking
|
||||
|
||||
coverage:
|
||||
uv run pytest --cov=src tests/ --cov-report=term-missing
|
||||
uv run pytest --cov=src tests/ --cov-report=term-missing --cov-report=xml
|
||||
|
||||
@@ -2,11 +2,11 @@
|
||||
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
|
||||
<!-- DeepWiki badge generated by https://deepwiki.ryoppippi.com/ -->
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md)
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)
|
||||
|
||||
> Originated from Open Source, give back to Open Source.
|
||||
|
||||
@@ -370,7 +370,7 @@ This will enable trace visualization in LangGraph Studio and send your traces to
|
||||
|
||||
You can also run this project with Docker.
|
||||
|
||||
First, you need read the [configuration](#configuration) below. Make sure `.env`, `.conf.yaml` files are ready.
|
||||
First, you need read the [configuration](docs/configuration_guide.md) below. Make sure `.env`, `.conf.yaml` files are ready.
|
||||
|
||||
Second, to build a Docker image of your own web server:
|
||||
|
||||
|
||||
+2
-2
@@ -2,10 +2,10 @@
|
||||
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
<!-- DeepWiki badge generated by https://deepwiki.ryoppippi.com/ -->
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md)
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)
|
||||
|
||||
> Aus Open Source entstanden, an Open Source zurückgeben.
|
||||
|
||||
|
||||
+554
@@ -0,0 +1,554 @@
|
||||
# 🦌 DeerFlow
|
||||
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
<!-- DeepWiki badge generated by https://deepwiki.ryoppippi.com/ -->
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)
|
||||
|
||||
> Originado del código abierto, retribuido al código abierto.
|
||||
|
||||
**DeerFlow** (**D**eep **E**xploration and **E**fficient **R**esearch **Flow**) es un marco de Investigación Profunda impulsado por la comunidad que se basa en el increíble trabajo de la comunidad de código abierto. Nuestro objetivo es combinar modelos de lenguaje con herramientas especializadas para tareas como búsqueda web, rastreo y ejecución de código Python, mientras devolvemos a la comunidad que hizo esto posible.
|
||||
|
||||
Por favor, visita [nuestra página web oficial](https://deerflow.tech/) para más detalles.
|
||||
|
||||
## Demostración
|
||||
|
||||
### Video
|
||||
|
||||
https://github.com/user-attachments/assets/f3786598-1f2a-4d07-919e-8b99dfa1de3e
|
||||
|
||||
En esta demostración, mostramos cómo usar DeerFlow para:
|
||||
|
||||
- Integrar perfectamente con servicios MCP
|
||||
- Realizar el proceso de Investigación Profunda y producir un informe completo con imágenes
|
||||
- Crear audio de podcast basado en el informe generado
|
||||
|
||||
### Repeticiones
|
||||
|
||||
- [¿Qué altura tiene la Torre Eiffel comparada con el edificio más alto?](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)
|
||||
- [¿Cuáles son los repositorios más populares en GitHub?](https://deerflow.tech/chat?replay=github-top-trending-repo)
|
||||
- [Escribir un artículo sobre los platos tradicionales de Nanjing](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)
|
||||
- [¿Cómo decorar un apartamento de alquiler?](https://deerflow.tech/chat?replay=rental-apartment-decoration)
|
||||
- [Visita nuestra página web oficial para explorar más repeticiones.](https://deerflow.tech/#case-studies)
|
||||
|
||||
---
|
||||
|
||||
## 📑 Tabla de Contenidos
|
||||
|
||||
- [🚀 Inicio Rápido](#inicio-rápido)
|
||||
- [🌟 Características](#características)
|
||||
- [🏗️ Arquitectura](#arquitectura)
|
||||
- [🛠️ Desarrollo](#desarrollo)
|
||||
- [🐳 Docker](#docker)
|
||||
- [🗣️ Integración de Texto a Voz](#integración-de-texto-a-voz)
|
||||
- [📚 Ejemplos](#ejemplos)
|
||||
- [❓ Preguntas Frecuentes](#preguntas-frecuentes)
|
||||
- [📜 Licencia](#licencia)
|
||||
- [💖 Agradecimientos](#agradecimientos)
|
||||
- [⭐ Historial de Estrellas](#historial-de-estrellas)
|
||||
|
||||
## Inicio Rápido
|
||||
|
||||
DeerFlow está desarrollado en Python y viene con una interfaz web escrita en Node.js. Para garantizar un proceso de configuración sin problemas, recomendamos utilizar las siguientes herramientas:
|
||||
|
||||
### Herramientas Recomendadas
|
||||
|
||||
- **[`uv`](https://docs.astral.sh/uv/getting-started/installation/):**
|
||||
Simplifica la gestión del entorno Python y las dependencias. `uv` crea automáticamente un entorno virtual en el directorio raíz e instala todos los paquetes necesarios por ti—sin necesidad de instalar entornos Python manualmente.
|
||||
|
||||
- **[`nvm`](https://github.com/nvm-sh/nvm):**
|
||||
Gestiona múltiples versiones del entorno de ejecución Node.js sin esfuerzo.
|
||||
|
||||
- **[`pnpm`](https://pnpm.io/installation):**
|
||||
Instala y gestiona dependencias del proyecto Node.js.
|
||||
|
||||
### Requisitos del Entorno
|
||||
|
||||
Asegúrate de que tu sistema cumple con los siguientes requisitos mínimos:
|
||||
|
||||
- **[Python](https://www.python.org/downloads/):** Versión `3.12+`
|
||||
- **[Node.js](https://nodejs.org/en/download/):** Versión `22+`
|
||||
|
||||
### Instalación
|
||||
|
||||
```bash
|
||||
# Clonar el repositorio
|
||||
git clone https://github.com/bytedance/deer-flow.git
|
||||
cd deer-flow
|
||||
|
||||
# Instalar dependencias, uv se encargará del intérprete de python, la creación del entorno virtual y la instalación de los paquetes necesarios
|
||||
uv sync
|
||||
|
||||
# Configurar .env con tus claves API
|
||||
# Tavily: https://app.tavily.com/home
|
||||
# Brave_SEARCH: https://brave.com/search/api/
|
||||
# volcengine TTS: Añade tus credenciales TTS si las tienes
|
||||
cp .env.example .env
|
||||
|
||||
# Ver las secciones 'Motores de Búsqueda Compatibles' e 'Integración de Texto a Voz' a continuación para todas las opciones disponibles
|
||||
|
||||
# Configurar conf.yaml para tu modelo LLM y claves API
|
||||
# Por favor, consulta 'docs/configuration_guide.md' para más detalles
|
||||
cp conf.yaml.example conf.yaml
|
||||
|
||||
# Instalar marp para la generación de presentaciones
|
||||
# https://github.com/marp-team/marp-cli?tab=readme-ov-file#use-package-manager
|
||||
brew install marp-cli
|
||||
```
|
||||
|
||||
Opcionalmente, instala las dependencias de la interfaz web vía [pnpm](https://pnpm.io/installation):
|
||||
|
||||
```bash
|
||||
cd deer-flow/web
|
||||
pnpm install
|
||||
```
|
||||
|
||||
### Configuraciones
|
||||
|
||||
Por favor, consulta la [Guía de Configuración](docs/configuration_guide.md) para más detalles.
|
||||
|
||||
> [!NOTA]
|
||||
> Antes de iniciar el proyecto, lee la guía cuidadosamente y actualiza las configuraciones para que coincidan con tus ajustes y requisitos específicos.
|
||||
|
||||
### Interfaz de Consola
|
||||
|
||||
La forma más rápida de ejecutar el proyecto es utilizar la interfaz de consola.
|
||||
|
||||
```bash
|
||||
# Ejecutar el proyecto en un shell tipo bash
|
||||
uv run main.py
|
||||
```
|
||||
|
||||
### Interfaz Web
|
||||
|
||||
Este proyecto también incluye una Interfaz Web, que ofrece una experiencia interactiva más dinámica y atractiva.
|
||||
|
||||
> [!NOTA]
|
||||
> Necesitas instalar primero las dependencias de la interfaz web.
|
||||
|
||||
```bash
|
||||
# Ejecutar tanto el servidor backend como el frontend en modo desarrollo
|
||||
# En macOS/Linux
|
||||
./bootstrap.sh -d
|
||||
|
||||
# En Windows
|
||||
bootstrap.bat -d
|
||||
```
|
||||
|
||||
Abre tu navegador y visita [`http://localhost:3000`](http://localhost:3000) para explorar la interfaz web.
|
||||
|
||||
Explora más detalles en el directorio [`web`](./web/).
|
||||
|
||||
## Motores de Búsqueda Compatibles
|
||||
|
||||
DeerFlow soporta múltiples motores de búsqueda que pueden configurarse en tu archivo `.env` usando la variable `SEARCH_API`:
|
||||
|
||||
- **Tavily** (predeterminado): Una API de búsqueda especializada para aplicaciones de IA
|
||||
|
||||
- Requiere `TAVILY_API_KEY` en tu archivo `.env`
|
||||
- Regístrate en: https://app.tavily.com/home
|
||||
|
||||
- **DuckDuckGo**: Motor de búsqueda centrado en la privacidad
|
||||
|
||||
- No requiere clave API
|
||||
|
||||
- **Brave Search**: Motor de búsqueda centrado en la privacidad con características avanzadas
|
||||
|
||||
- Requiere `BRAVE_SEARCH_API_KEY` en tu archivo `.env`
|
||||
- Regístrate en: https://brave.com/search/api/
|
||||
|
||||
- **Arxiv**: Búsqueda de artículos científicos para investigación académica
|
||||
- No requiere clave API
|
||||
- Especializado en artículos científicos y académicos
|
||||
|
||||
Para configurar tu motor de búsqueda preferido, establece la variable `SEARCH_API` en tu archivo `.env`:
|
||||
|
||||
```bash
|
||||
# Elige uno: tavily, duckduckgo, brave_search, arxiv
|
||||
SEARCH_API=tavily
|
||||
```
|
||||
|
||||
## Características
|
||||
|
||||
### Capacidades Principales
|
||||
|
||||
- 🤖 **Integración de LLM**
|
||||
- Soporta la integración de la mayoría de los modelos a través de [litellm](https://docs.litellm.ai/docs/providers).
|
||||
- Soporte para modelos de código abierto como Qwen
|
||||
- Interfaz API compatible con OpenAI
|
||||
- Sistema LLM de múltiples niveles para diferentes complejidades de tareas
|
||||
|
||||
### Herramientas e Integraciones MCP
|
||||
|
||||
- 🔍 **Búsqueda y Recuperación**
|
||||
|
||||
- Búsqueda web a través de Tavily, Brave Search y más
|
||||
- Rastreo con Jina
|
||||
- Extracción avanzada de contenido
|
||||
|
||||
- 🔗 **Integración Perfecta con MCP**
|
||||
- Amplía capacidades para acceso a dominio privado, gráfico de conocimiento, navegación web y más
|
||||
- Facilita la integración de diversas herramientas y metodologías de investigación
|
||||
|
||||
### Colaboración Humana
|
||||
|
||||
- 🧠 **Humano en el Bucle**
|
||||
|
||||
- Soporta modificación interactiva de planes de investigación usando lenguaje natural
|
||||
- Soporta aceptación automática de planes de investigación
|
||||
|
||||
- 📝 **Post-Edición de Informes**
|
||||
- Soporta edición de bloques tipo Notion
|
||||
- Permite refinamientos por IA, incluyendo pulido asistido por IA, acortamiento y expansión de oraciones
|
||||
- Impulsado por [tiptap](https://tiptap.dev/)
|
||||
|
||||
### Creación de Contenido
|
||||
|
||||
- 🎙️ **Generación de Podcasts y Presentaciones**
|
||||
- Generación de guiones de podcast y síntesis de audio impulsadas por IA
|
||||
- Creación automatizada de presentaciones PowerPoint simples
|
||||
- Plantillas personalizables para contenido a medida
|
||||
|
||||
## Arquitectura
|
||||
|
||||
DeerFlow implementa una arquitectura modular de sistema multi-agente diseñada para investigación automatizada y análisis de código. El sistema está construido sobre LangGraph, permitiendo un flujo de trabajo flexible basado en estados donde los componentes se comunican a través de un sistema de paso de mensajes bien definido.
|
||||
|
||||
|
||||
|
||||
> Vélo en vivo en [deerflow.tech](https://deerflow.tech/#multi-agent-architecture)
|
||||
|
||||
El sistema emplea un flujo de trabajo racionalizado con los siguientes componentes:
|
||||
|
||||
1. **Coordinador**: El punto de entrada que gestiona el ciclo de vida del flujo de trabajo
|
||||
|
||||
- Inicia el proceso de investigación basado en la entrada del usuario
|
||||
- Delega tareas al planificador cuando corresponde
|
||||
- Actúa como la interfaz principal entre el usuario y el sistema
|
||||
|
||||
2. **Planificador**: Componente estratégico para descomposición y planificación de tareas
|
||||
|
||||
- Analiza objetivos de investigación y crea planes de ejecución estructurados
|
||||
- Determina si hay suficiente contexto disponible o si se necesita más investigación
|
||||
- Gestiona el flujo de investigación y decide cuándo generar el informe final
|
||||
|
||||
3. **Equipo de Investigación**: Una colección de agentes especializados que ejecutan el plan:
|
||||
|
||||
- **Investigador**: Realiza búsquedas web y recopilación de información utilizando herramientas como motores de búsqueda web, rastreo e incluso servicios MCP.
|
||||
- **Programador**: Maneja análisis de código, ejecución y tareas técnicas utilizando la herramienta Python REPL.
|
||||
Cada agente tiene acceso a herramientas específicas optimizadas para su rol y opera dentro del marco LangGraph
|
||||
|
||||
4. **Reportero**: Procesador de etapa final para los resultados de la investigación
|
||||
- Agrega hallazgos del equipo de investigación
|
||||
- Procesa y estructura la información recopilada
|
||||
- Genera informes de investigación completos
|
||||
|
||||
## Integración de Texto a Voz
|
||||
|
||||
DeerFlow ahora incluye una función de Texto a Voz (TTS) que te permite convertir informes de investigación a voz. Esta función utiliza la API TTS de volcengine para generar audio de alta calidad a partir de texto. Características como velocidad, volumen y tono también son personalizables.
|
||||
|
||||
### Usando la API TTS
|
||||
|
||||
Puedes acceder a la funcionalidad TTS a través del punto final `/api/tts`:
|
||||
|
||||
```bash
|
||||
# Ejemplo de llamada API usando curl
|
||||
curl --location 'http://localhost:8000/api/tts' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"text": "Esto es una prueba de la funcionalidad de texto a voz.",
|
||||
"speed_ratio": 1.0,
|
||||
"volume_ratio": 1.0,
|
||||
"pitch_ratio": 1.0
|
||||
}' \
|
||||
--output speech.mp3
|
||||
```
|
||||
|
||||
## Desarrollo
|
||||
|
||||
### Pruebas
|
||||
|
||||
Ejecuta el conjunto de pruebas:
|
||||
|
||||
```bash
|
||||
# Ejecutar todas las pruebas
|
||||
make test
|
||||
|
||||
# Ejecutar archivo de prueba específico
|
||||
pytest tests/integration/test_workflow.py
|
||||
|
||||
# Ejecutar con cobertura
|
||||
make coverage
|
||||
```
|
||||
|
||||
### Calidad del Código
|
||||
|
||||
```bash
|
||||
# Ejecutar linting
|
||||
make lint
|
||||
|
||||
# Formatear código
|
||||
make format
|
||||
```
|
||||
|
||||
### Depuración con LangGraph Studio
|
||||
|
||||
DeerFlow utiliza LangGraph para su arquitectura de flujo de trabajo. Puedes usar LangGraph Studio para depurar y visualizar el flujo de trabajo en tiempo real.
|
||||
|
||||
#### Ejecutando LangGraph Studio Localmente
|
||||
|
||||
DeerFlow incluye un archivo de configuración `langgraph.json` que define la estructura del grafo y las dependencias para LangGraph Studio. Este archivo apunta a los grafos de flujo de trabajo definidos en el proyecto y carga automáticamente variables de entorno desde el archivo `.env`.
|
||||
|
||||
##### Mac
|
||||
|
||||
```bash
|
||||
# Instala el gestor de paquetes uv si no lo tienes
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
|
||||
# Instala dependencias e inicia el servidor LangGraph
|
||||
uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.12 langgraph dev --allow-blocking
|
||||
```
|
||||
|
||||
##### Windows / Linux
|
||||
|
||||
```bash
|
||||
# Instalar dependencias
|
||||
pip install -e .
|
||||
pip install -U "langgraph-cli[inmem]"
|
||||
|
||||
# Iniciar el servidor LangGraph
|
||||
langgraph dev
|
||||
```
|
||||
|
||||
Después de iniciar el servidor LangGraph, verás varias URLs en la terminal:
|
||||
|
||||
- API: http://127.0.0.1:2024
|
||||
- UI de Studio: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
|
||||
- Docs de API: http://127.0.0.1:2024/docs
|
||||
|
||||
Abre el enlace de UI de Studio en tu navegador para acceder a la interfaz de depuración.
|
||||
|
||||
#### Usando LangGraph Studio
|
||||
|
||||
En la UI de Studio, puedes:
|
||||
|
||||
1. Visualizar el grafo de flujo de trabajo y ver cómo se conectan los componentes
|
||||
2. Rastrear la ejecución en tiempo real para ver cómo fluyen los datos a través del sistema
|
||||
3. Inspeccionar el estado en cada paso del flujo de trabajo
|
||||
4. Depurar problemas examinando entradas y salidas de cada componente
|
||||
5. Proporcionar retroalimentación durante la fase de planificación para refinar planes de investigación
|
||||
|
||||
Cuando envías un tema de investigación en la UI de Studio, podrás ver toda la ejecución del flujo de trabajo, incluyendo:
|
||||
|
||||
- La fase de planificación donde se crea el plan de investigación
|
||||
- El bucle de retroalimentación donde puedes modificar el plan
|
||||
- Las fases de investigación y escritura para cada sección
|
||||
- La generación del informe final
|
||||
|
||||
### Habilitando el Rastreo de LangSmith
|
||||
|
||||
DeerFlow soporta el rastreo de LangSmith para ayudarte a depurar y monitorear tus flujos de trabajo. Para habilitar el rastreo de LangSmith:
|
||||
|
||||
1. Asegúrate de que tu archivo `.env` tenga las siguientes configuraciones (ver `.env.example`):
|
||||
```bash
|
||||
LANGSMITH_TRACING=true
|
||||
LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
|
||||
LANGSMITH_API_KEY="xxx"
|
||||
LANGSMITH_PROJECT="xxx"
|
||||
```
|
||||
|
||||
2. Inicia el rastreo y visualiza el grafo localmente con LangSmith ejecutando:
|
||||
```bash
|
||||
langgraph dev
|
||||
```
|
||||
|
||||
Esto habilitará la visualización de rastros en LangGraph Studio y enviará tus rastros a LangSmith para monitoreo y análisis.
|
||||
|
||||
## Docker
|
||||
|
||||
También puedes ejecutar este proyecto con Docker.
|
||||
|
||||
Primero, necesitas leer la [configuración](docs/configuration_guide.md) a continuación. Asegúrate de que los archivos `.env` y `.conf.yaml` estén listos.
|
||||
|
||||
Segundo, para construir una imagen Docker de tu propio servidor web:
|
||||
|
||||
```bash
|
||||
docker build -t deer-flow-api .
|
||||
```
|
||||
|
||||
Finalmente, inicia un contenedor Docker que ejecute el servidor web:
|
||||
|
||||
```bash
|
||||
# Reemplaza deer-flow-api-app con tu nombre de contenedor preferido
|
||||
docker run -d -t -p 8000:8000 --env-file .env --name deer-flow-api-app deer-flow-api
|
||||
|
||||
# detener el servidor
|
||||
docker stop deer-flow-api-app
|
||||
```
|
||||
|
||||
### Docker Compose (incluye tanto backend como frontend)
|
||||
|
||||
DeerFlow proporciona una configuración docker-compose para ejecutar fácilmente tanto el backend como el frontend juntos:
|
||||
|
||||
```bash
|
||||
# construir imagen docker
|
||||
docker compose build
|
||||
|
||||
# iniciar el servidor
|
||||
docker compose up
|
||||
```
|
||||
|
||||
## Ejemplos
|
||||
|
||||
Los siguientes ejemplos demuestran las capacidades de DeerFlow:
|
||||
|
||||
### Informes de Investigación
|
||||
|
||||
1. **Informe sobre OpenAI Sora** - Análisis de la herramienta IA Sora de OpenAI
|
||||
|
||||
- Discute características, acceso, ingeniería de prompts, limitaciones y consideraciones éticas
|
||||
- [Ver informe completo](examples/openai_sora_report.md)
|
||||
|
||||
2. **Informe sobre el Protocolo Agent to Agent de Google** - Visión general del protocolo Agent to Agent (A2A) de Google
|
||||
|
||||
- Discute su papel en la comunicación de agentes IA y su relación con el Model Context Protocol (MCP) de Anthropic
|
||||
- [Ver informe completo](examples/what_is_agent_to_agent_protocol.md)
|
||||
|
||||
3. **¿Qué es MCP?** - Un análisis completo del término "MCP" en múltiples contextos
|
||||
|
||||
- Explora Model Context Protocol en IA, Fosfato Monocálcico en química y Placa de Microcanales en electrónica
|
||||
- [Ver informe completo](examples/what_is_mcp.md)
|
||||
|
||||
4. **Fluctuaciones del Precio de Bitcoin** - Análisis de los movimientos recientes del precio de Bitcoin
|
||||
|
||||
- Examina tendencias del mercado, influencias regulatorias e indicadores técnicos
|
||||
- Proporciona recomendaciones basadas en datos históricos
|
||||
- [Ver informe completo](examples/bitcoin_price_fluctuation.md)
|
||||
|
||||
5. **¿Qué es LLM?** - Una exploración en profundidad de los Modelos de Lenguaje Grandes
|
||||
|
||||
- Discute arquitectura, entrenamiento, aplicaciones y consideraciones éticas
|
||||
- [Ver informe completo](examples/what_is_llm.md)
|
||||
|
||||
6. **¿Cómo usar Claude para Investigación Profunda?** - Mejores prácticas y flujos de trabajo para usar Claude en investigación profunda
|
||||
|
||||
- Cubre ingeniería de prompts, análisis de datos e integración con otras herramientas
|
||||
- [Ver informe completo](examples/how_to_use_claude_deep_research.md)
|
||||
|
||||
7. **Adopción de IA en Salud: Factores de Influencia** - Análisis de factores que impulsan la adopción de IA en salud
|
||||
|
||||
- Discute tecnologías IA, calidad de datos, consideraciones éticas, evaluaciones económicas, preparación organizativa e infraestructura digital
|
||||
- [Ver informe completo](examples/AI_adoption_in_healthcare.md)
|
||||
|
||||
8. **Impacto de la Computación Cuántica en la Criptografía** - Análisis del impacto de la computación cuántica en la criptografía
|
||||
|
||||
- Discute vulnerabilidades de la criptografía clásica, criptografía post-cuántica y soluciones criptográficas resistentes a la cuántica
|
||||
- [Ver informe completo](examples/Quantum_Computing_Impact_on_Cryptography.md)
|
||||
|
||||
9. **Aspectos Destacados del Rendimiento de Cristiano Ronaldo** - Análisis de los aspectos destacados del rendimiento de Cristiano Ronaldo
|
||||
- Discute sus logros profesionales, goles internacionales y rendimiento en varios partidos
|
||||
- [Ver informe completo](examples/Cristiano_Ronaldo's_Performance_Highlights.md)
|
||||
|
||||
Para ejecutar estos ejemplos o crear tus propios informes de investigación, puedes usar los siguientes comandos:
|
||||
|
||||
```bash
|
||||
# Ejecutar con una consulta específica
|
||||
uv run main.py "¿Qué factores están influyendo en la adopción de IA en salud?"
|
||||
|
||||
# Ejecutar con parámetros de planificación personalizados
|
||||
uv run main.py --max_plan_iterations 3 "¿Cómo impacta la computación cuántica en la criptografía?"
|
||||
|
||||
# Ejecutar en modo interactivo con preguntas integradas
|
||||
uv run main.py --interactive
|
||||
|
||||
# O ejecutar con prompt interactivo básico
|
||||
uv run main.py
|
||||
|
||||
# Ver todas las opciones disponibles
|
||||
uv run main.py --help
|
||||
```
|
||||
|
||||
### Modo Interactivo
|
||||
|
||||
La aplicación ahora soporta un modo interactivo con preguntas integradas tanto en inglés como en chino:
|
||||
|
||||
1. Lanza el modo interactivo:
|
||||
|
||||
```bash
|
||||
uv run main.py --interactive
|
||||
```
|
||||
|
||||
2. Selecciona tu idioma preferido (English o 中文)
|
||||
|
||||
3. Elige de una lista de preguntas integradas o selecciona la opción para hacer tu propia pregunta
|
||||
|
||||
4. El sistema procesará tu pregunta y generará un informe de investigación completo
|
||||
|
||||
### Humano en el Bucle
|
||||
|
||||
DeerFlow incluye un mecanismo de humano en el bucle que te permite revisar, editar y aprobar planes de investigación antes de que sean ejecutados:
|
||||
|
||||
1. **Revisión del Plan**: Cuando el humano en el bucle está habilitado, el sistema presentará el plan de investigación generado para tu revisión antes de la ejecución
|
||||
|
||||
2. **Proporcionando Retroalimentación**: Puedes:
|
||||
|
||||
- Aceptar el plan respondiendo con `[ACCEPTED]`
|
||||
- Editar el plan proporcionando retroalimentación (p.ej., `[EDIT PLAN] Añadir más pasos sobre implementación técnica`)
|
||||
- El sistema incorporará tu retroalimentación y generará un plan revisado
|
||||
|
||||
3. **Auto-aceptación**: Puedes habilitar la auto-aceptación para omitir el proceso de revisión:
|
||||
|
||||
- Vía API: Establece `auto_accepted_plan: true` en tu solicitud
|
||||
|
||||
4. **Integración API**: Cuando uses la API, puedes proporcionar retroalimentación a través del parámetro `feedback`:
|
||||
```json
|
||||
{
|
||||
"messages": [{ "role": "user", "content": "¿Qué es la computación cuántica?" }],
|
||||
"thread_id": "my_thread_id",
|
||||
"auto_accepted_plan": false,
|
||||
"feedback": "[EDIT PLAN] Incluir más sobre algoritmos cuánticos"
|
||||
}
|
||||
```
|
||||
|
||||
### Argumentos de Línea de Comandos
|
||||
|
||||
La aplicación soporta varios argumentos de línea de comandos para personalizar su comportamiento:
|
||||
|
||||
- **query**: La consulta de investigación a procesar (puede ser múltiples palabras)
|
||||
- **--interactive**: Ejecutar en modo interactivo con preguntas integradas
|
||||
- **--max_plan_iterations**: Número máximo de ciclos de planificación (predeterminado: 1)
|
||||
- **--max_step_num**: Número máximo de pasos en un plan de investigación (predeterminado: 3)
|
||||
- **--debug**: Habilitar registro detallado de depuración
|
||||
|
||||
## Preguntas Frecuentes
|
||||
|
||||
Por favor, consulta [FAQ.md](docs/FAQ.md) para más detalles.
|
||||
|
||||
## Licencia
|
||||
|
||||
Este proyecto es de código abierto y está disponible bajo la [Licencia MIT](./LICENSE).
|
||||
|
||||
## Agradecimientos
|
||||
|
||||
DeerFlow está construido sobre el increíble trabajo de la comunidad de código abierto. Estamos profundamente agradecidos a todos los proyectos y contribuyentes cuyos esfuerzos han hecho posible DeerFlow. Verdaderamente, nos apoyamos en hombros de gigantes.
|
||||
|
||||
Nos gustaría extender nuestro sincero agradecimiento a los siguientes proyectos por sus invaluables contribuciones:
|
||||
|
||||
- **[LangChain](https://github.com/langchain-ai/langchain)**: Su excepcional marco impulsa nuestras interacciones y cadenas LLM, permitiendo integración y funcionalidad sin problemas.
|
||||
- **[LangGraph](https://github.com/langchain-ai/langgraph)**: Su enfoque innovador para la orquestación multi-agente ha sido instrumental en permitir los sofisticados flujos de trabajo de DeerFlow.
|
||||
|
||||
Estos proyectos ejemplifican el poder transformador de la colaboración de código abierto, y estamos orgullosos de construir sobre sus cimientos.
|
||||
|
||||
### Contribuyentes Clave
|
||||
|
||||
Un sentido agradecimiento va para los autores principales de `DeerFlow`, cuya visión, pasión y dedicación han dado vida a este proyecto:
|
||||
|
||||
- **[Daniel Walnut](https://github.com/hetaoBackend/)**
|
||||
- **[Henry Li](https://github.com/magiccube/)**
|
||||
|
||||
Su compromiso inquebrantable y experiencia han sido la fuerza impulsora detrás del éxito de DeerFlow. Nos sentimos honrados de tenerlos al timón de este viaje.
|
||||
|
||||
## Historial de Estrellas
|
||||
|
||||
[](https://star-history.com/#bytedance/deer-flow&Date)
|
||||
+1
-1
@@ -3,7 +3,7 @@
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md)
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)
|
||||
|
||||
> オープンソースから生まれ、オープンソースに還元する。
|
||||
|
||||
|
||||
+545
@@ -0,0 +1,545 @@
|
||||
# 🦌 DeerFlow
|
||||
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
|
||||
<!-- DeepWiki badge generated by https://deepwiki.ryoppippi.com/ -->
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)
|
||||
|
||||
> Originado do Open Source, de volta ao Open Source
|
||||
|
||||
**DeerFlow** (**D**eep **E**xploration and **E**fficient **R**esearch **Flow**) é um framework de Pesquisa Profunda orientado-a-comunidade que baseia-se em um íncrivel trabalho da comunidade open source. Nosso objetivo é combinar modelos de linguagem com ferramentas especializadas para tarefas como busca na web, crawling, e execução de código Python, enquanto retribui com a comunidade que o tornou possível.
|
||||
|
||||
Por favor, visite [Nosso Site Oficial](https://deerflow.tech/) para maiores detalhes.
|
||||
|
||||
## Demo
|
||||
|
||||
### Video
|
||||
|
||||
https://github.com/user-attachments/assets/f3786598-1f2a-4d07-919e-8b99dfa1de3e
|
||||
|
||||
Nesse demo, nós demonstramos como usar o DeerFlow para:
|
||||
In this demo, we showcase how to use DeerFlow to:
|
||||
|
||||
- Integração fácil com serviços MCP
|
||||
- Conduzir o processo de Pesquisa Profunda e produzir um relatório abrangente com imagens
|
||||
- Criar um áudio podcast baseado no relatório gerado
|
||||
|
||||
### Replays
|
||||
|
||||
- [Quão alta é a Torre Eiffel comparada ao prédio mais alto?](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)
|
||||
- [Quais são os top repositórios tendência no GitHub?](https://deerflow.tech/chat?replay=github-top-trending-repo)
|
||||
- [Escreva um artigo sobre os pratos tradicionais de Nanjing's](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)
|
||||
- [Como decorar um apartamento alugado?](https://deerflow.tech/chat?replay=rental-apartment-decoration)
|
||||
- [Visite nosso site oficial para explorar mais replays.](https://deerflow.tech/#case-studies)
|
||||
|
||||
---
|
||||
|
||||
## 📑 Tabela de Conteúdos
|
||||
|
||||
- [🚀 Início Rápido](#Início-Rápido)
|
||||
- [🌟 Funcionalidades](#funcionalidades)
|
||||
- [🏗️ Arquitetura](#arquitetura)
|
||||
- [🛠️ Desenvolvimento](#desenvolvimento)
|
||||
- [🐳 Docker](#docker)
|
||||
- [🗣️ Texto-para-fala Integração](#texto-para-fala-integração)
|
||||
- [📚 Exemplos](#exemplos)
|
||||
- [❓ FAQ](#faq)
|
||||
- [📜 Licença](#licença)
|
||||
- [💖 Agradecimentos](#agradecimentos)
|
||||
- [🏆 Contribuidores-Chave](#contribuidores-chave)
|
||||
- [⭐ Histórico de Estrelas](#Histórico-Estrelas)
|
||||
|
||||
## Início-Rápido
|
||||
|
||||
DeerFlow é desenvolvido em Python, e vem com uma IU web escrita em Node.js. Para garantir um processo de configuração fácil, nós recomendamos o uso das seguintes ferramentas:
|
||||
|
||||
### Ferramentas Recomendadas
|
||||
|
||||
- **[`uv`](https://docs.astral.sh/uv/getting-started/installation/):**
|
||||
Simplifica o gerenciamento de dependência de ambientes Python. `uv` automaticamente cria um ambiente virtual no diretório raiz e instala todos os pacotes necessários para não haver a necessidade de instalar ambientes Python manualmente
|
||||
|
||||
- **[`nvm`](https://github.com/nvm-sh/nvm):**
|
||||
Gerencia múltiplas versões do ambiente de execução do Node.js sem esforço.
|
||||
|
||||
- **[`pnpm`](https://pnpm.io/installation):**
|
||||
Instala e gerencia dependências do projeto Node.js.
|
||||
|
||||
### Requisitos de Ambiente
|
||||
|
||||
Certifique-se de que seu sistema atenda os seguintes requisitos mínimos:
|
||||
|
||||
- **[Python](https://www.python.org/downloads/):** Versão `3.12+`
|
||||
- **[Node.js](https://nodejs.org/en/download/):** Versão `22+`
|
||||
|
||||
### Instalação
|
||||
|
||||
```bash
|
||||
# Clone o repositório
|
||||
git clone https://github.com/bytedance/deer-flow.git
|
||||
cd deer-flow
|
||||
|
||||
# Instale as dependências, uv irá lidar com o interpretador do python e a criação do venv, e instalar os pacotes necessários
|
||||
uv sync
|
||||
|
||||
# Configure .env com suas chaves de API
|
||||
# Tavily: https://app.tavily.com/home
|
||||
# Brave_SEARCH: https://brave.com/search/api/
|
||||
# volcengine TTS: Adicione sua credencial TTS caso você a possua
|
||||
cp .env.example .env
|
||||
|
||||
# Veja as seções abaixo 'Supported Search Engines' and 'Texto-para-Fala Integração' para todas as opções disponíveis
|
||||
|
||||
# Configure o conf.yaml para o seu modelo LLM e chaves API
|
||||
# Por favor, consulte 'docs/configuration_guide.md' para maiores detalhes
|
||||
cp conf.yaml.example conf.yaml
|
||||
|
||||
# Instale marp para geração de ppt
|
||||
# https://github.com/marp-team/marp-cli?tab=readme-ov-file#use-package-manager
|
||||
brew install marp-cli
|
||||
```
|
||||
|
||||
Opcionalmente, instale as dependências IU web via [pnpm](https://pnpm.io/installation):
|
||||
|
||||
```bash
|
||||
cd deer-flow/web
|
||||
pnpm install
|
||||
```
|
||||
|
||||
### Configurações
|
||||
|
||||
Por favor, consulte o [Guia de Configuração](docs/configuration_guide.md) para maiores detalhes.
|
||||
|
||||
> [!NOTA]
|
||||
> Antes de iniciar o projeto, leia o guia detalhadamente, e atualize as configurações para baterem com os seus requisitos e configurações específicas.
|
||||
|
||||
### Console IU
|
||||
|
||||
A maneira mais rápida de rodar o projeto é usar o console IU.
|
||||
|
||||
```bash
|
||||
# Execute o projeto em um shell tipo-bash
|
||||
uv run main.py
|
||||
```
|
||||
|
||||
### Web IU
|
||||
|
||||
Esse projeto também inclui uma IU Web, trazendo uma experiência mais interativa, dinâmica e engajadora.
|
||||
|
||||
> [!NOTA]
|
||||
> Você precisa instalar as dependências do IU web primeiro.
|
||||
|
||||
```bash
|
||||
# Execute ambos os servidores de backend e frontend em modo desenvolvimento
|
||||
# No macOS/Linux
|
||||
./bootstrap.sh -d
|
||||
|
||||
# No Windows
|
||||
bootstrap.bat -d
|
||||
```
|
||||
|
||||
Abra seu navegador e visite [`http://localhost:3000`](http://localhost:3000) para explorar a IU web.
|
||||
|
||||
Explore mais detalhes no diretório [`web`](./web/) .
|
||||
|
||||
## Mecanismos de Busca Suportados
|
||||
|
||||
|
||||
DeerFlow suporta múltiplos mecanismos de busca que podem ser configurados no seu arquivo `.env` usando a variável `SEARCH_API`:
|
||||
|
||||
- **Tavily** (padrão): Uma API de busca especializada para aplicações de IA
|
||||
|
||||
- Requer `TAVILY_API_KEY` no seu arquivo `.env`
|
||||
- Inscreva-se em: https://app.tavily.com/home
|
||||
|
||||
- **DuckDuckGo**: Mecanismo de busca focado em privacidade
|
||||
|
||||
- Não requer chave API
|
||||
|
||||
- **Brave Search**: Mecanismo de busca focado em privacidade com funcionalidades avançadas
|
||||
|
||||
- Requer `BRAVE_SEARCH_API_KEY` no seu arquivo `.env`
|
||||
- Inscreva-se em: https://brave.com/search/api/
|
||||
|
||||
- **Arxiv**: Busca de artigos científicos para pesquisa acadêmica
|
||||
- Não requer chave API
|
||||
- Especializado em artigos científicos e acadêmicos
|
||||
|
||||
Para configurar o seu mecanismo preferido, defina a variável `SEARCH_API` no seu arquivo:
|
||||
|
||||
```bash
|
||||
# Escolha uma: tavily, duckduckgo, brave_search, arxiv
|
||||
SEARCH_API=tavily
|
||||
```
|
||||
|
||||
## Funcionalidades
|
||||
|
||||
### Principais Funcionalidades
|
||||
|
||||
- 🤖 **Integração LLM**
|
||||
|
||||
- Suporta a integração da maioria dos modelos através de [litellm](https://docs.litellm.ai/docs/providers).
|
||||
- Suporte a modelos open source como Qwen
|
||||
- Interface API compatível com a OpenAI
|
||||
- Sistema LLM multicamadas para diferentes complexidades de tarefa
|
||||
|
||||
### Ferramentas e Integrações MCP
|
||||
|
||||
- 🔍 **Busca e Recuperação**
|
||||
|
||||
- Busca web com Tavily, Brave Search e mais
|
||||
- Crawling com Jina
|
||||
- Extração de Conteúdo avançada
|
||||
|
||||
- 🔗 **Integração MCP perfeita**
|
||||
|
||||
- Expansão de capacidades de acesso para acesso a domínios privados, grafo de conhecimento, navegação web e mais
|
||||
- Integração facilitdade de diversas ferramentas de pesquisa e metodologias
|
||||
|
||||
### Colaboração Humana
|
||||
|
||||
- 🧠 **Humano-no-processo**
|
||||
|
||||
|
||||
- Suporta modificação interativa de planos de pesquisa usando linguagem natural
|
||||
- Suporta auto-aceite de planos de pesquisa
|
||||
|
||||
- 📝 **Relatório Pós-Edição**
|
||||
- Suporta edição de edição de blocos estilo Notion
|
||||
- Permite refinamentos de IA, incluindo polimento de IA assistida, encurtamento de frase, e expansão
|
||||
- Distribuído por [tiptap](https://tiptap.dev/)
|
||||
|
||||
### Criação de Conteúdo
|
||||
|
||||
- 🎙️ **Geração de Podcast e apresentação**
|
||||
|
||||
- Script de geração de podcast e síntese de áudio movido por IA
|
||||
- Criação automatizada de apresentações PowerPoint simples
|
||||
- Templates customizáveis para conteúdo personalizado
|
||||
|
||||
## Arquitetura
|
||||
|
||||
DeerFlow implementa uma arquitetura de sistema multi-agente modular designada para pesquisa e análise de código automatizada. O sistema é construído em LangGraph, possibilitando um fluxo de trabalho flexível baseado-em-estado onde os componentes se comunicam através de um sistema de transmissão de mensagens bem-definido.
|
||||
|
||||
|
||||
|
||||
> Veja ao vivo em [deerflow.tech](https://deerflow.tech/#multi-agent-architecture)
|
||||
|
||||
O sistema emprega um fluxo de trabalho simplificado com os seguintes componentes:
|
||||
|
||||
1. **Coordenador**: O ponto de entrada que gerencia o ciclo de vida do fluxo de trabalho
|
||||
|
||||
- Inicia o processo de pesquisa baseado na entrada do usuário
|
||||
- Delega tarefas so planejador quando apropriado
|
||||
- Atua como a interface primária entre o usuário e o sistema
|
||||
|
||||
2. **Planejador**: Componente estratégico para a decomposição e planejamento
|
||||
|
||||
- Analisa objetivos de pesquisa e cria planos de execução estruturados
|
||||
- Determina se há contexto suficiente disponível ou se mais pesquisa é necessária
|
||||
- Gerencia o fluxo de pesquisa e decide quando gerar o relatório final
|
||||
|
||||
3. **Time de Pesquisa**: Uma coleção de agentes especializados que executam o plano:
|
||||
|
||||
- **Pesquisador**: Conduz buscas web e coleta informações utilizando ferramentas como mecanismos de busca web, crawling e mesmo serviços MCP.
|
||||
- **Programador**: Lida com a análise de código, execução e tarefas técnicas como usar a ferramenta Python REPL.
|
||||
Cada agente tem acesso à ferramentas específicas otimizadas para seu papel e opera dentro do fluxo de trabalho LangGraph.
|
||||
|
||||
4. **Repórter**: Estágio final do processador de estágio para saídas de pesquisa
|
||||
- Resultados agregados do time de pesquisa
|
||||
- Processa e estrutura as informações coletadas
|
||||
- Gera relatórios abrangentes de pesquisas
|
||||
|
||||
## Texto-para-Fala Integração
|
||||
|
||||
DeerFlow agora inclui uma funcionalidade Texto-para-Fala (TTS) que permite que você converta relatórios de busca para voz. Essa funcionalidade usa o mecanismo de voz da API TTS para gerar áudio de alta qualidade a partir do texto. Funcionalidades como velocidade, volume e tom também são customizáveis.
|
||||
|
||||
### Usando a API TTS
|
||||
|
||||
Você pode acessar a funcionalidade TTS através do endpoint `/api/tts`:
|
||||
|
||||
```bash
|
||||
# Exemplo de chamada da API usando curl
|
||||
curl --location 'http://localhost:8000/api/tts' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"text": "This is a test of the text-to-speech functionality.",
|
||||
"speed_ratio": 1.0,
|
||||
"volume_ratio": 1.0,
|
||||
"pitch_ratio": 1.0
|
||||
}' \
|
||||
--output speech.mp3
|
||||
```
|
||||
|
||||
## Desenvolvimento
|
||||
|
||||
### Testando
|
||||
|
||||
Rode o conjunto de testes:
|
||||
|
||||
```bash
|
||||
# Roda todos os testes
|
||||
make test
|
||||
|
||||
# Roda um arquivo de teste específico
|
||||
pytest tests/integration/test_workflow.py
|
||||
|
||||
# Roda com coverage
|
||||
make coverage
|
||||
```
|
||||
|
||||
### Qualidade de Código
|
||||
|
||||
```bash
|
||||
# Roda o linting
|
||||
make lint
|
||||
|
||||
# Formata de código
|
||||
make format
|
||||
```
|
||||
|
||||
### Debugando com o LangGraph Studio
|
||||
|
||||
DeerFlow usa LangGraph para sua arquitetura de fluxo de trabalho. Nós podemos usar o LangGraph Studio para debugar e visualizar o fluxo de trabalho em tempo real.
|
||||
|
||||
#### Rodando o LangGraph Studio Localmente
|
||||
|
||||
DeerFlow inclui um arquivo de configuração `langgraph.json` que define a estrutura do grafo e dependências para o LangGraph Studio. Esse arquivo aponta para o grafo do fluxo de trabalho definido no projeto e automaticamente carrega as variáveis de ambiente do arquivo `.env`.
|
||||
|
||||
##### Mac
|
||||
|
||||
```bash
|
||||
# Instala o gerenciador de pacote uv caso você não o possua
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
|
||||
# Instala as dependências e inicia o servidor LangGraph
|
||||
uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.12 langgraph dev --allow-blocking
|
||||
```
|
||||
|
||||
##### Windows / Linux
|
||||
|
||||
```bash
|
||||
# Instala as dependências
|
||||
pip install -e .
|
||||
pip install -U "langgraph-cli[inmem]"
|
||||
|
||||
# Inicia o servidor LangGraph
|
||||
langgraph dev
|
||||
```
|
||||
|
||||
Após iniciar o servidor LangGraph, você verá diversas URLs no seu terminal:
|
||||
|
||||
- API: http://127.0.0.1:2024
|
||||
- Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
|
||||
- API Docs: http://127.0.0.1:2024/docs
|
||||
|
||||
Abra o link do Studio UI no seu navegador para acessar a interface de depuração.
|
||||
|
||||
#### Usando o LangGraph Studio
|
||||
|
||||
No Studio UI, você pode:
|
||||
|
||||
|
||||
1. Visualizar o grafo do fluxo de trabalho e como seus componentes se conectam
|
||||
2. Rastrear a execução em tempo-real e ver como os dados fluem através do sistema
|
||||
3. Inspecionar o estado de cada passo do fluxo de trabalho
|
||||
4. Depurar problemas ao examinar entradas e saídas de cada componente
|
||||
5. Coletar feedback durante a fase de planejamento para refinar os planos de pesquisa
|
||||
|
||||
Quando você envia um tópico de pesquisa ao Studio UI, você será capaz de ver toda a execução do fluxo de trabalho, incluindo:
|
||||
|
||||
- A fase de planejamento onde o plano de pesquisa foi criado
|
||||
- O processo de feedback onde você pode modificar o plano
|
||||
- As fases de pesquisa e escrita de cada seção
|
||||
- A geração do relatório final
|
||||
|
||||
## Docker
|
||||
|
||||
Você também pode executar esse projeto via Docker.
|
||||
|
||||
Primeiro, voce deve ler a [configuração](#configuration) below. Make sure `.env`, `.conf.yaml` files are ready.
|
||||
|
||||
Segundo, para fazer o build de sua imagem docker em seu próprio servidor:
|
||||
|
||||
```bash
|
||||
docker build -t deer-flow-api .
|
||||
```
|
||||
|
||||
E por fim, inicie um container docker rodando o servidor web:
|
||||
|
||||
```bash
|
||||
# substitua deer-flow-api-app com seu nome de container preferido
|
||||
docker run -d -t -p 8000:8000 --env-file .env --name deer-flow-api-app deer-flow-api
|
||||
|
||||
# pare o servidor
|
||||
docker stop deer-flow-api-app
|
||||
```
|
||||
|
||||
### Docker Compose (inclui ambos backend e frontend)
|
||||
|
||||
DeerFlow fornece uma estrutura docker-compose para facilmente executar ambos o backend e frontend juntos:
|
||||
|
||||
```bash
|
||||
# building docker image
|
||||
docker compose build
|
||||
|
||||
# start the server
|
||||
docker compose up
|
||||
```
|
||||
|
||||
## Exemplos:
|
||||
|
||||
Os seguintes exemplos demonstram as capacidades do DeerFlow:
|
||||
|
||||
### Relatórios de Pesquisa
|
||||
|
||||
1. **Relatório OpenAI Sora** - Análise da ferramenta Sora da OpenAI
|
||||
|
||||
- Discute funcionalidades, acesso, engenharia de prompt, limitações e considerações éticas
|
||||
|
||||
- [Veja o relatório completo](examples/openai_sora_report.md)
|
||||
|
||||
2. **Relatório Protocolo Agent-to-Agent do Google** - Visão geral do protocolo Agent-to-Agent (A2A) do Google
|
||||
|
||||
- Discute o seu papel na comunicação de Agente de IA e seu relacionamento com o Protocolo de Contexto de Modelo ( MCP ) da Anthropic
|
||||
- [Veja o relatório completo](examples/what_is_agent_to_agent_protocol.md)
|
||||
|
||||
3. **O que é MCP?** - Uma análise abrangente to termo "MCP" através de múltiplos contextos
|
||||
|
||||
- Explora o Protocolo de Contexto de Modelo em IA, Fosfato Monocálcio em Química, e placa de microcanal em eletrônica
|
||||
- [Veja o relatório completo](examples/what_is_mcp.md)
|
||||
|
||||
4. **Bitcoin Price Fluctuations** - Análise das recentes movimentações de preço do Bitcoin
|
||||
|
||||
- Examina tendências de mercado, influências regulatórias, e indicadores técnicos
|
||||
- Fornece recomendações baseadas nos dados históricos
|
||||
- [Veja o relatório completo](examples/bitcoin_price_fluctuation.md)
|
||||
|
||||
5. **O que é LLM?** - Uma exploração em profundidade de Large Language Models
|
||||
|
||||
- Discute arquitetura, treinamento, aplicações, e considerações éticas
|
||||
- [Veja o relatório completo](examples/what_is_llm.md)
|
||||
|
||||
6. **Como usar Claude para Pesquisa Aprofundada?** - Melhores práticas e fluxos de trabalho para usar Claude em pesquisa aprofundada
|
||||
|
||||
- Cobre engenharia de prompt, análise de dados, e integração com outras ferramentas
|
||||
- [Veja o relatório completo](examples/how_to_use_claude_deep_research.md)
|
||||
|
||||
7. **Adoção de IA na Área da Saúde: Fatores de Influência** - Análise dos fatores que levam à adoção de IA na área da saúde
|
||||
|
||||
- Discute tecnologias de IA, qualidade de dados, considerações éticas, avaliações econômicas, prontidão organizacional, e infraestrutura digital
|
||||
- [Veja o relatório completo](examples/AI_adoption_in_healthcare.md)
|
||||
|
||||
8. **Impacto da Computação Quântica em Criptografia** - Análise dos impactos da computação quântica em criptografia
|
||||
|
||||
- Discture vulnerabilidades da criptografia clássica, criptografia pós-quântica, e soluções criptográficas de resistência-quântica
|
||||
- [Veja o relatório completo](examples/Quantum_Computing_Impact_on_Cryptography.md)
|
||||
|
||||
9. **Destaques da Performance do Cristiano Ronaldo** - Análise dos destaques da performance do Cristiano Ronaldo
|
||||
- Discute as suas conquistas de carreira, objetivos internacionais, e performance em diversas partidas
|
||||
- [Veja o relatório completo](examples/Cristiano_Ronaldo's_Performance_Highlights.md)
|
||||
|
||||
Para executar esses exemplos ou criar seus próprios relatórios de pesquisa, você deve utilizar os seguintes comandos:
|
||||
|
||||
```bash
|
||||
# Executa com uma consulta específica
|
||||
uv run main.py "Quais fatores estão influenciando a adoção de IA na área da saúde?"
|
||||
|
||||
# Executa com parâmetros de planejamento customizados
|
||||
uv run main.py --max_plan_iterations 3 "Como a computação quântica impacta na criptografia?"
|
||||
|
||||
# Executa em modo interativo com questões embutidas
|
||||
uv run main.py --interactive
|
||||
|
||||
# Ou executa com um prompt interativo básico
|
||||
uv run main.py
|
||||
|
||||
# Vê todas as opções disponíveis
|
||||
uv run main.py --help
|
||||
```
|
||||
|
||||
### Modo Interativo
|
||||
|
||||
A aplicação agora suporta um modo interativo com questões embutidas tanto em Inglês quanto Chinês:
|
||||
|
||||
1. Inicie o modo interativo:
|
||||
|
||||
```bash
|
||||
uv run main.py --interactive
|
||||
```
|
||||
|
||||
2. Selecione sua linguagem de preferência (English or 中文)
|
||||
|
||||
3. Escolha uma das questões embutidas da lista ou selecione a opção para perguntar sua própria questão
|
||||
|
||||
4. O sistema irá processar sua questão e gerar um relatório abrangente de pesquisa
|
||||
|
||||
### Humano no processo
|
||||
|
||||
DeerFlow inclue um mecanismo de humano no processo que permite a você revisar, editar e aprovar planos de pesquisa antes que estes sejam executados:
|
||||
|
||||
1. **Revisão de Plano**: Quando o humano no processo está habilitado, o sistema irá apresentar o plano de pesquisa gerado para sua revisão antes da execução
|
||||
|
||||
2. **Fornecimento de Feedback**: Você pode:
|
||||
|
||||
- Aceitar o plano respondendo com `[ACCEPTED]`
|
||||
- Edite o plano fornecendo feedback (e.g., `[EDIT PLAN] Adicione mais passos sobre a implementação técnica`)
|
||||
- O sistema irá incorporar seu feedback e gerar um plano revisado
|
||||
|
||||
3. **Auto-aceite**: Você pode habilitar o auto-aceite ou pular o processo de revisão:
|
||||
|
||||
- Via API: Defina `auto_accepted_plan: true` na sua requisição
|
||||
|
||||
4. **Integração de API**: Quanto usar a API, você pode fornecer um feedback através do parâmetro `feedback`:
|
||||
```json
|
||||
{
|
||||
"messages": [{ "role": "user", "content": "O que é computação quântica?" }],
|
||||
"thread_id": "my_thread_id",
|
||||
"auto_accepted_plan": false,
|
||||
"feedback": "[EDIT PLAN] Inclua mais sobre algoritmos quânticos"
|
||||
}
|
||||
```
|
||||
|
||||
### Argumentos via Linha de Comando
|
||||
|
||||
A aplicação suporta diversos argumentos via linha de comando para customizar o seu comportamento:
|
||||
|
||||
- **consulta**: A consulta de pesquisa a ser processada (podem ser múltiplas palavras)
|
||||
- **--interativo**: Roda no modo interativo com questões embutidas
|
||||
- **--max_plan_iterations**: Número máximo de ciclos de planejamento (padrão: 1)
|
||||
- **--max_step_num**: Número máximo de passos em um plano de pesquisa (padrão: 3)
|
||||
- **--debug**: Habilita Enable um log de depuração detalhado
|
||||
|
||||
## FAQ
|
||||
|
||||
Por favor consulte a [FAQ.md](docs/FAQ.md) para maiores detalhes.
|
||||
|
||||
## Licença
|
||||
|
||||
Esse projeto é open source e disponível sob a [MIT License](./LICENSE).
|
||||
|
||||
## Agradecimentos
|
||||
|
||||
DeerFlow é construído através do incrível trabalho da comunidade open-source. Nós somos profundamente gratos a todos os projetos e contribuidores cujos esforços tornaram o DeerFlow possível. Realmente, nós estamos apoiados nos ombros de gigantes.
|
||||
|
||||
Nós gostaríamos de extender nossos sinceros agradecimentos aos seguintes projetos por suas invaloráveis contribuições:
|
||||
|
||||
- **[LangChain](https://github.com/langchain-ai/langchain)**: O framework excepcional deles empodera nossas interações via LLM e correntes, permitindo uma integração perfeita e funcional.
|
||||
- **[LangGraph](https://github.com/langchain-ai/langgraph)**: A abordagem inovativa para orquestração multi-agente deles tem sido foi fundamental em permitir o acesso dos fluxos de trabalho sofisticados do DeerFlow.
|
||||
|
||||
Esses projetos exemplificam o poder transformador da colaboração open-source, e nós temos orgulho de construir baseado em suas fundações.
|
||||
|
||||
### Contribuidores-Chave
|
||||
|
||||
Um sincero muito obrigado vai para os principais autores do `DeerFlow`, cuja visão, paixão, e dedicação trouxe esse projeto à vida:
|
||||
|
||||
- **[Daniel Walnut](https://github.com/hetaoBackend/)**
|
||||
- **[Henry Li](https://github.com/magiccube/)**
|
||||
|
||||
O seu compromisso inabalável e experiência tem sido a força por trás do sucesso do DeerFlow. Nós estamos honrados em tê-los no comando dessa trajetória.
|
||||
|
||||
## Histórico-Estrelas
|
||||
|
||||
[](https://star-history.com/#bytedance/deer-flow&Date)
|
||||
+554
@@ -0,0 +1,554 @@
|
||||
# 🦌 DeerFlow
|
||||
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://deepwiki.com/bytedance/deer-flow)
|
||||
<!-- DeepWiki badge generated by https://deepwiki.ryoppippi.com/ -->
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)
|
||||
|
||||
> Создано на базе открытого кода, возвращено в открытый код.
|
||||
|
||||
**DeerFlow** (**D**eep **E**xploration and **E**fficient **R**esearch **Flow**) - это фреймворк для глубокого исследования, разработанный сообществом и основанный на впечатляющей работе сообщества открытого кода. Наша цель - объединить языковые модели со специализированными инструментами для таких задач, как веб-поиск, сканирование и выполнение кода Python, одновременно возвращая пользу сообществу, которое сделало это возможным.
|
||||
|
||||
Пожалуйста, посетите [наш официальный сайт](https://deerflow.tech/) для получения дополнительной информации.
|
||||
|
||||
## Демонстрация
|
||||
|
||||
### Видео
|
||||
|
||||
https://github.com/user-attachments/assets/f3786598-1f2a-4d07-919e-8b99dfa1de3e
|
||||
|
||||
В этой демонстрации мы показываем, как использовать DeerFlow для:
|
||||
|
||||
- Бесшовной интеграции с сервисами MCP
|
||||
- Проведения процесса глубокого исследования и создания комплексного отчета с изображениями
|
||||
- Создания аудио подкаста на основе сгенерированного отчета
|
||||
|
||||
### Повторы
|
||||
|
||||
- [Какова высота Эйфелевой башни по сравнению с самым высоким зданием?](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)
|
||||
- [Какие репозитории самые популярные на GitHub?](https://deerflow.tech/chat?replay=github-top-trending-repo)
|
||||
- [Написать статью о традиционных блюдах Нанкина](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)
|
||||
- [Как украсить съемную квартиру?](https://deerflow.tech/chat?replay=rental-apartment-decoration)
|
||||
- [Посетите наш официальный сайт, чтобы изучить больше повторов.](https://deerflow.tech/#case-studies)
|
||||
|
||||
---
|
||||
|
||||
## 📑 Оглавление
|
||||
|
||||
- [🚀 Быстрый старт](#быстрый-старт)
|
||||
- [🌟 Особенности](#особенности)
|
||||
- [🏗️ Архитектура](#архитектура)
|
||||
- [🛠️ Разработка](#разработка)
|
||||
- [🐳 Docker](#docker)
|
||||
- [🗣️ Интеграция преобразования текста в речь](#интеграция-преобразования-текста-в-речь)
|
||||
- [📚 Примеры](#примеры)
|
||||
- [❓ FAQ](#faq)
|
||||
- [📜 Лицензия](#лицензия)
|
||||
- [💖 Благодарности](#благодарности)
|
||||
- [⭐ История звезд](#история-звезд)
|
||||
|
||||
## Быстрый старт
|
||||
|
||||
DeerFlow разработан на Python и поставляется с веб-интерфейсом, написанным на Node.js. Для обеспечения плавного процесса настройки мы рекомендуем использовать следующие инструменты:
|
||||
|
||||
### Рекомендуемые инструменты
|
||||
|
||||
- **[`uv`](https://docs.astral.sh/uv/getting-started/installation/):**
|
||||
Упрощает управление средой Python и зависимостями. `uv` автоматически создает виртуальную среду в корневом каталоге и устанавливает все необходимые пакеты за вас—без необходимости вручную устанавливать среды Python.
|
||||
|
||||
- **[`nvm`](https://github.com/nvm-sh/nvm):**
|
||||
Легко управляйте несколькими версиями среды выполнения Node.js.
|
||||
|
||||
- **[`pnpm`](https://pnpm.io/installation):**
|
||||
Установка и управление зависимостями проекта Node.js.
|
||||
|
||||
### Требования к среде
|
||||
|
||||
Убедитесь, что ваша система соответствует следующим минимальным требованиям:
|
||||
|
||||
- **[Python](https://www.python.org/downloads/):** Версия `3.12+`
|
||||
- **[Node.js](https://nodejs.org/en/download/):** Версия `22+`
|
||||
|
||||
### Установка
|
||||
|
||||
```bash
|
||||
# Клонировать репозиторий
|
||||
git clone https://github.com/bytedance/deer-flow.git
|
||||
cd deer-flow
|
||||
|
||||
# Установить зависимости, uv позаботится об интерпретаторе python и создании venv, и установит необходимые пакеты
|
||||
uv sync
|
||||
|
||||
# Настроить .env с вашими API-ключами
|
||||
# Tavily: https://app.tavily.com/home
|
||||
# Brave_SEARCH: https://brave.com/search/api/
|
||||
# volcengine TTS: Добавьте ваши учетные данные TTS, если они у вас есть
|
||||
cp .env.example .env
|
||||
|
||||
# См. разделы 'Поддерживаемые поисковые системы' и 'Интеграция преобразования текста в речь' ниже для всех доступных опций
|
||||
|
||||
# Настроить conf.yaml для вашей модели LLM и API-ключей
|
||||
# Пожалуйста, обратитесь к 'docs/configuration_guide.md' для получения дополнительной информации
|
||||
cp conf.yaml.example conf.yaml
|
||||
|
||||
# Установить marp для генерации презентаций
|
||||
# https://github.com/marp-team/marp-cli?tab=readme-ov-file#use-package-manager
|
||||
brew install marp-cli
|
||||
```
|
||||
|
||||
По желанию установите зависимости веб-интерфейса через [pnpm](https://pnpm.io/installation):
|
||||
|
||||
```bash
|
||||
cd deer-flow/web
|
||||
pnpm install
|
||||
```
|
||||
|
||||
### Конфигурации
|
||||
|
||||
Пожалуйста, обратитесь к [Руководству по конфигурации](docs/configuration_guide.md) для получения дополнительной информации.
|
||||
|
||||
> [!ПРИМЕЧАНИЕ]
|
||||
> Прежде чем запустить проект, внимательно прочитайте руководство и обновите конфигурации в соответствии с вашими конкретными настройками и требованиями.
|
||||
|
||||
### Консольный интерфейс
|
||||
|
||||
Самый быстрый способ запустить проект - использовать консольный интерфейс.
|
||||
|
||||
```bash
|
||||
# Запустить проект в оболочке, похожей на bash
|
||||
uv run main.py
|
||||
```
|
||||
|
||||
### Веб-интерфейс
|
||||
|
||||
Этот проект также включает веб-интерфейс, предлагающий более динамичный и привлекательный интерактивный опыт.
|
||||
|
||||
> [!ПРИМЕЧАНИЕ]
|
||||
> Сначала вам нужно установить зависимости веб-интерфейса.
|
||||
|
||||
```bash
|
||||
# Запустить оба сервера, бэкенд и фронтенд, в режиме разработки
|
||||
# На macOS/Linux
|
||||
./bootstrap.sh -d
|
||||
|
||||
# На Windows
|
||||
bootstrap.bat -d
|
||||
```
|
||||
|
||||
Откройте ваш браузер и посетите [`http://localhost:3000`](http://localhost:3000), чтобы исследовать веб-интерфейс.
|
||||
|
||||
Исследуйте больше деталей в каталоге [`web`](./web/).
|
||||
|
||||
## Поддерживаемые поисковые системы
|
||||
|
||||
DeerFlow поддерживает несколько поисковых систем, которые можно настроить в файле `.env` с помощью переменной `SEARCH_API`:
|
||||
|
||||
- **Tavily** (по умолчанию): Специализированный поисковый API для приложений ИИ
|
||||
|
||||
- Требуется `TAVILY_API_KEY` в вашем файле `.env`
|
||||
- Зарегистрируйтесь на: https://app.tavily.com/home
|
||||
|
||||
- **DuckDuckGo**: Поисковая система, ориентированная на конфиденциальность
|
||||
|
||||
- Не требуется API-ключ
|
||||
|
||||
- **Brave Search**: Поисковая система, ориентированная на конфиденциальность, с расширенными функциями
|
||||
|
||||
- Требуется `BRAVE_SEARCH_API_KEY` в вашем файле `.env`
|
||||
- Зарегистрируйтесь на: https://brave.com/search/api/
|
||||
|
||||
- **Arxiv**: Поиск научных статей для академических исследований
|
||||
- Не требуется API-ключ
|
||||
- Специализируется на научных и академических статьях
|
||||
|
||||
Чтобы настроить предпочитаемую поисковую систему, установите переменную `SEARCH_API` в вашем файле `.env`:
|
||||
|
||||
```bash
|
||||
# Выберите одно: tavily, duckduckgo, brave_search, arxiv
|
||||
SEARCH_API=tavily
|
||||
```
|
||||
|
||||
## Особенности
|
||||
|
||||
### Ключевые возможности
|
||||
|
||||
- 🤖 **Интеграция LLM**
|
||||
- Поддерживает интеграцию большинства моделей через [litellm](https://docs.litellm.ai/docs/providers).
|
||||
- Поддержка моделей с открытым исходным кодом, таких как Qwen
|
||||
- API-интерфейс, совместимый с OpenAI
|
||||
- Многоуровневая система LLM для задач различной сложности
|
||||
|
||||
### Инструменты и интеграции MCP
|
||||
|
||||
- 🔍 **Поиск и извлечение**
|
||||
|
||||
- Веб-поиск через Tavily, Brave Search и другие
|
||||
- Сканирование с Jina
|
||||
- Расширенное извлечение контента
|
||||
|
||||
- 🔗 **Бесшовная интеграция MCP**
|
||||
- Расширение возможностей для доступа к частным доменам, графам знаний, веб-браузингу и многому другому
|
||||
- Облегчает интеграцию различных исследовательских инструментов и методологий
|
||||
|
||||
### Человеческое взаимодействие
|
||||
|
||||
- 🧠 **Человек в контуре**
|
||||
|
||||
- Поддерживает интерактивное изменение планов исследования с использованием естественного языка
|
||||
- Поддерживает автоматическое принятие планов исследования
|
||||
|
||||
- 📝 **Пост-редактирование отчетов**
|
||||
- Поддерживает блочное редактирование в стиле Notion
|
||||
- Позволяет совершенствовать с помощью ИИ, включая полировку, сокращение и расширение предложений
|
||||
- Работает на [tiptap](https://tiptap.dev/)
|
||||
|
||||
### Создание контента
|
||||
|
||||
- 🎙️ **Генерация подкастов и презентаций**
|
||||
- Генерация сценариев подкастов и синтез аудио с помощью ИИ
|
||||
- Автоматическое создание простых презентаций PowerPoint
|
||||
- Настраиваемые шаблоны для индивидуального контента
|
||||
|
||||
## Архитектура
|
||||
|
||||
DeerFlow реализует модульную архитектуру системы с несколькими агентами, предназначенную для автоматизированных исследований и анализа кода. Система построена на LangGraph, обеспечивающей гибкий рабочий процесс на основе состояний, где компоненты взаимодействуют через четко определенную систему передачи сообщений.
|
||||
|
||||
|
||||
|
||||
> Посмотрите вживую на [deerflow.tech](https://deerflow.tech/#multi-agent-architecture)
|
||||
|
||||
В системе используется оптимизированный рабочий процесс со следующими компонентами:
|
||||
|
||||
1. **Координатор**: Точка входа, управляющая жизненным циклом рабочего процесса
|
||||
|
||||
- Инициирует процесс исследования на основе пользовательского ввода
|
||||
- Делегирует задачи планировщику, когда это необходимо
|
||||
- Выступает в качестве основного интерфейса между пользователем и системой
|
||||
|
||||
2. **Планировщик**: Стратегический компонент для декомпозиции и планирования задач
|
||||
|
||||
- Анализирует цели исследования и создает структурированные планы выполнения
|
||||
- Определяет, достаточно ли доступного контекста или требуется дополнительное исследование
|
||||
- Управляет потоком исследования и решает, когда генерировать итоговый отчет
|
||||
|
||||
3. **Исследовательская команда**: Набор специализированных агентов, которые выполняют план:
|
||||
|
||||
- **Исследователь**: Проводит веб-поиск и сбор информации с использованием таких инструментов, как поисковые системы, сканирование и даже сервисы MCP.
|
||||
- **Программист**: Обрабатывает анализ кода, выполнение и технические задачи с помощью инструмента Python REPL.
|
||||
Каждый агент имеет доступ к определенным инструментам, оптимизированным для его роли, и работает в рамках фреймворка LangGraph
|
||||
|
||||
4. **Репортер**: Процессор финальной стадии для результатов исследования
|
||||
- Агрегирует находки исследовательской команды
|
||||
- Обрабатывает и структурирует собранную информацию
|
||||
- Генерирует комплексные исследовательские отчеты
|
||||
|
||||
## Интеграция преобразования текста в речь
|
||||
|
||||
DeerFlow теперь включает функцию преобразования текста в речь (TTS), которая позволяет конвертировать исследовательские отчеты в речь. Эта функция использует API TTS volcengine для генерации высококачественного аудио из текста. Также можно настраивать такие параметры, как скорость, громкость и тон.
|
||||
|
||||
### Использование API TTS
|
||||
|
||||
Вы можете получить доступ к функциональности TTS через конечную точку `/api/tts`:
|
||||
|
||||
```bash
|
||||
# Пример вызова API с использованием curl
|
||||
curl --location 'http://localhost:8000/api/tts' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"text": "Это тест функциональности преобразования текста в речь.",
|
||||
"speed_ratio": 1.0,
|
||||
"volume_ratio": 1.0,
|
||||
"pitch_ratio": 1.0
|
||||
}' \
|
||||
--output speech.mp3
|
||||
```
|
||||
|
||||
## Разработка
|
||||
|
||||
### Тестирование
|
||||
|
||||
Запустите набор тестов:
|
||||
|
||||
```bash
|
||||
# Запустить все тесты
|
||||
make test
|
||||
|
||||
# Запустить определенный тестовый файл
|
||||
pytest tests/integration/test_workflow.py
|
||||
|
||||
# Запустить с покрытием
|
||||
make coverage
|
||||
```
|
||||
|
||||
### Качество кода
|
||||
|
||||
```bash
|
||||
# Запустить линтинг
|
||||
make lint
|
||||
|
||||
# Форматировать код
|
||||
make format
|
||||
```
|
||||
|
||||
### Отладка с LangGraph Studio
|
||||
|
||||
DeerFlow использует LangGraph для своей архитектуры рабочего процесса. Вы можете использовать LangGraph Studio для отладки и визуализации рабочего процесса в реальном времени.
|
||||
|
||||
#### Запуск LangGraph Studio локально
|
||||
|
||||
DeerFlow включает конфигурационный файл `langgraph.json`, который определяет структуру графа и зависимости для LangGraph Studio. Этот файл указывает на графы рабочего процесса, определенные в проекте, и автоматически загружает переменные окружения из файла `.env`.
|
||||
|
||||
##### Mac
|
||||
|
||||
```bash
|
||||
# Установите менеджер пакетов uv, если у вас его нет
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
|
||||
# Установите зависимости и запустите сервер LangGraph
|
||||
uvx --refresh --from "langgraph-cli[inmem]" --with-editable . --python 3.12 langgraph dev --allow-blocking
|
||||
```
|
||||
|
||||
##### Windows / Linux
|
||||
|
||||
```bash
|
||||
# Установить зависимости
|
||||
pip install -e .
|
||||
pip install -U "langgraph-cli[inmem]"
|
||||
|
||||
# Запустить сервер LangGraph
|
||||
langgraph dev
|
||||
```
|
||||
|
||||
После запуска сервера LangGraph вы увидите несколько URL в терминале:
|
||||
|
||||
- API: http://127.0.0.1:2024
|
||||
- Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
|
||||
- API Docs: http://127.0.0.1:2024/docs
|
||||
|
||||
Откройте ссылку Studio UI в вашем браузере для доступа к интерфейсу отладки.
|
||||
|
||||
#### Использование LangGraph Studio
|
||||
|
||||
В интерфейсе Studio вы можете:
|
||||
|
||||
1. Визуализировать граф рабочего процесса и видеть, как соединяются компоненты
|
||||
2. Отслеживать выполнение в реальном времени, чтобы видеть, как данные проходят через систему
|
||||
3. Исследовать состояние на каждом шаге рабочего процесса
|
||||
4. Отлаживать проблемы путем изучения входов и выходов каждого компонента
|
||||
5. Предоставлять обратную связь во время фазы планирования для уточнения планов исследования
|
||||
|
||||
Когда вы отправляете тему исследования в интерфейсе Studio, вы сможете увидеть весь процесс выполнения рабочего процесса, включая:
|
||||
|
||||
- Фазу планирования, где создается план исследования
|
||||
- Цикл обратной связи, где вы можете модифицировать план
|
||||
- Фазы исследования и написания для каждого раздела
|
||||
- Генерацию итогового отчета
|
||||
|
||||
### Включение трассировки LangSmith
|
||||
|
||||
DeerFlow поддерживает трассировку LangSmith, чтобы помочь вам отладить и контролировать ваши рабочие процессы. Чтобы включить трассировку LangSmith:
|
||||
|
||||
1. Убедитесь, что в вашем файле `.env` есть следующие конфигурации (см. `.env.example`):
|
||||
```bash
|
||||
LANGSMITH_TRACING=true
|
||||
LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
|
||||
LANGSMITH_API_KEY="xxx"
|
||||
LANGSMITH_PROJECT="xxx"
|
||||
```
|
||||
|
||||
2. Запустите трассировку и визуализируйте граф локально с LangSmith, выполнив:
|
||||
```bash
|
||||
langgraph dev
|
||||
```
|
||||
|
||||
Это включит визуализацию трассировки в LangGraph Studio и отправит ваши трассировки в LangSmith для мониторинга и анализа.
|
||||
|
||||
## Docker
|
||||
|
||||
Вы также можете запустить этот проект с Docker.
|
||||
|
||||
Во-первых, вам нужно прочитать [конфигурацию](docs/configuration_guide.md) ниже. Убедитесь, что файлы `.env`, `.conf.yaml` готовы.
|
||||
|
||||
Во-вторых, чтобы построить Docker-образ вашего собственного веб-сервера:
|
||||
|
||||
```bash
|
||||
docker build -t deer-flow-api .
|
||||
```
|
||||
|
||||
Наконец, запустите Docker-контейнер с веб-сервером:
|
||||
|
||||
```bash
|
||||
# Замените deer-flow-api-app на предпочитаемое вами имя контейнера
|
||||
docker run -d -t -p 8000:8000 --env-file .env --name deer-flow-api-app deer-flow-api
|
||||
|
||||
# остановить сервер
|
||||
docker stop deer-flow-api-app
|
||||
```
|
||||
|
||||
### Docker Compose (включает как бэкенд, так и фронтенд)
|
||||
|
||||
DeerFlow предоставляет настройку docker-compose для легкого запуска бэкенда и фронтенда вместе:
|
||||
|
||||
```bash
|
||||
# сборка docker-образа
|
||||
docker compose build
|
||||
|
||||
# запуск сервера
|
||||
docker compose up
|
||||
```
|
||||
|
||||
## Примеры
|
||||
|
||||
Следующие примеры демонстрируют возможности DeerFlow:
|
||||
|
||||
### Исследовательские отчеты
|
||||
|
||||
1. **Отчет о OpenAI Sora** - Анализ инструмента ИИ Sora от OpenAI
|
||||
|
||||
- Обсуждаются функции, доступ, инженерия промптов, ограничения и этические соображения
|
||||
- [Просмотреть полный отчет](examples/openai_sora_report.md)
|
||||
|
||||
2. **Отчет о протоколе Agent to Agent от Google** - Обзор протокола Agent to Agent (A2A) от Google
|
||||
|
||||
- Обсуждается его роль в коммуникации агентов ИИ и его отношение к протоколу Model Context Protocol (MCP) от Anthropic
|
||||
- [Просмотреть полный отчет](examples/what_is_agent_to_agent_protocol.md)
|
||||
|
||||
3. **Что такое MCP?** - Комплексный анализ термина "MCP" в различных контекстах
|
||||
|
||||
- Исследует Model Context Protocol в ИИ, Монокальцийфосфат в химии и Микроканальные пластины в электронике
|
||||
- [Просмотреть полный отчет](examples/what_is_mcp.md)
|
||||
|
||||
4. **Колебания цены Биткоина** - Анализ недавних движений цены Биткоина
|
||||
|
||||
- Исследует рыночные тренды, регуляторные влияния и технические индикаторы
|
||||
- Предоставляет рекомендации на основе исторических данных
|
||||
- [Просмотреть полный отчет](examples/bitcoin_price_fluctuation.md)
|
||||
|
||||
5. **Что такое LLM?** - Углубленное исследование больших языковых моделей
|
||||
|
||||
- Обсуждаются архитектура, обучение, приложения и этические соображения
|
||||
- [Просмотреть полный отчет](examples/what_is_llm.md)
|
||||
|
||||
6. **Как использовать Claude для глубокого исследования?** - Лучшие практики и рабочие процессы для использования Claude в глубоком исследовании
|
||||
|
||||
- Охватывает инженерию промптов, анализ данных и интеграцию с другими инструментами
|
||||
- [Просмотреть полный отчет](examples/how_to_use_claude_deep_research.md)
|
||||
|
||||
7. **Внедрение ИИ в здравоохранении: Влияющие факторы** - Анализ факторов, движущих внедрением ИИ в здравоохранении
|
||||
|
||||
- Обсуждаются технологии ИИ, качество данных, этические соображения, экономические оценки, организационная готовность и цифровая инфраструктура
|
||||
- [Просмотреть полный отчет](examples/AI_adoption_in_healthcare.md)
|
||||
|
||||
8. **Влияние квантовых вычислений на криптографию** - Анализ влияния квантовых вычислений на криптографию
|
||||
|
||||
- Обсуждаются уязвимости классической криптографии, пост-квантовая криптография и криптографические решения, устойчивые к квантовым вычислениям
|
||||
- [Просмотреть полный отчет](examples/Quantum_Computing_Impact_on_Cryptography.md)
|
||||
|
||||
9. **Ключевые моменты выступлений Криштиану Роналду** - Анализ выдающихся выступлений Криштиану Роналду
|
||||
- Обсуждаются его карьерные достижения, международные голы и выступления в различных матчах
|
||||
- [Просмотреть полный отчет](examples/Cristiano_Ronaldo's_Performance_Highlights.md)
|
||||
|
||||
Чтобы запустить эти примеры или создать собственные исследовательские отчеты, вы можете использовать следующие команды:
|
||||
|
||||
```bash
|
||||
# Запустить с определенным запросом
|
||||
uv run main.py "Какие факторы влияют на внедрение ИИ в здравоохранении?"
|
||||
|
||||
# Запустить с пользовательскими параметрами планирования
|
||||
uv run main.py --max_plan_iterations 3 "Как квантовые вычисления влияют на криптографию?"
|
||||
|
||||
# Запустить в интерактивном режиме с встроенными вопросами
|
||||
uv run main.py --interactive
|
||||
|
||||
# Или запустить с базовым интерактивным приглашением
|
||||
uv run main.py
|
||||
|
||||
# Посмотреть все доступные опции
|
||||
uv run main.py --help
|
||||
```
|
||||
|
||||
### Интерактивный режим
|
||||
|
||||
Приложение теперь поддерживает интерактивный режим с встроенными вопросами как на английском, так и на китайском языках:
|
||||
|
||||
1. Запустите интерактивный режим:
|
||||
|
||||
```bash
|
||||
uv run main.py --interactive
|
||||
```
|
||||
|
||||
2. Выберите предпочитаемый язык (English или 中文)
|
||||
|
||||
3. Выберите из списка встроенных вопросов или выберите опцию задать собственный вопрос
|
||||
|
||||
4. Система обработает ваш вопрос и сгенерирует комплексный исследовательский отчет
|
||||
|
||||
### Человек в контуре
|
||||
|
||||
DeerFlow включает механизм "человек в контуре", который позволяет вам просматривать, редактировать и утверждать планы исследования перед их выполнением:
|
||||
|
||||
1. **Просмотр плана**: Когда активирован режим "человек в контуре", система представит сгенерированный план исследования для вашего просмотра перед выполнением
|
||||
|
||||
2. **Предоставление обратной связи**: Вы можете:
|
||||
|
||||
- Принять план, ответив `[ACCEPTED]`
|
||||
- Отредактировать план, предоставив обратную связь (например, `[EDIT PLAN] Добавить больше шагов о технической реализации`)
|
||||
- Система включит вашу обратную связь и сгенерирует пересмотренный план
|
||||
|
||||
3. **Автоматическое принятие**: Вы можете включить автоматическое принятие, чтобы пропустить процесс просмотра:
|
||||
|
||||
- Через API: Установите `auto_accepted_plan: true` в вашем запросе
|
||||
|
||||
4. **Интеграция API**: При использовании API вы можете предоставить обратную связь через параметр `feedback`:
|
||||
```json
|
||||
{
|
||||
"messages": [{ "role": "user", "content": "Что такое квантовые вычисления?" }],
|
||||
"thread_id": "my_thread_id",
|
||||
"auto_accepted_plan": false,
|
||||
"feedback": "[EDIT PLAN] Включить больше о квантовых алгоритмах"
|
||||
}
|
||||
```
|
||||
|
||||
### Аргументы командной строки
|
||||
|
||||
Приложение поддерживает несколько аргументов командной строки для настройки его поведения:
|
||||
|
||||
- **query**: Запрос исследования для обработки (может состоять из нескольких слов)
|
||||
- **--interactive**: Запустить в интерактивном режиме с встроенными вопросами
|
||||
- **--max_plan_iterations**: Максимальное количество циклов планирования (по умолчанию: 1)
|
||||
- **--max_step_num**: Максимальное количество шагов в плане исследования (по умолчанию: 3)
|
||||
- **--debug**: Включить подробное логирование отладки
|
||||
|
||||
## FAQ
|
||||
|
||||
Пожалуйста, обратитесь к [FAQ.md](docs/FAQ.md) для получения дополнительной информации.
|
||||
|
||||
## Лицензия
|
||||
|
||||
Этот проект имеет открытый исходный код и доступен под [Лицензией MIT](./LICENSE).
|
||||
|
||||
## Благодарности
|
||||
|
||||
DeerFlow создан на основе невероятной работы сообщества открытого кода. Мы глубоко благодарны всем проектам и контрибьюторам, чьи усилия сделали DeerFlow возможным. Поистине, мы стоим на плечах гигантов.
|
||||
|
||||
Мы хотели бы выразить искреннюю признательность следующим проектам за их неоценимый вклад:
|
||||
|
||||
- **[LangChain](https://github.com/langchain-ai/langchain)**: Их исключительный фреймворк обеспечивает наши взаимодействия и цепочки LLM, позволяя бесшовную интеграцию и функциональность.
|
||||
- **[LangGraph](https://github.com/langchain-ai/langgraph)**: Их инновационный подход к оркестровке многоагентных систем сыграл решающую роль в обеспечении сложных рабочих процессов DeerFlow.
|
||||
|
||||
Эти проекты являются примером преобразующей силы сотрудничества в области открытого кода, и мы гордимся тем, что строим на их основе.
|
||||
|
||||
### Ключевые контрибьюторы
|
||||
|
||||
Сердечная благодарность основным авторам `DeerFlow`, чье видение, страсть и преданность делу вдохнули жизнь в этот проект:
|
||||
|
||||
- **[Daniel Walnut](https://github.com/hetaoBackend/)**
|
||||
- **[Henry Li](https://github.com/magiccube/)**
|
||||
|
||||
Ваша непоколебимая приверженность и опыт стали движущей силой успеха DeerFlow. Мы считаем за честь иметь вас во главе этого путешествия.
|
||||
|
||||
## История звезд
|
||||
|
||||
[](https://star-history.com/#bytedance/deer-flow&Date)
|
||||
+1
-1
@@ -3,7 +3,7 @@
|
||||
[](https://www.python.org/downloads/)
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md)
|
||||
[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) |[Portuguese](./README_pt.md)
|
||||
|
||||
> 源于开源，回馈开源。
|
||||
|
||||
|
||||
+3
-2
@@ -10,9 +10,10 @@ IF "%MODE%"=="development" GOTO DEV
|
||||
|
||||
:PROD
|
||||
echo Starting DeerFlow in [PRODUCTION] mode...
|
||||
uv run server.py
|
||||
start uv run server.py
|
||||
cd web
|
||||
pnpm start
|
||||
start pnpm start
|
||||
REM Wait for user to close
|
||||
GOTO END
|
||||
|
||||
:DEV
|
||||
|
||||
+4
-2
@@ -11,6 +11,8 @@ if [ "$1" = "--dev" -o "$1" = "-d" -o "$1" = "dev" -o "$1" = "development" ]; th
|
||||
wait
|
||||
else
|
||||
echo -e "Starting DeerFlow in [PRODUCTION] mode...\n"
|
||||
uv run server.py
|
||||
cd web && pnpm start
|
||||
uv run server.py & SERVER_PID=$$!
|
||||
cd web && pnpm start & WEB_PID=$$!
|
||||
trap "kill $$SERVER_PID $$WEB_PID" SIGINT SIGTERM
|
||||
wait
|
||||
fi
|
||||
|
||||
@@ -37,6 +37,7 @@ dependencies = [
|
||||
[project.optional-dependencies]
|
||||
dev = [
|
||||
"black>=24.2.0",
|
||||
"langgraph-cli[inmem]>=0.2.10",
|
||||
]
|
||||
test = [
|
||||
"pytest>=7.4.0",
|
||||
@@ -52,6 +53,9 @@ filterwarnings = [
|
||||
"ignore::UserWarning",
|
||||
]
|
||||
|
||||
[tool.coverage.report]
|
||||
fail_under = 25
|
||||
|
||||
[tool.hatch.build.targets.wheel]
|
||||
packages = ["src"]
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
||||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from .agents import research_agent, coder_agent
|
||||
from .agents import create_agent
|
||||
|
||||
__all__ = ["research_agent", "coder_agent"]
|
||||
__all__ = ["create_agent"]
|
||||
|
||||
@@ -4,12 +4,6 @@
|
||||
from langgraph.prebuilt import create_react_agent
|
||||
|
||||
from src.prompts import apply_prompt_template
|
||||
from src.tools import (
|
||||
crawl_tool,
|
||||
python_repl_tool,
|
||||
web_search_tool,
|
||||
)
|
||||
|
||||
from src.llms.llm import get_llm_by_type
|
||||
from src.config.agents import AGENT_LLM_MAP
|
||||
|
||||
@@ -23,10 +17,3 @@ def create_agent(agent_name: str, agent_type: str, tools: list, prompt_template:
|
||||
tools=tools,
|
||||
prompt=lambda state: apply_prompt_template(prompt_template, state),
|
||||
)
|
||||
|
||||
|
||||
# Create agents using the factory function
|
||||
research_agent = create_agent(
|
||||
"researcher", "researcher", [web_search_tool, crawl_tool], "researcher"
|
||||
)
|
||||
coder_agent = create_agent("coder", "coder", [python_repl_tool], "coder")
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
||||
# SPDX-License-Identifier: MIT
|
||||
|
||||
from .tools import SEARCH_MAX_RESULTS, SELECTED_SEARCH_ENGINE, SearchEngine
|
||||
from .tools import SELECTED_SEARCH_ENGINE, SearchEngine
|
||||
from .loader import load_yaml_config
|
||||
from .questions import BUILT_IN_QUESTIONS, BUILT_IN_QUESTIONS_ZH_CN
|
||||
|
||||
@@ -42,7 +42,6 @@ __all__ = [
|
||||
# Other configurations
|
||||
"TEAM_MEMBERS",
|
||||
"TEAM_MEMBER_CONFIGRATIONS",
|
||||
"SEARCH_MAX_RESULTS",
|
||||
"SELECTED_SEARCH_ENGINE",
|
||||
"SearchEngine",
|
||||
"BUILT_IN_QUESTIONS",
|
||||
|
||||
@@ -14,6 +14,7 @@ class Configuration:
|
||||
|
||||
max_plan_iterations: int = 1 # Maximum number of plan iterations
|
||||
max_step_num: int = 3 # Maximum number of steps in a plan
|
||||
max_search_results: int = 3 # Maximum number of search results
|
||||
mcp_settings: dict = None # MCP settings, including dynamic loaded tools
|
||||
|
||||
@classmethod
|
||||
|
||||
@@ -17,4 +17,3 @@ class SearchEngine(enum.Enum):
|
||||
|
||||
# Tool configuration
|
||||
SELECTED_SEARCH_ENGINE = os.getenv("SEARCH_API", SearchEngine.TAVILY.value)
|
||||
SEARCH_MAX_RESULTS = 3
|
||||
|
||||
+66
-22
@@ -3,6 +3,7 @@
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from typing import Annotated, Literal
|
||||
|
||||
from langchain_core.messages import AIMessage, HumanMessage
|
||||
@@ -11,12 +12,11 @@ from langchain_core.tools import tool
|
||||
from langgraph.types import Command, interrupt
|
||||
from langchain_mcp_adapters.client import MultiServerMCPClient
|
||||
|
||||
from src.agents.agents import coder_agent, research_agent, create_agent
|
||||
|
||||
from src.agents import create_agent
|
||||
from src.tools.search import LoggedTavilySearch
|
||||
from src.tools import (
|
||||
crawl_tool,
|
||||
web_search_tool,
|
||||
get_web_search_tool,
|
||||
python_repl_tool,
|
||||
)
|
||||
|
||||
@@ -28,7 +28,7 @@ from src.prompts.template import apply_prompt_template
|
||||
from src.utils.json_utils import repair_json_output
|
||||
|
||||
from .types import State
|
||||
from ..config import SEARCH_MAX_RESULTS, SELECTED_SEARCH_ENGINE, SearchEngine
|
||||
from ..config import SELECTED_SEARCH_ENGINE, SearchEngine
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -44,13 +44,16 @@ def handoff_to_planner(
|
||||
return
|
||||
|
||||
|
||||
def background_investigation_node(state: State) -> Command[Literal["planner"]]:
|
||||
def background_investigation_node(
|
||||
state: State, config: RunnableConfig
|
||||
) -> Command[Literal["planner"]]:
|
||||
logger.info("background investigation node is running.")
|
||||
configurable = Configuration.from_runnable_config(config)
|
||||
query = state["messages"][-1].content
|
||||
if SELECTED_SEARCH_ENGINE == SearchEngine.TAVILY:
|
||||
searched_content = LoggedTavilySearch(max_results=SEARCH_MAX_RESULTS).invoke(
|
||||
{"query": query}
|
||||
)
|
||||
searched_content = LoggedTavilySearch(
|
||||
max_results=configurable.max_search_results
|
||||
).invoke({"query": query})
|
||||
background_investigation_results = None
|
||||
if isinstance(searched_content, list):
|
||||
background_investigation_results = [
|
||||
@@ -62,7 +65,9 @@ def background_investigation_node(state: State) -> Command[Literal["planner"]]:
|
||||
f"Tavily search returned malformed response: {searched_content}"
|
||||
)
|
||||
else:
|
||||
background_investigation_results = web_search_tool.invoke(query)
|
||||
background_investigation_results = get_web_search_tool(
|
||||
configurable.max_search_results
|
||||
).invoke(query)
|
||||
return Command(
|
||||
update={
|
||||
"background_investigation_results": json.dumps(
|
||||
@@ -308,17 +313,34 @@ async def _execute_agent_step(
|
||||
observations = state.get("observations", [])
|
||||
|
||||
# Find the first unexecuted step
|
||||
current_step = None
|
||||
completed_steps = []
|
||||
for step in current_plan.steps:
|
||||
if not step.execution_res:
|
||||
current_step = step
|
||||
break
|
||||
else:
|
||||
completed_steps.append(step)
|
||||
|
||||
logger.info(f"Executing step: {step.title}")
|
||||
if not current_step:
|
||||
logger.warning("No unexecuted step found")
|
||||
return Command(goto="research_team")
|
||||
|
||||
# Prepare the input for the agent
|
||||
logger.info(f"Executing step: {current_step.title}")
|
||||
|
||||
# Format completed steps information
|
||||
completed_steps_info = ""
|
||||
if completed_steps:
|
||||
completed_steps_info = "# Existing Research Findings\n\n"
|
||||
for i, step in enumerate(completed_steps):
|
||||
completed_steps_info += f"## Existing Finding {i+1}: {step.title}\n\n"
|
||||
completed_steps_info += f"<finding>\n{step.execution_res}\n</finding>\n\n"
|
||||
|
||||
# Prepare the input for the agent with completed steps info
|
||||
agent_input = {
|
||||
"messages": [
|
||||
HumanMessage(
|
||||
content=f"#Task\n\n##title\n\n{step.title}\n\n##description\n\n{step.description}\n\n##locale\n\n{state.get('locale', 'en-US')}"
|
||||
content=f"{completed_steps_info}# Current Task\n\n## Title\n\n{current_step.title}\n\n## Description\n\n{current_step.description}\n\n## Locale\n\n{state.get('locale', 'en-US')}"
|
||||
)
|
||||
]
|
||||
}
|
||||
@@ -333,15 +355,39 @@ async def _execute_agent_step(
|
||||
)
|
||||
|
||||
# Invoke the agent
|
||||
result = await agent.ainvoke(input=agent_input)
|
||||
default_recursion_limit = 25
|
||||
try:
|
||||
env_value_str = os.getenv("AGENT_RECURSION_LIMIT", str(default_recursion_limit))
|
||||
parsed_limit = int(env_value_str)
|
||||
|
||||
if parsed_limit > 0:
|
||||
recursion_limit = parsed_limit
|
||||
logger.info(f"Recursion limit set to: {recursion_limit}")
|
||||
else:
|
||||
logger.warning(
|
||||
f"AGENT_RECURSION_LIMIT value '{env_value_str}' (parsed as {parsed_limit}) is not positive. "
|
||||
f"Using default value {default_recursion_limit}."
|
||||
)
|
||||
recursion_limit = default_recursion_limit
|
||||
except ValueError:
|
||||
raw_env_value = os.getenv("AGENT_RECURSION_LIMIT")
|
||||
logger.warning(
|
||||
f"Invalid AGENT_RECURSION_LIMIT value: '{raw_env_value}'. "
|
||||
f"Using default value {default_recursion_limit}."
|
||||
)
|
||||
recursion_limit = default_recursion_limit
|
||||
|
||||
result = await agent.ainvoke(
|
||||
input=agent_input, config={"recursion_limit": recursion_limit}
|
||||
)
|
||||
|
||||
# Process the result
|
||||
response_content = result["messages"][-1].content
|
||||
logger.debug(f"{agent_name.capitalize()} full response: {response_content}")
|
||||
|
||||
# Update the step with the execution result
|
||||
step.execution_res = response_content
|
||||
logger.info(f"Step '{step.title}' execution completed by {agent_name}")
|
||||
current_step.execution_res = response_content
|
||||
logger.info(f"Step '{current_step.title}' execution completed by {agent_name}")
|
||||
|
||||
return Command(
|
||||
update={
|
||||
@@ -361,7 +407,6 @@ async def _setup_and_execute_agent_step(
|
||||
state: State,
|
||||
config: RunnableConfig,
|
||||
agent_type: str,
|
||||
default_agent,
|
||||
default_tools: list,
|
||||
) -> Command[Literal["research_team"]]:
|
||||
"""Helper function to set up an agent with appropriate tools and execute a step.
|
||||
@@ -375,7 +420,6 @@ async def _setup_and_execute_agent_step(
|
||||
state: The current state
|
||||
config: The runnable config
|
||||
agent_type: The type of agent ("researcher" or "coder")
|
||||
default_agent: The default agent to use if no MCP servers are configured
|
||||
default_tools: The default tools to add to the agent
|
||||
|
||||
Returns:
|
||||
@@ -413,8 +457,9 @@ async def _setup_and_execute_agent_step(
|
||||
agent = create_agent(agent_type, agent_type, loaded_tools, agent_type)
|
||||
return await _execute_agent_step(state, agent, agent_type)
|
||||
else:
|
||||
# Use default agent if no MCP servers are configured
|
||||
return await _execute_agent_step(state, default_agent, agent_type)
|
||||
# Use default tools if no MCP servers are configured
|
||||
agent = create_agent(agent_type, agent_type, default_tools, agent_type)
|
||||
return await _execute_agent_step(state, agent, agent_type)
|
||||
|
||||
|
||||
async def researcher_node(
|
||||
@@ -422,12 +467,12 @@ async def researcher_node(
|
||||
) -> Command[Literal["research_team"]]:
|
||||
"""Researcher node that do research"""
|
||||
logger.info("Researcher node is researching.")
|
||||
configurable = Configuration.from_runnable_config(config)
|
||||
return await _setup_and_execute_agent_step(
|
||||
state,
|
||||
config,
|
||||
"researcher",
|
||||
research_agent,
|
||||
[web_search_tool, crawl_tool],
|
||||
[get_web_search_tool(configurable.max_search_results), crawl_tool],
|
||||
)
|
||||
|
||||
|
||||
@@ -440,6 +485,5 @@ async def coder_node(
|
||||
state,
|
||||
config,
|
||||
"coder",
|
||||
coder_agent,
|
||||
[python_repl_tool],
|
||||
)
|
||||
|
||||
+6
-3
@@ -11,7 +11,7 @@ from uuid import uuid4
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.responses import Response, StreamingResponse
|
||||
from langchain_core.messages import AIMessageChunk, ToolMessage
|
||||
from langchain_core.messages import AIMessageChunk, ToolMessage, BaseMessage
|
||||
from langgraph.types import Command
|
||||
|
||||
from src.graph.builder import build_graph_with_memory
|
||||
@@ -61,6 +61,7 @@ async def chat_stream(request: ChatRequest):
|
||||
thread_id,
|
||||
request.max_plan_iterations,
|
||||
request.max_step_num,
|
||||
request.max_search_results,
|
||||
request.auto_accepted_plan,
|
||||
request.interrupt_feedback,
|
||||
request.mcp_settings,
|
||||
@@ -75,6 +76,7 @@ async def _astream_workflow_generator(
|
||||
thread_id: str,
|
||||
max_plan_iterations: int,
|
||||
max_step_num: int,
|
||||
max_search_results: int,
|
||||
auto_accepted_plan: bool,
|
||||
interrupt_feedback: str,
|
||||
mcp_settings: dict,
|
||||
@@ -101,6 +103,7 @@ async def _astream_workflow_generator(
|
||||
"thread_id": thread_id,
|
||||
"max_plan_iterations": max_plan_iterations,
|
||||
"max_step_num": max_step_num,
|
||||
"max_search_results": max_search_results,
|
||||
"mcp_settings": mcp_settings,
|
||||
},
|
||||
stream_mode=["messages", "updates"],
|
||||
@@ -124,7 +127,7 @@ async def _astream_workflow_generator(
|
||||
)
|
||||
continue
|
||||
message_chunk, message_metadata = cast(
|
||||
tuple[AIMessageChunk, dict[str, any]], event_data
|
||||
tuple[BaseMessage, dict[str, any]], event_data
|
||||
)
|
||||
event_stream_message: dict[str, any] = {
|
||||
"thread_id": thread_id,
|
||||
@@ -141,7 +144,7 @@ async def _astream_workflow_generator(
|
||||
# Tool Message - Return the result of the tool call
|
||||
event_stream_message["tool_call_id"] = message_chunk.tool_call_id
|
||||
yield _make_event("tool_call_result", event_stream_message)
|
||||
else:
|
||||
elif isinstance(message_chunk, AIMessageChunk):
|
||||
# AI Message - Raw message tokens
|
||||
if message_chunk.tool_calls:
|
||||
# AI Message - Tool Call
|
||||
|
||||
@@ -38,6 +38,9 @@ class ChatRequest(BaseModel):
|
||||
max_step_num: Optional[int] = Field(
|
||||
3, description="The maximum number of steps in a plan"
|
||||
)
|
||||
max_search_results: Optional[int] = Field(
|
||||
3, description="The maximum number of search results"
|
||||
)
|
||||
auto_accepted_plan: Optional[bool] = Field(
|
||||
False, description="Whether to automatically accept the plan"
|
||||
)
|
||||
|
||||
+2
-18
@@ -5,28 +5,12 @@ import os
|
||||
|
||||
from .crawl import crawl_tool
|
||||
from .python_repl import python_repl_tool
|
||||
from .search import (
|
||||
tavily_search_tool,
|
||||
duckduckgo_search_tool,
|
||||
brave_search_tool,
|
||||
arxiv_search_tool,
|
||||
)
|
||||
from .search import get_web_search_tool
|
||||
from .tts import VolcengineTTS
|
||||
from src.config import SELECTED_SEARCH_ENGINE, SearchEngine
|
||||
|
||||
# Map search engine names to their respective tools
|
||||
search_tool_mappings = {
|
||||
SearchEngine.TAVILY.value: tavily_search_tool,
|
||||
SearchEngine.DUCKDUCKGO.value: duckduckgo_search_tool,
|
||||
SearchEngine.BRAVE_SEARCH.value: brave_search_tool,
|
||||
SearchEngine.ARXIV.value: arxiv_search_tool,
|
||||
}
|
||||
|
||||
web_search_tool = search_tool_mappings.get(SELECTED_SEARCH_ENGINE, tavily_search_tool)
|
||||
|
||||
__all__ = [
|
||||
"crawl_tool",
|
||||
"web_search_tool",
|
||||
"python_repl_tool",
|
||||
"get_web_search_tool",
|
||||
"VolcengineTTS",
|
||||
]
|
||||
|
||||
+37
-33
@@ -9,7 +9,7 @@ from langchain_community.tools import BraveSearch, DuckDuckGoSearchResults
|
||||
from langchain_community.tools.arxiv import ArxivQueryRun
|
||||
from langchain_community.utilities import ArxivAPIWrapper, BraveSearchWrapper
|
||||
|
||||
from src.config import SEARCH_MAX_RESULTS, SearchEngine
|
||||
from src.config import SearchEngine, SELECTED_SEARCH_ENGINE
|
||||
from src.tools.tavily_search.tavily_search_results_with_images import (
|
||||
TavilySearchResultsWithImages,
|
||||
)
|
||||
@@ -18,44 +18,48 @@ from src.tools.decorators import create_logged_tool
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Create logged versions of the search tools
|
||||
LoggedTavilySearch = create_logged_tool(TavilySearchResultsWithImages)
|
||||
if os.getenv("SEARCH_API", "") == SearchEngine.TAVILY.value:
|
||||
tavily_search_tool = LoggedTavilySearch(
|
||||
name="web_search",
|
||||
max_results=SEARCH_MAX_RESULTS,
|
||||
include_raw_content=True,
|
||||
include_images=True,
|
||||
include_image_descriptions=True,
|
||||
)
|
||||
else:
|
||||
tavily_search_tool = None
|
||||
|
||||
LoggedDuckDuckGoSearch = create_logged_tool(DuckDuckGoSearchResults)
|
||||
duckduckgo_search_tool = LoggedDuckDuckGoSearch(
|
||||
name="web_search", max_results=SEARCH_MAX_RESULTS
|
||||
)
|
||||
|
||||
LoggedBraveSearch = create_logged_tool(BraveSearch)
|
||||
brave_search_tool = LoggedBraveSearch(
|
||||
name="web_search",
|
||||
search_wrapper=BraveSearchWrapper(
|
||||
api_key=os.getenv("BRAVE_SEARCH_API_KEY", ""),
|
||||
search_kwargs={"count": SEARCH_MAX_RESULTS},
|
||||
),
|
||||
)
|
||||
|
||||
LoggedArxivSearch = create_logged_tool(ArxivQueryRun)
|
||||
arxiv_search_tool = LoggedArxivSearch(
|
||||
name="web_search",
|
||||
api_wrapper=ArxivAPIWrapper(
|
||||
top_k_results=SEARCH_MAX_RESULTS,
|
||||
load_max_docs=SEARCH_MAX_RESULTS,
|
||||
load_all_available_meta=True,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
# Get the selected search tool
|
||||
def get_web_search_tool(max_search_results: int):
|
||||
if SELECTED_SEARCH_ENGINE == SearchEngine.TAVILY.value:
|
||||
return LoggedTavilySearch(
|
||||
name="web_search",
|
||||
max_results=max_search_results,
|
||||
include_raw_content=True,
|
||||
include_images=True,
|
||||
include_image_descriptions=True,
|
||||
)
|
||||
elif SELECTED_SEARCH_ENGINE == SearchEngine.DUCKDUCKGO.value:
|
||||
return LoggedDuckDuckGoSearch(name="web_search", max_results=max_search_results)
|
||||
elif SELECTED_SEARCH_ENGINE == SearchEngine.BRAVE_SEARCH.value:
|
||||
return LoggedBraveSearch(
|
||||
name="web_search",
|
||||
search_wrapper=BraveSearchWrapper(
|
||||
api_key=os.getenv("BRAVE_SEARCH_API_KEY", ""),
|
||||
search_kwargs={"count": max_search_results},
|
||||
),
|
||||
)
|
||||
elif SELECTED_SEARCH_ENGINE == SearchEngine.ARXIV.value:
|
||||
return LoggedArxivSearch(
|
||||
name="web_search",
|
||||
api_wrapper=ArxivAPIWrapper(
|
||||
top_k_results=max_search_results,
|
||||
load_max_docs=max_search_results,
|
||||
load_all_available_meta=True,
|
||||
),
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unsupported search engine: {SELECTED_SEARCH_ENGINE}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
results = LoggedDuckDuckGoSearch(
|
||||
name="web_search", max_results=SEARCH_MAX_RESULTS, output_format="list"
|
||||
name="web_search", max_results=3, output_format="list"
|
||||
).invoke("cute panda")
|
||||
print(json.dumps(results, indent=2, ensure_ascii=False))
|
||||
|
||||
+24
@@ -0,0 +1,24 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
This script manually patches sys.modules to fix the LLM import issue
|
||||
so that tests can run without requiring LLM configuration.
|
||||
"""
|
||||
|
||||
import sys
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
# Create mocks
|
||||
mock_llm = MagicMock()
|
||||
mock_llm.invoke.return_value = "Mock LLM response"
|
||||
|
||||
# Create a mock module for llm.py
|
||||
mock_llm_module = MagicMock()
|
||||
mock_llm_module.get_llm_by_type = lambda llm_type: mock_llm
|
||||
mock_llm_module.basic_llm = mock_llm
|
||||
mock_llm_module._create_llm_use_conf = lambda llm_type, conf: mock_llm
|
||||
|
||||
# Set the mock module
|
||||
sys.modules["src.llms.llm"] = mock_llm_module
|
||||
|
||||
print("Successfully patched LLM module. You can now run your tests.")
|
||||
print("Example: uv run pytest tests/test_types.py -v")
|
||||
@@ -0,0 +1,131 @@
|
||||
import pytest
|
||||
import sys
|
||||
import os
|
||||
from typing import Annotated, List, Optional
|
||||
|
||||
# Import MessagesState directly from langgraph rather than through our application
|
||||
from langgraph.graph import MessagesState
|
||||
|
||||
|
||||
# Create stub versions of Plan/Step/StepType to avoid dependencies
|
||||
class StepType:
|
||||
RESEARCH = "research"
|
||||
PROCESSING = "processing"
|
||||
|
||||
|
||||
class Step:
|
||||
def __init__(self, need_web_search, title, description, step_type):
|
||||
self.need_web_search = need_web_search
|
||||
self.title = title
|
||||
self.description = description
|
||||
self.step_type = step_type
|
||||
|
||||
|
||||
class Plan:
|
||||
def __init__(self, locale, has_enough_context, thought, title, steps):
|
||||
self.locale = locale
|
||||
self.has_enough_context = has_enough_context
|
||||
self.thought = thought
|
||||
self.title = title
|
||||
self.steps = steps
|
||||
|
||||
|
||||
# Import the actual State class by loading the module directly
|
||||
# This avoids the cascade of imports that would normally happen
|
||||
def load_state_class():
|
||||
# Get the absolute path to the types.py file
|
||||
src_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "src"))
|
||||
types_path = os.path.join(src_dir, "graph", "types.py")
|
||||
|
||||
# Create a namespace for the module
|
||||
import types
|
||||
|
||||
module_name = "src.graph.types_direct"
|
||||
spec = types.ModuleType(module_name)
|
||||
|
||||
# Add the module to sys.modules to avoid import loops
|
||||
sys.modules[module_name] = spec
|
||||
|
||||
# Set up the namespace with required imports
|
||||
spec.__dict__["operator"] = __import__("operator")
|
||||
spec.__dict__["Annotated"] = Annotated
|
||||
spec.__dict__["MessagesState"] = MessagesState
|
||||
spec.__dict__["Plan"] = Plan
|
||||
|
||||
# Execute the module code
|
||||
with open(types_path, "r") as f:
|
||||
module_code = f.read()
|
||||
|
||||
exec(module_code, spec.__dict__)
|
||||
|
||||
# Return the State class
|
||||
return spec.State
|
||||
|
||||
|
||||
# Load the actual State class
|
||||
State = load_state_class()
|
||||
|
||||
|
||||
def test_state_initialization():
|
||||
"""Test that State class has correct default attribute definitions."""
|
||||
# Test that the class has the expected attribute definitions
|
||||
assert State.locale == "en-US"
|
||||
assert State.observations == []
|
||||
assert State.plan_iterations == 0
|
||||
assert State.current_plan is None
|
||||
assert State.final_report == ""
|
||||
assert State.auto_accepted_plan is False
|
||||
assert State.enable_background_investigation is True
|
||||
assert State.background_investigation_results is None
|
||||
|
||||
# Verify state initialization
|
||||
state = State(messages=[])
|
||||
assert "messages" in state
|
||||
|
||||
# Without explicitly passing attributes, they're not in the state
|
||||
assert "locale" not in state
|
||||
assert "observations" not in state
|
||||
|
||||
|
||||
def test_state_with_custom_values():
|
||||
"""Test that State can be initialized with custom values."""
|
||||
test_step = Step(
|
||||
need_web_search=True,
|
||||
title="Test Step",
|
||||
description="Step description",
|
||||
step_type=StepType.RESEARCH,
|
||||
)
|
||||
|
||||
test_plan = Plan(
|
||||
locale="en-US",
|
||||
has_enough_context=False,
|
||||
thought="Test thought",
|
||||
title="Test Plan",
|
||||
steps=[test_step],
|
||||
)
|
||||
|
||||
# Initialize state with custom values and required messages field
|
||||
state = State(
|
||||
messages=[],
|
||||
locale="fr-FR",
|
||||
observations=["Observation 1"],
|
||||
plan_iterations=2,
|
||||
current_plan=test_plan,
|
||||
final_report="Test report",
|
||||
auto_accepted_plan=True,
|
||||
enable_background_investigation=False,
|
||||
background_investigation_results="Test results",
|
||||
)
|
||||
|
||||
# Access state keys - these are explicitly initialized
|
||||
assert state["locale"] == "fr-FR"
|
||||
assert state["observations"] == ["Observation 1"]
|
||||
assert state["plan_iterations"] == 2
|
||||
assert state["current_plan"].title == "Test Plan"
|
||||
assert state["current_plan"].thought == "Test thought"
|
||||
assert len(state["current_plan"].steps) == 1
|
||||
assert state["current_plan"].steps[0].title == "Test Step"
|
||||
assert state["final_report"] == "Test report"
|
||||
assert state["auto_accepted_plan"] is True
|
||||
assert state["enable_background_investigation"] is False
|
||||
assert state["background_investigation_results"] == "Test results"
|
||||
@@ -159,6 +159,18 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/09/71/54e999902aed72baf26bca0d50781b01838251a462612966e9fc4891eadd/black-25.1.0-py3-none-any.whl", hash = "sha256:95e8176dae143ba9097f351d174fdaf0ccd29efb414b362ae3fd72bf0f710717", size = 207646 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "blockbuster"
|
||||
version = "1.5.24"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "forbiddenfruit", marker = "implementation_name == 'cpython'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/35/c8/1e456a043179f2aef10bcaafea79f6d06c0ac45cc994767a54f680509f3b/blockbuster-1.5.24.tar.gz", hash = "sha256:97645775761a5d425666ec0bc99629b65c7eccdc2f770d2439850682567af4ec", size = 51245 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/a7/c8/57a4c80e5abec29fa9406307a5277527f21210bfc6c2c61c3d8ded36c09b/blockbuster-1.5.24-py3-none-any.whl", hash = "sha256:e703497b55bc72af09d60d1cd746c2f3ba7ce0c446fa256be6ccda5e7d403520", size = 13214 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "certifi"
|
||||
version = "2025.1.31"
|
||||
@@ -248,6 +260,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2", size = 98188 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cloudpickle"
|
||||
version = "3.1.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/52/39/069100b84d7418bc358d81669d5748efb14b9cceacd2f9c75f550424132f/cloudpickle-3.1.1.tar.gz", hash = "sha256:b216fa8ae4019d5482a8ac3c95d8f6346115d8835911fd4aefd1a445e4242c64", size = 22113 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/e8/64c37fadfc2816a7701fa8a6ed8d87327c7d54eacfbfb6edab14a2f2be75/cloudpickle-3.1.1-py3-none-any.whl", hash = "sha256:c8c5a44295039331ee9dad40ba100a9c7297b6f988e50e87ccdf3765a668350e", size = 20992 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "colorama"
|
||||
version = "0.4.6"
|
||||
@@ -296,6 +317,41 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/fb/b2/f655700e1024dec98b10ebaafd0cedbc25e40e4abe62a3c8e2ceef4f8f0a/coverage-7.6.12-py3-none-any.whl", hash = "sha256:eb8668cfbc279a536c633137deeb9435d2962caec279c3f8cf8b91fff6ff8953", size = 200552 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cryptography"
|
||||
version = "44.0.3"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/53/d6/1411ab4d6108ab167d06254c5be517681f1e331f90edf1379895bcb87020/cryptography-44.0.3.tar.gz", hash = "sha256:fe19d8bc5536a91a24a8133328880a41831b6c5df54599a8417b62fe015d3053", size = 711096 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/08/53/c776d80e9d26441bb3868457909b4e74dd9ccabd182e10b2b0ae7a07e265/cryptography-44.0.3-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:962bc30480a08d133e631e8dfd4783ab71cc9e33d5d7c1e192f0b7c06397bb88", size = 6670281 },
|
||||
{ url = "https://files.pythonhosted.org/packages/6a/06/af2cf8d56ef87c77319e9086601bef621bedf40f6f59069e1b6d1ec498c5/cryptography-44.0.3-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ffc61e8f3bf5b60346d89cd3d37231019c17a081208dfbbd6e1605ba03fa137", size = 3959305 },
|
||||
{ url = "https://files.pythonhosted.org/packages/ae/01/80de3bec64627207d030f47bf3536889efee8913cd363e78ca9a09b13c8e/cryptography-44.0.3-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58968d331425a6f9eedcee087f77fd3c927c88f55368f43ff7e0a19891f2642c", size = 4171040 },
|
||||
{ url = "https://files.pythonhosted.org/packages/bd/48/bb16b7541d207a19d9ae8b541c70037a05e473ddc72ccb1386524d4f023c/cryptography-44.0.3-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:e28d62e59a4dbd1d22e747f57d4f00c459af22181f0b2f787ea83f5a876d7c76", size = 3963411 },
|
||||
{ url = "https://files.pythonhosted.org/packages/42/b2/7d31f2af5591d217d71d37d044ef5412945a8a8e98d5a2a8ae4fd9cd4489/cryptography-44.0.3-cp37-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:af653022a0c25ef2e3ffb2c673a50e5a0d02fecc41608f4954176f1933b12359", size = 3689263 },
|
||||
{ url = "https://files.pythonhosted.org/packages/25/50/c0dfb9d87ae88ccc01aad8eb93e23cfbcea6a6a106a9b63a7b14c1f93c75/cryptography-44.0.3-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:157f1f3b8d941c2bd8f3ffee0af9b049c9665c39d3da9db2dc338feca5e98a43", size = 4196198 },
|
||||
{ url = "https://files.pythonhosted.org/packages/66/c9/55c6b8794a74da652690c898cb43906310a3e4e4f6ee0b5f8b3b3e70c441/cryptography-44.0.3-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:c6cd67722619e4d55fdb42ead64ed8843d64638e9c07f4011163e46bc512cf01", size = 3966502 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b6/f7/7cb5488c682ca59a02a32ec5f975074084db4c983f849d47b7b67cc8697a/cryptography-44.0.3-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:b424563394c369a804ecbee9b06dfb34997f19d00b3518e39f83a5642618397d", size = 4196173 },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/0b/2f789a8403ae089b0b121f8f54f4a3e5228df756e2146efdf4a09a3d5083/cryptography-44.0.3-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:c91fc8e8fd78af553f98bc7f2a1d8db977334e4eea302a4bfd75b9461c2d8904", size = 4087713 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1d/aa/330c13655f1af398fc154089295cf259252f0ba5df93b4bc9d9c7d7f843e/cryptography-44.0.3-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:25cd194c39fa5a0aa4169125ee27d1172097857b27109a45fadc59653ec06f44", size = 4299064 },
|
||||
{ url = "https://files.pythonhosted.org/packages/10/a8/8c540a421b44fd267a7d58a1fd5f072a552d72204a3f08194f98889de76d/cryptography-44.0.3-cp37-abi3-win32.whl", hash = "sha256:3be3f649d91cb182c3a6bd336de8b61a0a71965bd13d1a04a0e15b39c3d5809d", size = 2773887 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b9/0d/c4b1657c39ead18d76bbd122da86bd95bdc4095413460d09544000a17d56/cryptography-44.0.3-cp37-abi3-win_amd64.whl", hash = "sha256:3883076d5c4cc56dbef0b898a74eb6992fdac29a7b9013870b34efe4ddb39a0d", size = 3209737 },
|
||||
{ url = "https://files.pythonhosted.org/packages/34/a3/ad08e0bcc34ad436013458d7528e83ac29910943cea42ad7dd4141a27bbb/cryptography-44.0.3-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:5639c2b16764c6f76eedf722dbad9a0914960d3489c0cc38694ddf9464f1bb2f", size = 6673501 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b1/f0/7491d44bba8d28b464a5bc8cc709f25a51e3eac54c0a4444cf2473a57c37/cryptography-44.0.3-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3ffef566ac88f75967d7abd852ed5f182da252d23fac11b4766da3957766759", size = 3960307 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f7/c8/e5c5d0e1364d3346a5747cdcd7ecbb23ca87e6dea4f942a44e88be349f06/cryptography-44.0.3-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:192ed30fac1728f7587c6f4613c29c584abdc565d7417c13904708db10206645", size = 4170876 },
|
||||
{ url = "https://files.pythonhosted.org/packages/73/96/025cb26fc351d8c7d3a1c44e20cf9a01e9f7cf740353c9c7a17072e4b264/cryptography-44.0.3-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:7d5fe7195c27c32a64955740b949070f21cba664604291c298518d2e255931d2", size = 3964127 },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/44/eb6522db7d9f84e8833ba3bf63313f8e257729cf3a8917379473fcfd6601/cryptography-44.0.3-cp39-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:3f07943aa4d7dad689e3bb1638ddc4944cc5e0921e3c227486daae0e31a05e54", size = 3689164 },
|
||||
{ url = "https://files.pythonhosted.org/packages/68/fb/d61a4defd0d6cee20b1b8a1ea8f5e25007e26aeb413ca53835f0cae2bcd1/cryptography-44.0.3-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:cb90f60e03d563ca2445099edf605c16ed1d5b15182d21831f58460c48bffb93", size = 4198081 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1b/50/457f6911d36432a8811c3ab8bd5a6090e8d18ce655c22820994913dd06ea/cryptography-44.0.3-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:ab0b005721cc0039e885ac3503825661bd9810b15d4f374e473f8c89b7d5460c", size = 3967716 },
|
||||
{ url = "https://files.pythonhosted.org/packages/35/6e/dca39d553075980ccb631955c47b93d87d27f3596da8d48b1ae81463d915/cryptography-44.0.3-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:3bb0847e6363c037df8f6ede57d88eaf3410ca2267fb12275370a76f85786a6f", size = 4197398 },
|
||||
{ url = "https://files.pythonhosted.org/packages/9b/9d/d1f2fe681eabc682067c66a74addd46c887ebacf39038ba01f8860338d3d/cryptography-44.0.3-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:b0cc66c74c797e1db750aaa842ad5b8b78e14805a9b5d1348dc603612d3e3ff5", size = 4087900 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c4/f5/3599e48c5464580b73b236aafb20973b953cd2e7b44c7c2533de1d888446/cryptography-44.0.3-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6866df152b581f9429020320e5eb9794c8780e90f7ccb021940d7f50ee00ae0b", size = 4301067 },
|
||||
{ url = "https://files.pythonhosted.org/packages/a7/6c/d2c48c8137eb39d0c193274db5c04a75dab20d2f7c3f81a7dcc3a8897701/cryptography-44.0.3-cp39-abi3-win32.whl", hash = "sha256:c138abae3a12a94c75c10499f1cbae81294a6f983b3af066390adee73f433028", size = 2775467 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c9/ad/51f212198681ea7b0deaaf8846ee10af99fba4e894f67b353524eab2bbe5/cryptography-44.0.3-cp39-abi3-win_amd64.whl", hash = "sha256:5d186f32e52e66994dce4f766884bcb9c68b8da62d61d9d215bfe5fb56d21334", size = 3210375 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dataclasses-json"
|
||||
version = "0.6.7"
|
||||
@@ -342,6 +398,7 @@ dependencies = [
|
||||
[package.optional-dependencies]
|
||||
dev = [
|
||||
{ name = "black" },
|
||||
{ name = "langgraph-cli", extra = ["inmem"] },
|
||||
]
|
||||
test = [
|
||||
{ name = "pytest" },
|
||||
@@ -363,6 +420,7 @@ requires-dist = [
|
||||
{ name = "langchain-mcp-adapters", specifier = ">=0.0.9" },
|
||||
{ name = "langchain-openai", specifier = ">=0.3.8" },
|
||||
{ name = "langgraph", specifier = ">=0.3.5" },
|
||||
{ name = "langgraph-cli", extras = ["inmem"], marker = "extra == 'dev'", specifier = ">=0.2.10" },
|
||||
{ name = "litellm", specifier = ">=1.63.11" },
|
||||
{ name = "markdownify", specifier = ">=1.1.0" },
|
||||
{ name = "mcp", specifier = ">=1.6.0" },
|
||||
@@ -437,6 +495,12 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/4d/36/2a115987e2d8c300a974597416d9de88f2444426de9571f4b59b2cca3acc/filelock-3.18.0-py3-none-any.whl", hash = "sha256:c401f4f8377c4464e6db25fff06205fd89bdd83b65eb0488ed1b160f780e21de", size = 16215 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "forbiddenfruit"
|
||||
version = "0.1.4"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e6/79/d4f20e91327c98096d605646bdc6a5ffedae820f38d378d3515c42ec5e60/forbiddenfruit-0.1.4.tar.gz", hash = "sha256:e3f7e66561a29ae129aac139a85d610dbf3dd896128187ed5454b6421f624253", size = 43756 }
|
||||
|
||||
[[package]]
|
||||
name = "frozendict"
|
||||
version = "2.4.6"
|
||||
@@ -741,6 +805,28 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/69/4a/4f9dbeb84e8850557c02365a0eee0649abe5eb1d84af92a25731c6c0f922/jsonschema-4.23.0-py3-none-any.whl", hash = "sha256:fbadb6f8b144a8f8cf9f0b89ba94501d143e50411a1278633f56a7acf7fd5566", size = 88462 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "jsonschema-rs"
|
||||
version = "0.29.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/b0/b4/33a9b25cad41d1e533c1ab7ff30eaec50628dd1bcb92171b99a2e944d61f/jsonschema_rs-0.29.1.tar.gz", hash = "sha256:a9f896a9e4517630374f175364705836c22f09d5bd5bbb06ec0611332b6702fd", size = 1406679 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7b/4a/67ea15558ab85e67d1438b2e5da63b8e89b273c457106cbc87f8f4959a3d/jsonschema_rs-0.29.1-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:9fe7529faa6a84d23e31b1f45853631e4d4d991c85f3d50e6d1df857bb52b72d", size = 3825206 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b9/2e/bc75ed65d11ba47200ade9795ebd88eb2e64c2852a36d9be640172563430/jsonschema_rs-0.29.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:b5d7e385298f250ed5ce4928fd59fabf2b238f8167f2c73b9414af8143dfd12e", size = 1966302 },
|
||||
{ url = "https://files.pythonhosted.org/packages/95/dd/4a90e96811f897de066c69d95bc0983138056b19cb169f2a99c736e21933/jsonschema_rs-0.29.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64a29be0504731a2e3164f66f609b9999aa66a2df3179ecbfc8ead88e0524388", size = 2062846 },
|
||||
{ url = "https://files.pythonhosted.org/packages/21/91/61834396748a741021716751a786312b8a8319715e6c61421447a07c887c/jsonschema_rs-0.29.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7e91defda5dfa87306543ee9b34d97553d9422c134998c0b64855b381f8b531d", size = 2065564 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f0/2c/920d92e88b9bdb6cb14867a55e5572e7b78bfc8554f9c625caa516aa13dd/jsonschema_rs-0.29.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:96f87680a6a1c16000c851d3578534ae3c154da894026c2a09a50f727bd623d4", size = 2083055 },
|
||||
{ url = "https://files.pythonhosted.org/packages/6d/0a/f4c1bea3193992fe4ff9ce330c6a594481caece06b1b67d30b15992bbf54/jsonschema_rs-0.29.1-cp312-cp312-win32.whl", hash = "sha256:bcfc0d52ecca6c1b2fbeede65c1ad1545de633045d42ad0c6699039f28b5fb71", size = 1701065 },
|
||||
{ url = "https://files.pythonhosted.org/packages/5e/89/3f89de071920208c0eb64b827a878d2e587f6a3431b58c02f63c3468b76e/jsonschema_rs-0.29.1-cp312-cp312-win_amd64.whl", hash = "sha256:a414c162d687ee19171e2d8aae821f396d2f84a966fd5c5c757bd47df0954452", size = 1871774 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1b/9b/d642024e8b39753b789598363fd5998eb3053b52755a5df6a021d53741d5/jsonschema_rs-0.29.1-cp313-cp313-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:0afee5f31a940dec350a33549ec03f2d1eda2da3049a15cd951a266a57ef97ee", size = 3824864 },
|
||||
{ url = "https://files.pythonhosted.org/packages/aa/3d/48a7baa2373b941e89a12e720dae123fd0a663c28c4e82213a29c89a4715/jsonschema_rs-0.29.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:c38453a5718bcf2ad1b0163d128814c12829c45f958f9407c69009d8b94a1232", size = 1966084 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1e/e4/f260917a17bb28bb1dec6fa5e869223341fac2c92053aa9bd23c1caaefa0/jsonschema_rs-0.29.1-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:5dc8bdb1067bf4f6d2f80001a636202dc2cea027b8579f1658ce8e736b06557f", size = 2062430 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f5/e7/61353403b76768601d802afa5b7b5902d52c33d1dd0f3159aafa47463634/jsonschema_rs-0.29.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4bcfe23992623a540169d0845ea8678209aa2fe7179941dc7c512efc0c2b6b46", size = 2065443 },
|
||||
{ url = "https://files.pythonhosted.org/packages/40/ed/40b971a09f46a22aa956071ea159413046e9d5fcd280a5910da058acdeb2/jsonschema_rs-0.29.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f2a526c0deacd588864d3400a0997421dffef6fe1df5cfda4513a453c01ad42", size = 2082606 },
|
||||
{ url = "https://files.pythonhosted.org/packages/bc/59/1c142e1bfb87d57c18fb189149f7aa8edf751725d238d787015278b07600/jsonschema_rs-0.29.1-cp313-cp313-win32.whl", hash = "sha256:68acaefb54f921243552d15cfee3734d222125584243ca438de4444c5654a8a3", size = 1700666 },
|
||||
{ url = "https://files.pythonhosted.org/packages/13/e8/f0ad941286cd350b879dd2b3c848deecd27f0b3fbc0ff44f2809ad59718d/jsonschema_rs-0.29.1-cp313-cp313-win_amd64.whl", hash = "sha256:1c4e5a61ac760a2fc3856a129cc84aa6f8fba7b9bc07b19fe4101050a8ecc33c", size = 1871619 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "jsonschema-specifications"
|
||||
version = "2024.10.1"
|
||||
@@ -866,30 +952,81 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "langgraph"
|
||||
version = "0.3.5"
|
||||
version = "0.4.3"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "langchain-core" },
|
||||
{ name = "langchain-core", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph-checkpoint" },
|
||||
{ name = "langgraph-prebuilt" },
|
||||
{ name = "langgraph-sdk" },
|
||||
{ name = "langgraph-prebuilt", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph-sdk", marker = "python_full_version < '4.0'" },
|
||||
{ name = "pydantic" },
|
||||
{ name = "xxhash" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/4e/fa/b1ecc95a2464bc7dbe5e67fbd21096013829119899c33236090b98c75508/langgraph-0.3.5.tar.gz", hash = "sha256:7c0d8e61aa02578b41036c9f7a599ccba2562d269f66ef76bacbba47a99a7eca", size = 114020 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/60/9e/5a64602eff18a99d0216a80eff823051ffbdb7c11b5a16171cee8b1ccce5/langgraph-0.4.3.tar.gz", hash = "sha256:272d5d5903f2c2882dbeeba849846a0f2500bd83fb3734a3801ebe64c1a60bdd", size = 125407 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/a4/5f/1e1d9173b5c41eff54f88d9f4ee82c38eb4928120ab6a21a68a78d1c499e/langgraph-0.3.5-py3-none-any.whl", hash = "sha256:be313ec300633c857873ea3e44aece4dd7d0b11f131d385108b359d377a85bf7", size = 131527 },
|
||||
{ url = "https://files.pythonhosted.org/packages/35/53/0a20edd9f41eb3707722444ec1b43752b792bbe904d1c8cc3ba27f8eb2c8/langgraph-0.4.3-py3-none-any.whl", hash = "sha256:dec926e034f4d440b92a3c52139cb6e9763bc1791e79a6ea53a233309cec864f", size = 151191 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "langgraph-api"
|
||||
version = "0.2.27"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "cloudpickle" },
|
||||
{ name = "cryptography" },
|
||||
{ name = "httpx" },
|
||||
{ name = "jsonschema-rs" },
|
||||
{ name = "langchain-core", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph-checkpoint", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph-runtime-inmem" },
|
||||
{ name = "langgraph-sdk", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langsmith" },
|
||||
{ name = "orjson" },
|
||||
{ name = "pyjwt" },
|
||||
{ name = "sse-starlette" },
|
||||
{ name = "starlette" },
|
||||
{ name = "structlog" },
|
||||
{ name = "tenacity" },
|
||||
{ name = "truststore" },
|
||||
{ name = "uvicorn" },
|
||||
{ name = "watchfiles" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/6c/39/796960b1c6d6196f3119081e6072d5a53797003c9695d576550c5590e346/langgraph_api-0.2.27.tar.gz", hash = "sha256:d53c77456de3888164fde8f1703b050c245aebdab3ba42b1868d4bfe319343f5", size = 172523 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/8e/0a/d224b694ae1033b90067096cf19ff0628f55053f267cea2c3224cd1e5417/langgraph_api-0.2.27-py3-none-any.whl", hash = "sha256:f2f6ec669e22f2ab6ebaa971573c9b3bdade8d83a968cfa3493de85b154b418b", size = 208097 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "langgraph-checkpoint"
|
||||
version = "2.0.18"
|
||||
version = "2.0.25"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "langchain-core" },
|
||||
{ name = "msgpack" },
|
||||
{ name = "ormsgpack" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/76/1d/27a178de8a40c0cd53671f6a7e9aa21967a17672fdc774e5c0ae6cc406a4/langgraph_checkpoint-2.0.18.tar.gz", hash = "sha256:2822eedd028b454b7bfebfb7e04347aed1b64db97dedb7eb68ef0fb42641606d", size = 34947 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/c5/72/d49828e6929cb3ded1472aa3e5e4a369d292c4f21021ac683d28fbc8f4f8/langgraph_checkpoint-2.0.25.tar.gz", hash = "sha256:77a63cab7b5f84dec1d49db561326ec28bdd48bcefb7fe4ac372069d2609287b", size = 36952 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/21/11/91062b03b22b9ce6474df7c3e056417a4c2b029f9cc71829dd6f62479dd0/langgraph_checkpoint-2.0.18-py3-none-any.whl", hash = "sha256:941de442e5a893a6cabb8c3845f03159301b85f63ff4e8f2b308f7dfd96a3f59", size = 39106 },
|
||||
{ url = "https://files.pythonhosted.org/packages/12/52/bceb5b5348c7a60ef0625ab0a0a0a9ff5d78f0e12aed8cc55c49d5e8a8c9/langgraph_checkpoint-2.0.25-py3-none-any.whl", hash = "sha256:23416a0f5bc9dd712ac10918fc13e8c9c4530c419d2985a441df71a38fc81602", size = 42312 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "langgraph-cli"
|
||||
version = "0.2.10"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "click" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/8d/5e/b12bc8140cd4f797ad7f596bf90558994fd6891df8974bc3fc4747eabdc7/langgraph_cli-0.2.10.tar.gz", hash = "sha256:0c215b364daeaf10de681e4960ecaafc7c9cd2a4100b41052d78d95cababf422", size = 31690 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/e1/06/7151d7c8d6c2bccc0919ddb35a63caf3707b96c94561f47f14b08d73ef5e/langgraph_cli-0.2.10-py3-none-any.whl", hash = "sha256:4aaa8d828d8d3bf0f55d2b2a36b2d9944021d65a4b06ed708c6d5eea725f65a7", size = 34833 },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
inmem = [
|
||||
{ name = "langgraph-api", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph-runtime-inmem", marker = "python_full_version < '4.0'" },
|
||||
{ name = "python-dotenv" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -905,17 +1042,34 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/36/72/9e092665502f8f52f2708065ed14fbbba3f95d1a1b65d62049b0c5fcdf00/langgraph_prebuilt-0.1.8-py3-none-any.whl", hash = "sha256:ae97b828ae00be2cefec503423aa782e1bff165e9b94592e224da132f2526968", size = 25903 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "langgraph-runtime-inmem"
|
||||
version = "0.0.11"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "blockbuster" },
|
||||
{ name = "langgraph", marker = "python_full_version < '4.0'" },
|
||||
{ name = "langgraph-checkpoint", marker = "python_full_version < '4.0'" },
|
||||
{ name = "sse-starlette" },
|
||||
{ name = "starlette" },
|
||||
{ name = "structlog" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/95/6c/f74a7c5a0a4c8998cdce064b6de0692f7d87f4b1776de9854107ee4f89c6/langgraph_runtime_inmem-0.0.11.tar.gz", hash = "sha256:2e4e1802e4721694d46c189e7f1c6e1116ad9366150c9c735a928a834c2b5b30", size = 23633 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/e9/a8/1c9250f1b45cc0ef66ca964cf3a78ec271a1f94e20b26adf3887c05b128f/langgraph_runtime_inmem-0.0.11-py3-none-any.whl", hash = "sha256:b0eaf3ea94d13040d75c956a0a54441de2428066aeffebf57241fb954ed2f1bd", size = 27844 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "langgraph-sdk"
|
||||
version = "0.1.55"
|
||||
version = "0.1.69"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "httpx" },
|
||||
{ name = "orjson" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/7a/6c/8286151a21124dc0189b57495541c2e3cace317056f60feb04076b438f82/langgraph_sdk-0.1.55.tar.gz", hash = "sha256:89a0240157a27822cc4edd1c9e72bc852e20f5c71165a4c9b91eeffa11fd6a6b", size = 42690 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/06/78/4ca0603240332be5fc8ebbb9bc418896310643bef32e3319a311fab37e4c/langgraph_sdk-0.1.69.tar.gz", hash = "sha256:2e85d73b78a03f9606d0fafd62048b3060371149f6f9e61f07f087fd56c766fa", size = 45343 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/4e/64/4b75f4b57f0c8f39bdb43aa74b1d2edcdb604b5baa58465ccc54b8b906c5/langgraph_sdk-0.1.55-py3-none-any.whl", hash = "sha256:266e92a558eb738da1ef04c29fbfc2157cd3a977b80905d9509a2cb79331f8fc", size = 45785 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b0/e6/8e82a0373e233392d83ae37f473c9799c536b307322f0caf49a59bce9522/langgraph_sdk-0.1.69-py3-none-any.whl", hash = "sha256:0ed117bcdf67285a17c57f6265f1d94f2dbd71346cf48a8e1a5fa25e523eb6b8", size = 48905 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1082,36 +1236,6 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/10/30/20a7f33b0b884a9d14dd3aa94ff1ac9da1479fe2ad66dd9e2736075d2506/mcp-1.6.0-py3-none-any.whl", hash = "sha256:7bd24c6ea042dbec44c754f100984d186620d8b841ec30f1b19eda9b93a634d0", size = 76077 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "msgpack"
|
||||
version = "1.1.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/cb/d0/7555686ae7ff5731205df1012ede15dd9d927f6227ea151e901c7406af4f/msgpack-1.1.0.tar.gz", hash = "sha256:dd432ccc2c72b914e4cb77afce64aab761c1137cc698be3984eee260bcb2896e", size = 167260 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/e1/d6/716b7ca1dbde63290d2973d22bbef1b5032ca634c3ff4384a958ec3f093a/msgpack-1.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:d46cf9e3705ea9485687aa4001a76e44748b609d260af21c4ceea7f2212a501d", size = 152421 },
|
||||
{ url = "https://files.pythonhosted.org/packages/70/da/5312b067f6773429cec2f8f08b021c06af416bba340c912c2ec778539ed6/msgpack-1.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5dbad74103df937e1325cc4bfeaf57713be0b4f15e1c2da43ccdd836393e2ea2", size = 85277 },
|
||||
{ url = "https://files.pythonhosted.org/packages/28/51/da7f3ae4462e8bb98af0d5bdf2707f1b8c65a0d4f496e46b6afb06cbc286/msgpack-1.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:58dfc47f8b102da61e8949708b3eafc3504509a5728f8b4ddef84bd9e16ad420", size = 82222 },
|
||||
{ url = "https://files.pythonhosted.org/packages/33/af/dc95c4b2a49cff17ce47611ca9ba218198806cad7796c0b01d1e332c86bb/msgpack-1.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4676e5be1b472909b2ee6356ff425ebedf5142427842aa06b4dfd5117d1ca8a2", size = 392971 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f1/54/65af8de681fa8255402c80eda2a501ba467921d5a7a028c9c22a2c2eedb5/msgpack-1.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:17fb65dd0bec285907f68b15734a993ad3fc94332b5bb21b0435846228de1f39", size = 401403 },
|
||||
{ url = "https://files.pythonhosted.org/packages/97/8c/e333690777bd33919ab7024269dc3c41c76ef5137b211d776fbb404bfead/msgpack-1.1.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a51abd48c6d8ac89e0cfd4fe177c61481aca2d5e7ba42044fd218cfd8ea9899f", size = 385356 },
|
||||
{ url = "https://files.pythonhosted.org/packages/57/52/406795ba478dc1c890559dd4e89280fa86506608a28ccf3a72fbf45df9f5/msgpack-1.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:2137773500afa5494a61b1208619e3871f75f27b03bcfca7b3a7023284140247", size = 383028 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e7/69/053b6549bf90a3acadcd8232eae03e2fefc87f066a5b9fbb37e2e608859f/msgpack-1.1.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:398b713459fea610861c8a7b62a6fec1882759f308ae0795b5413ff6a160cf3c", size = 391100 },
|
||||
{ url = "https://files.pythonhosted.org/packages/23/f0/d4101d4da054f04274995ddc4086c2715d9b93111eb9ed49686c0f7ccc8a/msgpack-1.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:06f5fd2f6bb2a7914922d935d3b8bb4a7fff3a9a91cfce6d06c13bc42bec975b", size = 394254 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1c/12/cf07458f35d0d775ff3a2dc5559fa2e1fcd06c46f1ef510e594ebefdca01/msgpack-1.1.0-cp312-cp312-win32.whl", hash = "sha256:ad33e8400e4ec17ba782f7b9cf868977d867ed784a1f5f2ab46e7ba53b6e1e1b", size = 69085 },
|
||||
{ url = "https://files.pythonhosted.org/packages/73/80/2708a4641f7d553a63bc934a3eb7214806b5b39d200133ca7f7afb0a53e8/msgpack-1.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:115a7af8ee9e8cddc10f87636767857e7e3717b7a2e97379dc2054712693e90f", size = 75347 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c8/b0/380f5f639543a4ac413e969109978feb1f3c66e931068f91ab6ab0f8be00/msgpack-1.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:071603e2f0771c45ad9bc65719291c568d4edf120b44eb36324dcb02a13bfddf", size = 151142 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c8/ee/be57e9702400a6cb2606883d55b05784fada898dfc7fd12608ab1fdb054e/msgpack-1.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0f92a83b84e7c0749e3f12821949d79485971f087604178026085f60ce109330", size = 84523 },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/3a/2919f63acca3c119565449681ad08a2f84b2171ddfcff1dba6959db2cceb/msgpack-1.1.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:4a1964df7b81285d00a84da4e70cb1383f2e665e0f1f2a7027e683956d04b734", size = 81556 },
|
||||
{ url = "https://files.pythonhosted.org/packages/7c/43/a11113d9e5c1498c145a8925768ea2d5fce7cbab15c99cda655aa09947ed/msgpack-1.1.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:59caf6a4ed0d164055ccff8fe31eddc0ebc07cf7326a2aaa0dbf7a4001cd823e", size = 392105 },
|
||||
{ url = "https://files.pythonhosted.org/packages/2d/7b/2c1d74ca6c94f70a1add74a8393a0138172207dc5de6fc6269483519d048/msgpack-1.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0907e1a7119b337971a689153665764adc34e89175f9a34793307d9def08e6ca", size = 399979 },
|
||||
{ url = "https://files.pythonhosted.org/packages/82/8c/cf64ae518c7b8efc763ca1f1348a96f0e37150061e777a8ea5430b413a74/msgpack-1.1.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:65553c9b6da8166e819a6aa90ad15288599b340f91d18f60b2061f402b9a4915", size = 383816 },
|
||||
{ url = "https://files.pythonhosted.org/packages/69/86/a847ef7a0f5ef3fa94ae20f52a4cacf596a4e4a010197fbcc27744eb9a83/msgpack-1.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:7a946a8992941fea80ed4beae6bff74ffd7ee129a90b4dd5cf9c476a30e9708d", size = 380973 },
|
||||
{ url = "https://files.pythonhosted.org/packages/aa/90/c74cf6e1126faa93185d3b830ee97246ecc4fe12cf9d2d31318ee4246994/msgpack-1.1.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:4b51405e36e075193bc051315dbf29168d6141ae2500ba8cd80a522964e31434", size = 387435 },
|
||||
{ url = "https://files.pythonhosted.org/packages/7a/40/631c238f1f338eb09f4acb0f34ab5862c4e9d7eda11c1b685471a4c5ea37/msgpack-1.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b4c01941fd2ff87c2a934ee6055bda4ed353a7846b8d4f341c428109e9fcde8c", size = 399082 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e9/1b/fa8a952be252a1555ed39f97c06778e3aeb9123aa4cccc0fd2acd0b4e315/msgpack-1.1.0-cp313-cp313-win32.whl", hash = "sha256:7c9a35ce2c2573bada929e0b7b3576de647b0defbd25f5139dcdaba0ae35a4cc", size = 69037 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b6/bc/8bd826dd03e022153bfa1766dcdec4976d6c818865ed54223d71f07862b3/msgpack-1.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:bce7d9e614a04d0883af0b3d4d501171fbfca038f12c77fa838d9f198147a23f", size = 75140 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "multidict"
|
||||
version = "6.1.0"
|
||||
@@ -1260,6 +1384,30 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/27/f1/1d7ec15b20f8ce9300bc850de1e059132b88990e46cd0ccac29cbf11e4f9/orjson-3.10.15-cp313-cp313-win_amd64.whl", hash = "sha256:fd56a26a04f6ba5fb2045b0acc487a63162a958ed837648c5781e1fe3316cfbf", size = 133444 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ormsgpack"
|
||||
version = "1.9.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/25/a7/462cf8ff5e29241868b82d3a5ec124d690eb6a6a5c6fa5bb1367b839e027/ormsgpack-1.9.1.tar.gz", hash = "sha256:3da6e63d82565e590b98178545e64f0f8506137b92bd31a2d04fd7c82baf5794", size = 56887 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/dd/f1/155a598cc8030526ccaaf91ba4d61530f87900645559487edba58b0a90a2/ormsgpack-1.9.1-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:1ede445fc3fdba219bb0e0d1f289df26a9c7602016b7daac6fafe8fe4e91548f", size = 383225 },
|
||||
{ url = "https://files.pythonhosted.org/packages/23/1c/ef3097ba550fad55c79525f461febdd4e0d9cc18d065248044536f09488e/ormsgpack-1.9.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db50b9f918e25b289114312ed775794d0978b469831b992bdc65bfe20b91fe30", size = 214056 },
|
||||
{ url = "https://files.pythonhosted.org/packages/27/77/64d0da25896b2cbb99505ca518c109d7dd1964d7fde14c10943731738b60/ormsgpack-1.9.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8c7d8fc58e4333308f58ec720b1ee6b12b2b3fe2d2d8f0766ab751cb351e8757", size = 217339 },
|
||||
{ url = "https://files.pythonhosted.org/packages/6c/10/c3a7fd0a0068b0bb52cccbfeb5656db895d69e895a3abbc210c4b3f98ff8/ormsgpack-1.9.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aeee6d08c040db265cb8563444aba343ecb32cbdbe2414a489dcead9f70c6765", size = 223816 },
|
||||
{ url = "https://files.pythonhosted.org/packages/43/e7/aee1238dba652f2116c2523d36fd1c5f9775436032be5c233108fd2a1415/ormsgpack-1.9.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:2fbb8181c198bdc413a4e889e5200f010724eea4b6d5a9a7eee2df039ac04aca", size = 394287 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/09/1b452a92376f29d7a2da7c18fb01cf09978197a8eccbb8b204e72fd5a970/ormsgpack-1.9.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:16488f094ac0e2250cceea6caf72962614aa432ee11dd57ef45e1ad25ece3eff", size = 480709 },
|
||||
{ url = "https://files.pythonhosted.org/packages/de/13/7fa9fee5a73af8a73a42bf8c2e69489605714f65f5a41454400a05e84a3b/ormsgpack-1.9.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:422d960bfd6ad88be20794f50ec7953d8f7a0f2df60e19d0e8feb994e2ed64ee", size = 397247 },
|
||||
{ url = "https://files.pythonhosted.org/packages/a1/2d/2e87cb28110db0d3bb750edd4d8719b5068852a2eef5e96b0bf376bb8a81/ormsgpack-1.9.1-cp312-cp312-win_amd64.whl", hash = "sha256:e6e2f9eab527cf43fb4a4293e493370276b1c8716cf305689202d646c6a782ef", size = 125368 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b8/54/0390d5d092831e4df29dbafe32402891fc14b3e6ffe5a644b16cbbc9d9bc/ormsgpack-1.9.1-cp313-cp313-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:ac61c18d9dd085e8519b949f7e655f7fb07909fd09c53b4338dd33309012e289", size = 383226 },
|
||||
{ url = "https://files.pythonhosted.org/packages/47/64/8b15d262d1caefead8fb22ec144f5ff7d9505fc31c22bc34598053d46fbe/ormsgpack-1.9.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:134840b8c6615da2c24ce77bd12a46098015c808197a9995c7a2d991e1904eec", size = 214057 },
|
||||
{ url = "https://files.pythonhosted.org/packages/57/00/65823609266bad4d5ed29ea753d24a3bdb01c7edaf923da80967fc31f9c5/ormsgpack-1.9.1-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38fd42618f626394b2c7713c5d4bcbc917254e9753d5d4cde460658b51b11a74", size = 217340 },
|
||||
{ url = "https://files.pythonhosted.org/packages/a0/51/e535c50f7f87b49110233647f55300d7975139ef5e51f1adb4c55f58c124/ormsgpack-1.9.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d36397333ad07b9eba4c2e271fa78951bd81afc059c85a6e9f6c0eb2de07cda", size = 223815 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0c/ee/393e4a6de2a62124bf589602648f295a9fb3907a0e2fe80061b88899d072/ormsgpack-1.9.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:603063089597917d04e4c1b1d53988a34f7dc2ff1a03adcfd1cf4ae966d5fba6", size = 394287 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c6/d8/e56d7c3cb73a0e533e3e2a21ae5838b2aa36a9dac1ca9c861af6bae5a369/ormsgpack-1.9.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:94bbf2b185e0cb721ceaba20e64b7158e6caf0cecd140ca29b9f05a8d5e91e2f", size = 480707 },
|
||||
{ url = "https://files.pythonhosted.org/packages/e6/e0/6a3c6a6dc98583a721c54b02f5195bde8f801aebdeda9b601fa2ab30ad39/ormsgpack-1.9.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:c38f380b1e8c96a712eb302b9349347385161a8e29046868ae2bfdfcb23e2692", size = 397246 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b0/60/0ee5d790f13507e1f75ac21fc82dc1ef29afe1f520bd0f249d65b2f4839b/ormsgpack-1.9.1-cp313-cp313-win_amd64.whl", hash = "sha256:a4bc63fb30db94075611cedbbc3d261dd17cf2aa8ff75a0fd684cd45ca29cb1b", size = 125371 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "packaging"
|
||||
version = "24.2"
|
||||
@@ -1505,6 +1653,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/0b/53/a64f03044927dc47aafe029c42a5b7aabc38dfb813475e0e1bf71c4a59d0/pydantic_settings-2.8.1-py3-none-any.whl", hash = "sha256:81942d5ac3d905f7f3ee1a70df5dfb62d5569c12f51a5a647defc1c3d9ee2e9c", size = 30839 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyjwt"
|
||||
version = "2.10.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e7/46/bd74733ff231675599650d3e47f361794b22ef3e3770998dda30d3b63726/pyjwt-2.10.1.tar.gz", hash = "sha256:3cc5772eb20009233caf06e9d8a0577824723b44e6648ee0a2aedb6cf9381953", size = 87785 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/61/ad/689f02752eeec26aed679477e80e632ef1b682313be70793d798c1d5fc8f/PyJWT-2.10.1-py3-none-any.whl", hash = "sha256:dcdd193e30abefd5debf142f9adfcdd2b58004e644f25406ffaebd50bd98dacb", size = 22997 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pytest"
|
||||
version = "8.3.5"
|
||||
@@ -1803,15 +1960,16 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "sse-starlette"
|
||||
version = "2.2.1"
|
||||
version = "2.1.3"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "anyio" },
|
||||
{ name = "starlette" },
|
||||
{ name = "uvicorn" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/71/a4/80d2a11af59fe75b48230846989e93979c892d3a20016b42bb44edb9e398/sse_starlette-2.2.1.tar.gz", hash = "sha256:54470d5f19274aeed6b2d473430b08b4b379ea851d953b11d7f1c4a2c118b419", size = 17376 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/72/fc/56ab9f116b2133521f532fce8d03194cf04dcac25f583cf3d839be4c0496/sse_starlette-2.1.3.tar.gz", hash = "sha256:9cd27eb35319e1414e3d2558ee7414487f9529ce3b3cf9b21434fd110e017169", size = 19678 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d9/e0/5b8bd393f27f4a62461c5cf2479c75a2cc2ffa330976f9f00f5f6e4f50eb/sse_starlette-2.2.1-py3-none-any.whl", hash = "sha256:6410a3d3ba0c89e7675d4c273a301d64649c03a5ef1ca101f10b47f895fd0e99", size = 10120 },
|
||||
{ url = "https://files.pythonhosted.org/packages/52/aa/36b271bc4fa1d2796311ee7c7283a3a1c348bad426d37293609ca4300eef/sse_starlette-2.1.3-py3-none-any.whl", hash = "sha256:8ec846438b4665b9e8c560fcdea6bc8081a3abf7942faa95e5a744999d219772", size = 9383 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1826,6 +1984,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/a0/4b/528ccf7a982216885a1ff4908e886b8fb5f19862d1962f56a3fce2435a70/starlette-0.46.1-py3-none-any.whl", hash = "sha256:77c74ed9d2720138b25875133f3a2dae6d854af2ec37dceb56aef370c1d8a227", size = 71995 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "structlog"
|
||||
version = "25.3.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/ff/6a/b0b6d440e429d2267076c4819300d9929563b1da959cf1f68afbcd69fe45/structlog-25.3.0.tar.gz", hash = "sha256:8dab497e6f6ca962abad0c283c46744185e0c9ba900db52a423cb6db99f7abeb", size = 1367514 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f5/52/7a2c7a317b254af857464da3d60a0d3730c44f912f8c510c76a738a207fd/structlog-25.3.0-py3-none-any.whl", hash = "sha256:a341f5524004c158498c3127eecded091eb67d3a611e7a3093deca30db06e172", size = 68240 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tenacity"
|
||||
version = "9.0.0"
|
||||
@@ -1896,6 +2063,15 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2", size = 78540 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "truststore"
|
||||
version = "0.10.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/0f/a7/b7a43228762966a13598a404f3dfb4803ea29a906f449d8b0e73ed0bcd30/truststore-0.10.1.tar.gz", hash = "sha256:eda021616b59021812e800fa0a071e51b266721bef3ce092db8a699e21c63539", size = 26101 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/bc/df/8ad635bdcfa8214c399e5614f7c2121dced47defb755a85ea1fa702ffb1c/truststore-0.10.1-py3-none-any.whl", hash = "sha256:b64e6025a409a43ebdd2807b0c41c8bff49ea7ae6550b5087ac6df6619352d4c", size = 18496 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typing-extensions"
|
||||
version = "4.12.2"
|
||||
@@ -1949,6 +2125,42 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/61/14/33a3a1352cfa71812a3a21e8c9bfb83f60b0011f5e36f2b1399d51928209/uvicorn-0.34.0-py3-none-any.whl", hash = "sha256:023dc038422502fa28a09c7a30bf2b6991512da7dcdb8fd35fe57cfc154126f4", size = 62315 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "watchfiles"
|
||||
version = "1.0.5"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "anyio" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/03/e2/8ed598c42057de7aa5d97c472254af4906ff0a59a66699d426fc9ef795d7/watchfiles-1.0.5.tar.gz", hash = "sha256:b7529b5dcc114679d43827d8c35a07c493ad6f083633d573d81c660abc5979e9", size = 94537 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/2a/8c/4f0b9bdb75a1bfbd9c78fad7d8854369283f74fe7cf03eb16be77054536d/watchfiles-1.0.5-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:b5eb568c2aa6018e26da9e6c86f3ec3fd958cee7f0311b35c2630fa4217d17f2", size = 401511 },
|
||||
{ url = "https://files.pythonhosted.org/packages/dc/4e/7e15825def77f8bd359b6d3f379f0c9dac4eb09dd4ddd58fd7d14127179c/watchfiles-1.0.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0a04059f4923ce4e856b4b4e5e783a70f49d9663d22a4c3b3298165996d1377f", size = 392715 },
|
||||
{ url = "https://files.pythonhosted.org/packages/58/65/b72fb817518728e08de5840d5d38571466c1b4a3f724d190cec909ee6f3f/watchfiles-1.0.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e380c89983ce6e6fe2dd1e1921b9952fb4e6da882931abd1824c092ed495dec", size = 454138 },
|
||||
{ url = "https://files.pythonhosted.org/packages/3e/a4/86833fd2ea2e50ae28989f5950b5c3f91022d67092bfec08f8300d8b347b/watchfiles-1.0.5-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fe43139b2c0fdc4a14d4f8d5b5d967f7a2777fd3d38ecf5b1ec669b0d7e43c21", size = 458592 },
|
||||
{ url = "https://files.pythonhosted.org/packages/38/7e/42cb8df8be9a37e50dd3a818816501cf7a20d635d76d6bd65aae3dbbff68/watchfiles-1.0.5-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ee0822ce1b8a14fe5a066f93edd20aada932acfe348bede8aa2149f1a4489512", size = 487532 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fc/fd/13d26721c85d7f3df6169d8b495fcac8ab0dc8f0945ebea8845de4681dab/watchfiles-1.0.5-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a0dbcb1c2d8f2ab6e0a81c6699b236932bd264d4cef1ac475858d16c403de74d", size = 522865 },
|
||||
{ url = "https://files.pythonhosted.org/packages/a1/0d/7f9ae243c04e96c5455d111e21b09087d0eeaf9a1369e13a01c7d3d82478/watchfiles-1.0.5-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a2014a2b18ad3ca53b1f6c23f8cd94a18ce930c1837bd891262c182640eb40a6", size = 499887 },
|
||||
{ url = "https://files.pythonhosted.org/packages/8e/0f/a257766998e26aca4b3acf2ae97dff04b57071e991a510857d3799247c67/watchfiles-1.0.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10f6ae86d5cb647bf58f9f655fcf577f713915a5d69057a0371bc257e2553234", size = 454498 },
|
||||
{ url = "https://files.pythonhosted.org/packages/81/79/8bf142575a03e0af9c3d5f8bcae911ee6683ae93a625d349d4ecf4c8f7df/watchfiles-1.0.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:1a7bac2bde1d661fb31f4d4e8e539e178774b76db3c2c17c4bb3e960a5de07a2", size = 630663 },
|
||||
{ url = "https://files.pythonhosted.org/packages/f1/80/abe2e79f610e45c63a70d271caea90c49bbf93eb00fa947fa9b803a1d51f/watchfiles-1.0.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4ab626da2fc1ac277bbf752446470b367f84b50295264d2d313e28dc4405d663", size = 625410 },
|
||||
{ url = "https://files.pythonhosted.org/packages/91/6f/bc7fbecb84a41a9069c2c6eb6319f7f7df113adf113e358c57fc1aff7ff5/watchfiles-1.0.5-cp312-cp312-win32.whl", hash = "sha256:9f4571a783914feda92018ef3901dab8caf5b029325b5fe4558c074582815249", size = 277965 },
|
||||
{ url = "https://files.pythonhosted.org/packages/99/a5/bf1c297ea6649ec59e935ab311f63d8af5faa8f0b86993e3282b984263e3/watchfiles-1.0.5-cp312-cp312-win_amd64.whl", hash = "sha256:360a398c3a19672cf93527f7e8d8b60d8275119c5d900f2e184d32483117a705", size = 291693 },
|
||||
{ url = "https://files.pythonhosted.org/packages/7f/7b/fd01087cc21db5c47e5beae507b87965db341cce8a86f9eb12bf5219d4e0/watchfiles-1.0.5-cp312-cp312-win_arm64.whl", hash = "sha256:1a2902ede862969077b97523987c38db28abbe09fb19866e711485d9fbf0d417", size = 283287 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/62/435766874b704f39b2fecd8395a29042db2b5ec4005bd34523415e9bd2e0/watchfiles-1.0.5-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:0b289572c33a0deae62daa57e44a25b99b783e5f7aed81b314232b3d3c81a11d", size = 401531 },
|
||||
{ url = "https://files.pythonhosted.org/packages/6e/a6/e52a02c05411b9cb02823e6797ef9bbba0bfaf1bb627da1634d44d8af833/watchfiles-1.0.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:a056c2f692d65bf1e99c41045e3bdcaea3cb9e6b5a53dcaf60a5f3bd95fc9763", size = 392417 },
|
||||
{ url = "https://files.pythonhosted.org/packages/3f/53/c4af6819770455932144e0109d4854437769672d7ad897e76e8e1673435d/watchfiles-1.0.5-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9dca99744991fc9850d18015c4f0438865414e50069670f5f7eee08340d8b40", size = 453423 },
|
||||
{ url = "https://files.pythonhosted.org/packages/cb/d1/8e88df58bbbf819b8bc5cfbacd3c79e01b40261cad0fc84d1e1ebd778a07/watchfiles-1.0.5-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:894342d61d355446d02cd3988a7326af344143eb33a2fd5d38482a92072d9563", size = 458185 },
|
||||
{ url = "https://files.pythonhosted.org/packages/ff/70/fffaa11962dd5429e47e478a18736d4e42bec42404f5ee3b92ef1b87ad60/watchfiles-1.0.5-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ab44e1580924d1ffd7b3938e02716d5ad190441965138b4aa1d1f31ea0877f04", size = 486696 },
|
||||
{ url = "https://files.pythonhosted.org/packages/39/db/723c0328e8b3692d53eb273797d9a08be6ffb1d16f1c0ba2bdbdc2a3852c/watchfiles-1.0.5-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d6f9367b132078b2ceb8d066ff6c93a970a18c3029cea37bfd7b2d3dd2e5db8f", size = 522327 },
|
||||
{ url = "https://files.pythonhosted.org/packages/cd/05/9fccc43c50c39a76b68343484b9da7b12d42d0859c37c61aec018c967a32/watchfiles-1.0.5-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f2e55a9b162e06e3f862fb61e399fe9f05d908d019d87bf5b496a04ef18a970a", size = 499741 },
|
||||
{ url = "https://files.pythonhosted.org/packages/23/14/499e90c37fa518976782b10a18b18db9f55ea73ca14641615056f8194bb3/watchfiles-1.0.5-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0125f91f70e0732a9f8ee01e49515c35d38ba48db507a50c5bdcad9503af5827", size = 453995 },
|
||||
{ url = "https://files.pythonhosted.org/packages/61/d9/f75d6840059320df5adecd2c687fbc18960a7f97b55c300d20f207d48aef/watchfiles-1.0.5-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:13bb21f8ba3248386337c9fa51c528868e6c34a707f729ab041c846d52a0c69a", size = 629693 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fc/17/180ca383f5061b61406477218c55d66ec118e6c0c51f02d8142895fcf0a9/watchfiles-1.0.5-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:839ebd0df4a18c5b3c1b890145b5a3f5f64063c2a0d02b13c76d78fe5de34936", size = 624677 },
|
||||
{ url = "https://files.pythonhosted.org/packages/bf/15/714d6ef307f803f236d69ee9d421763707899d6298d9f3183e55e366d9af/watchfiles-1.0.5-cp313-cp313-win32.whl", hash = "sha256:4a8ec1e4e16e2d5bafc9ba82f7aaecfeec990ca7cd27e84fb6f191804ed2fcfc", size = 277804 },
|
||||
{ url = "https://files.pythonhosted.org/packages/a8/b4/c57b99518fadf431f3ef47a610839e46e5f8abf9814f969859d1c65c02c7/watchfiles-1.0.5-cp313-cp313-win_amd64.whl", hash = "sha256:f436601594f15bf406518af922a89dcaab416568edb6f65c4e5bbbad1ea45c11", size = 291087 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wcwidth"
|
||||
version = "0.2.13"
|
||||
@@ -1967,6 +2179,44 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f4/24/2a3e3df732393fed8b3ebf2ec078f05546de641fe1b667ee316ec1dcf3b7/webencodings-0.5.1-py2.py3-none-any.whl", hash = "sha256:a0af1213f3c2226497a97e2b3aa01a7e4bee4f403f95be16fc9acd2947514a78", size = 11774 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "xxhash"
|
||||
version = "3.5.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/00/5e/d6e5258d69df8b4ed8c83b6664f2b47d30d2dec551a29ad72a6c69eafd31/xxhash-3.5.0.tar.gz", hash = "sha256:84f2caddf951c9cbf8dc2e22a89d4ccf5d86391ac6418fe81e3c67d0cf60b45f", size = 84241 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/07/0e/1bfce2502c57d7e2e787600b31c83535af83746885aa1a5f153d8c8059d6/xxhash-3.5.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:14470ace8bd3b5d51318782cd94e6f94431974f16cb3b8dc15d52f3b69df8e00", size = 31969 },
|
||||
{ url = "https://files.pythonhosted.org/packages/3f/d6/8ca450d6fe5b71ce521b4e5db69622383d039e2b253e9b2f24f93265b52c/xxhash-3.5.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:59aa1203de1cb96dbeab595ded0ad0c0056bb2245ae11fac11c0ceea861382b9", size = 30787 },
|
||||
{ url = "https://files.pythonhosted.org/packages/5b/84/de7c89bc6ef63d750159086a6ada6416cc4349eab23f76ab870407178b93/xxhash-3.5.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:08424f6648526076e28fae6ea2806c0a7d504b9ef05ae61d196d571e5c879c84", size = 220959 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fe/86/51258d3e8a8545ff26468c977101964c14d56a8a37f5835bc0082426c672/xxhash-3.5.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:61a1ff00674879725b194695e17f23d3248998b843eb5e933007ca743310f793", size = 200006 },
|
||||
{ url = "https://files.pythonhosted.org/packages/02/0a/96973bd325412feccf23cf3680fd2246aebf4b789122f938d5557c54a6b2/xxhash-3.5.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f2f2c61bee5844d41c3eb015ac652a0229e901074951ae48581d58bfb2ba01be", size = 428326 },
|
||||
{ url = "https://files.pythonhosted.org/packages/11/a7/81dba5010f7e733de88af9555725146fc133be97ce36533867f4c7e75066/xxhash-3.5.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d32a592cac88d18cc09a89172e1c32d7f2a6e516c3dfde1b9adb90ab5df54a6", size = 194380 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fb/7d/f29006ab398a173f4501c0e4977ba288f1c621d878ec217b4ff516810c04/xxhash-3.5.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:70dabf941dede727cca579e8c205e61121afc9b28516752fd65724be1355cc90", size = 207934 },
|
||||
{ url = "https://files.pythonhosted.org/packages/8a/6e/6e88b8f24612510e73d4d70d9b0c7dff62a2e78451b9f0d042a5462c8d03/xxhash-3.5.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e5d0ddaca65ecca9c10dcf01730165fd858533d0be84c75c327487c37a906a27", size = 216301 },
|
||||
{ url = "https://files.pythonhosted.org/packages/af/51/7862f4fa4b75a25c3b4163c8a873f070532fe5f2d3f9b3fc869c8337a398/xxhash-3.5.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:3e5b5e16c5a480fe5f59f56c30abdeba09ffd75da8d13f6b9b6fd224d0b4d0a2", size = 203351 },
|
||||
{ url = "https://files.pythonhosted.org/packages/22/61/8d6a40f288f791cf79ed5bb113159abf0c81d6efb86e734334f698eb4c59/xxhash-3.5.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:149b7914451eb154b3dfaa721315117ea1dac2cc55a01bfbd4df7c68c5dd683d", size = 210294 },
|
||||
{ url = "https://files.pythonhosted.org/packages/17/02/215c4698955762d45a8158117190261b2dbefe9ae7e5b906768c09d8bc74/xxhash-3.5.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:eade977f5c96c677035ff39c56ac74d851b1cca7d607ab3d8f23c6b859379cab", size = 414674 },
|
||||
{ url = "https://files.pythonhosted.org/packages/31/5c/b7a8db8a3237cff3d535261325d95de509f6a8ae439a5a7a4ffcff478189/xxhash-3.5.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fa9f547bd98f5553d03160967866a71056a60960be00356a15ecc44efb40ba8e", size = 192022 },
|
||||
{ url = "https://files.pythonhosted.org/packages/78/e3/dd76659b2811b3fd06892a8beb850e1996b63e9235af5a86ea348f053e9e/xxhash-3.5.0-cp312-cp312-win32.whl", hash = "sha256:f7b58d1fd3551b8c80a971199543379be1cee3d0d409e1f6d8b01c1a2eebf1f8", size = 30170 },
|
||||
{ url = "https://files.pythonhosted.org/packages/d9/6b/1c443fe6cfeb4ad1dcf231cdec96eb94fb43d6498b4469ed8b51f8b59a37/xxhash-3.5.0-cp312-cp312-win_amd64.whl", hash = "sha256:fa0cafd3a2af231b4e113fba24a65d7922af91aeb23774a8b78228e6cd785e3e", size = 30040 },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/eb/04405305f290173acc0350eba6d2f1a794b57925df0398861a20fbafa415/xxhash-3.5.0-cp312-cp312-win_arm64.whl", hash = "sha256:586886c7e89cb9828bcd8a5686b12e161368e0064d040e225e72607b43858ba2", size = 26796 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c9/b8/e4b3ad92d249be5c83fa72916c9091b0965cb0faeff05d9a0a3870ae6bff/xxhash-3.5.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:37889a0d13b0b7d739cfc128b1c902f04e32de17b33d74b637ad42f1c55101f6", size = 31795 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fc/d8/b3627a0aebfbfa4c12a41e22af3742cf08c8ea84f5cc3367b5de2d039cce/xxhash-3.5.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:97a662338797c660178e682f3bc180277b9569a59abfb5925e8620fba00b9fc5", size = 30792 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c3/cc/762312960691da989c7cd0545cb120ba2a4148741c6ba458aa723c00a3f8/xxhash-3.5.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f85e0108d51092bdda90672476c7d909c04ada6923c14ff9d913c4f7dc8a3bc", size = 220950 },
|
||||
{ url = "https://files.pythonhosted.org/packages/fe/e9/cc266f1042c3c13750e86a535496b58beb12bf8c50a915c336136f6168dc/xxhash-3.5.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cd2fd827b0ba763ac919440042302315c564fdb797294d86e8cdd4578e3bc7f3", size = 199980 },
|
||||
{ url = "https://files.pythonhosted.org/packages/bf/85/a836cd0dc5cc20376de26b346858d0ac9656f8f730998ca4324921a010b9/xxhash-3.5.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:82085c2abec437abebf457c1d12fccb30cc8b3774a0814872511f0f0562c768c", size = 428324 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b4/0e/15c243775342ce840b9ba34aceace06a1148fa1630cd8ca269e3223987f5/xxhash-3.5.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:07fda5de378626e502b42b311b049848c2ef38784d0d67b6f30bb5008642f8eb", size = 194370 },
|
||||
{ url = "https://files.pythonhosted.org/packages/87/a1/b028bb02636dfdc190da01951d0703b3d904301ed0ef6094d948983bef0e/xxhash-3.5.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c279f0d2b34ef15f922b77966640ade58b4ccdfef1c4d94b20f2a364617a493f", size = 207911 },
|
||||
{ url = "https://files.pythonhosted.org/packages/80/d5/73c73b03fc0ac73dacf069fdf6036c9abad82de0a47549e9912c955ab449/xxhash-3.5.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:89e66ceed67b213dec5a773e2f7a9e8c58f64daeb38c7859d8815d2c89f39ad7", size = 216352 },
|
||||
{ url = "https://files.pythonhosted.org/packages/b6/2a/5043dba5ddbe35b4fe6ea0a111280ad9c3d4ba477dd0f2d1fe1129bda9d0/xxhash-3.5.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:bcd51708a633410737111e998ceb3b45d3dbc98c0931f743d9bb0a209033a326", size = 203410 },
|
||||
{ url = "https://files.pythonhosted.org/packages/a2/b2/9a8ded888b7b190aed75b484eb5c853ddd48aa2896e7b59bbfbce442f0a1/xxhash-3.5.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:3ff2c0a34eae7df88c868be53a8dd56fbdf592109e21d4bfa092a27b0bf4a7bf", size = 210322 },
|
||||
{ url = "https://files.pythonhosted.org/packages/98/62/440083fafbc917bf3e4b67c2ade621920dd905517e85631c10aac955c1d2/xxhash-3.5.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:4e28503dccc7d32e0b9817aa0cbfc1f45f563b2c995b7a66c4c8a0d232e840c7", size = 414725 },
|
||||
{ url = "https://files.pythonhosted.org/packages/75/db/009206f7076ad60a517e016bb0058381d96a007ce3f79fa91d3010f49cc2/xxhash-3.5.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a6c50017518329ed65a9e4829154626f008916d36295b6a3ba336e2458824c8c", size = 192070 },
|
||||
{ url = "https://files.pythonhosted.org/packages/1f/6d/c61e0668943a034abc3a569cdc5aeae37d686d9da7e39cf2ed621d533e36/xxhash-3.5.0-cp313-cp313-win32.whl", hash = "sha256:53a068fe70301ec30d868ece566ac90d873e3bb059cf83c32e76012c889b8637", size = 30172 },
|
||||
{ url = "https://files.pythonhosted.org/packages/96/14/8416dce965f35e3d24722cdf79361ae154fa23e2ab730e5323aa98d7919e/xxhash-3.5.0-cp313-cp313-win_amd64.whl", hash = "sha256:80babcc30e7a1a484eab952d76a4f4673ff601f54d5142c26826502740e70b43", size = 30041 },
|
||||
{ url = "https://files.pythonhosted.org/packages/27/ee/518b72faa2073f5aa8e3262408d284892cb79cf2754ba0c3a5870645ef73/xxhash-3.5.0-cp313-cp313-win_arm64.whl", hash = "sha256:4811336f1ce11cac89dcbd18f3a25c527c16311709a89313c3acaf771def2d4b", size = 26801 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "yarl"
|
||||
version = "1.18.3"
|
||||
|
||||
@@ -75,7 +75,9 @@ function ActivityMessage({ messageId }: { messageId: string }) {
|
||||
if (message.agent !== "reporter" && message.agent !== "planner") {
|
||||
return (
|
||||
<div className="px-4 py-2">
|
||||
<Markdown animated>{message.content}</Markdown>
|
||||
<Markdown animated checkLinkCredibility>
|
||||
{message.content}
|
||||
</Markdown>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -304,10 +306,58 @@ function PythonToolCall({ toolCall }: { toolCall: ToolCallRuntime }) {
|
||||
</SyntaxHighlighter>
|
||||
</div>
|
||||
</div>
|
||||
{toolCall.result && <PythonToolCallResult result={toolCall.result} />}
|
||||
</section>
|
||||
);
|
||||
}
|
||||
|
||||
function PythonToolCallResult({ result }: { result: string }) {
|
||||
const { resolvedTheme } = useTheme();
|
||||
const hasError = useMemo(
|
||||
() => result.includes("Error executing code:\n"),
|
||||
[result],
|
||||
);
|
||||
const error = useMemo(() => {
|
||||
if (hasError) {
|
||||
const parts = result.split("```\nError: ");
|
||||
if (parts.length > 1) {
|
||||
return parts[1]!.trim();
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}, [result, hasError]);
|
||||
const stdout = useMemo(() => {
|
||||
if (!hasError) {
|
||||
const parts = result.split("```\nStdout: ");
|
||||
if (parts.length > 1) {
|
||||
return parts[1]!.trim();
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}, [result, hasError]);
|
||||
return (
|
||||
<>
|
||||
<div className="mt-4 font-medium italic">
|
||||
{hasError ? "Error when executing the above code" : "Execution output"}
|
||||
</div>
|
||||
<div className="bg-accent mt-2 max-h-[400px] max-w-[calc(100%-120px)] overflow-y-auto rounded-md p-2 text-sm">
|
||||
<SyntaxHighlighter
|
||||
language="plaintext"
|
||||
style={resolvedTheme === "dark" ? dark : docco}
|
||||
customStyle={{
|
||||
color: hasError ? "red" : "inherit",
|
||||
background: "transparent",
|
||||
border: "none",
|
||||
boxShadow: "none",
|
||||
}}
|
||||
>
|
||||
{error ?? stdout ?? "(empty)"}
|
||||
</SyntaxHighlighter>
|
||||
</div>
|
||||
</>
|
||||
);
|
||||
}
|
||||
|
||||
function MCPToolCall({ toolCall }: { toolCall: ToolCallRuntime }) {
|
||||
const tool = useMemo(() => findMCPTool(toolCall.name), [toolCall.name]);
|
||||
const { resolvedTheme } = useTheme();
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
// Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
||||
// SPDX-License-Identifier: MIT
|
||||
|
||||
import { Check, Copy, Headphones, X } from "lucide-react";
|
||||
import { Check, Copy, Headphones, Pencil, Undo2, X } from "lucide-react";
|
||||
import { useCallback, useEffect, useState } from "react";
|
||||
|
||||
import { ScrollContainer } from "~/components/deer-flow/scroll-container";
|
||||
@@ -47,6 +47,7 @@ export function ResearchBlock({
|
||||
await listenToPodcast(researchId);
|
||||
}, [researchId]);
|
||||
|
||||
const [editing, setEditing] = useState(false);
|
||||
const [copied, setCopied] = useState(false);
|
||||
const handleCopy = useCallback(() => {
|
||||
if (!reportId) {
|
||||
@@ -63,6 +64,10 @@ export function ResearchBlock({
|
||||
}, 1000);
|
||||
}, [reportId]);
|
||||
|
||||
const handleEdit = useCallback(() => {
|
||||
setEditing((editing) => !editing);
|
||||
}, []);
|
||||
|
||||
// When the research id changes, set the active tab to activities
|
||||
useEffect(() => {
|
||||
if (!hasReport) {
|
||||
@@ -87,6 +92,17 @@ export function ResearchBlock({
|
||||
<Headphones />
|
||||
</Button>
|
||||
</Tooltip>
|
||||
<Tooltip title="Edit">
|
||||
<Button
|
||||
className="text-gray-400"
|
||||
size="icon"
|
||||
variant="ghost"
|
||||
disabled={isReplay}
|
||||
onClick={handleEdit}
|
||||
>
|
||||
{editing ? <Undo2 /> : <Pencil />}
|
||||
</Button>
|
||||
</Tooltip>
|
||||
<Tooltip title="Copy">
|
||||
<Button
|
||||
className="text-gray-400"
|
||||
@@ -147,6 +163,7 @@ export function ResearchBlock({
|
||||
className="mt-4"
|
||||
researchId={researchId}
|
||||
messageId={reportId}
|
||||
editing={editing}
|
||||
/>
|
||||
)}
|
||||
</ScrollContainer>
|
||||
|
||||
@@ -13,10 +13,12 @@ import { cn } from "~/lib/utils";
|
||||
export function ResearchReportBlock({
|
||||
className,
|
||||
messageId,
|
||||
editing,
|
||||
}: {
|
||||
className?: string;
|
||||
researchId: string;
|
||||
messageId: string;
|
||||
editing: boolean;
|
||||
}) {
|
||||
const message = useMessage(messageId);
|
||||
const { isReplay } = useReplay();
|
||||
@@ -55,14 +57,16 @@ export function ResearchReportBlock({
|
||||
ref={contentRef}
|
||||
className={cn("relative flex flex-col pt-4 pb-8", className)}
|
||||
>
|
||||
{!isReplay && isCompleted ? (
|
||||
{!isReplay && isCompleted && editing ? (
|
||||
<ReportEditor
|
||||
content={message?.content}
|
||||
onMarkdownChange={handleMarkdownChange}
|
||||
/>
|
||||
) : (
|
||||
<>
|
||||
<Markdown animated>{message?.content}</Markdown>
|
||||
<Markdown animated checkLinkCredibility>
|
||||
{message?.content}
|
||||
</Markdown>
|
||||
{message?.isStreaming && <LoadingAnimation className="my-12" />}
|
||||
</>
|
||||
)}
|
||||
|
||||
@@ -20,7 +20,7 @@ export default function Main() {
|
||||
return (
|
||||
<div
|
||||
className={cn(
|
||||
"flex h-full w-full justify-center px-4 pt-12 pb-4",
|
||||
"flex h-full w-full justify-center-safe px-4 pt-12 pb-4",
|
||||
doubleColumnMode && "gap-8",
|
||||
)}
|
||||
>
|
||||
@@ -28,13 +28,13 @@ export default function Main() {
|
||||
className={cn(
|
||||
"shrink-0 transition-all duration-300 ease-out",
|
||||
!doubleColumnMode &&
|
||||
`w-[768px] translate-x-[min(calc((100vw-538px)*0.75/2),960px/2)]`,
|
||||
`w-[768px] translate-x-[min(max(calc((100vw-538px)*0.75),575px)/2,960px/2)]`,
|
||||
doubleColumnMode && `w-[538px]`,
|
||||
)}
|
||||
/>
|
||||
<ResearchBlock
|
||||
className={cn(
|
||||
"w-[min(calc((100vw-538px)*0.75),960px)] pb-4 transition-all duration-300 ease-out",
|
||||
"w-[min(max(calc((100vw-538px)*0.75),575px),960px)] pb-4 transition-all duration-300 ease-out",
|
||||
!doubleColumnMode && "scale-0",
|
||||
doubleColumnMode && "",
|
||||
)}
|
||||
|
||||
@@ -147,7 +147,7 @@ export function MultiAgentVisualization({ className }: { className?: string }) {
|
||||
</Tooltip>
|
||||
<div className="text-muted-foreground ml-2 flex items-center justify-center">
|
||||
<Slider
|
||||
className="w-120"
|
||||
className="w-40 sm:w-80 md:w-100 lg:w-120"
|
||||
max={playbook.steps.length - 1}
|
||||
min={0}
|
||||
step={1}
|
||||
|
||||
@@ -32,6 +32,9 @@ const generalFormSchema = z.object({
|
||||
maxStepNum: z.number().min(1, {
|
||||
message: "Max step number must be at least 1.",
|
||||
}),
|
||||
maxSearchResults: z.number().min(1, {
|
||||
message: "Max search results must be at least 1.",
|
||||
}),
|
||||
});
|
||||
|
||||
export const GeneralTab: Tab = ({
|
||||
@@ -143,6 +146,30 @@ export const GeneralTab: Tab = ({
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
<FormField
|
||||
control={form.control}
|
||||
name="maxSearchResults"
|
||||
render={({ field }) => (
|
||||
<FormItem>
|
||||
<FormLabel>Max search results</FormLabel>
|
||||
<FormControl>
|
||||
<Input
|
||||
className="w-60"
|
||||
type="number"
|
||||
defaultValue={field.value}
|
||||
min={1}
|
||||
onChange={(event) =>
|
||||
field.onChange(parseInt(event.target.value || "0"))
|
||||
}
|
||||
/>
|
||||
</FormControl>
|
||||
<FormDescription>
|
||||
By default, each search step has 3 results.
|
||||
</FormDescription>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
</form>
|
||||
</Form>
|
||||
</main>
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
import { useMemo } from "react";
|
||||
import { useStore, useToolCalls } from "~/core/store";
|
||||
import { Tooltip } from "./tooltip";
|
||||
import { WarningFilled } from "@ant-design/icons";
|
||||
|
||||
export const Link = ({
|
||||
href,
|
||||
children,
|
||||
checkLinkCredibility = false,
|
||||
}: {
|
||||
href: string | undefined;
|
||||
children: React.ReactNode;
|
||||
checkLinkCredibility: boolean;
|
||||
}) => {
|
||||
const toolCalls = useToolCalls();
|
||||
const responding = useStore((state) => state.responding);
|
||||
|
||||
const credibleLinks = useMemo(() => {
|
||||
const links = new Set<string>();
|
||||
if (!checkLinkCredibility) return links;
|
||||
|
||||
(toolCalls || []).forEach((call) => {
|
||||
if (call && call.name === "web_search" && call.result) {
|
||||
const result = JSON.parse(call.result) as Array<{ url: string }>;
|
||||
result.forEach((r) => {
|
||||
links.add(r.url);
|
||||
});
|
||||
}
|
||||
});
|
||||
return links;
|
||||
}, [toolCalls]);
|
||||
|
||||
const isCredible = useMemo(() => {
|
||||
return checkLinkCredibility && href && !responding
|
||||
? credibleLinks.has(href)
|
||||
: true;
|
||||
}, [credibleLinks, href, responding, checkLinkCredibility]);
|
||||
|
||||
return (
|
||||
<span className="flex items-center gap-1.5">
|
||||
<a href={href} target="_blank" rel="noopener noreferrer">
|
||||
{children}
|
||||
</a>
|
||||
{!isCredible && (
|
||||
<Tooltip
|
||||
title="This link might be a hallucination from AI model and may not be reliable."
|
||||
delayDuration={300}
|
||||
>
|
||||
<WarningFilled className="text-sx transition-colors hover:!text-yellow-500" />
|
||||
</Tooltip>
|
||||
)}
|
||||
</span>
|
||||
);
|
||||
};
|
||||
@@ -18,19 +18,7 @@ import { cn } from "~/lib/utils";
|
||||
|
||||
import Image from "./image";
|
||||
import { Tooltip } from "./tooltip";
|
||||
|
||||
const components: ReactMarkdownOptions["components"] = {
|
||||
a: ({ href, children }) => (
|
||||
<a href={href} target="_blank" rel="noopener noreferrer">
|
||||
{children}
|
||||
</a>
|
||||
),
|
||||
img: ({ src, alt }) => (
|
||||
<a href={src as string} target="_blank" rel="noopener noreferrer">
|
||||
<Image className="rounded" src={src as string} alt={alt ?? ""} />
|
||||
</a>
|
||||
),
|
||||
};
|
||||
import { Link } from "./link";
|
||||
|
||||
export function Markdown({
|
||||
className,
|
||||
@@ -38,13 +26,30 @@ export function Markdown({
|
||||
style,
|
||||
enableCopy,
|
||||
animated = false,
|
||||
checkLinkCredibility = false,
|
||||
...props
|
||||
}: ReactMarkdownOptions & {
|
||||
className?: string;
|
||||
enableCopy?: boolean;
|
||||
style?: React.CSSProperties;
|
||||
animated?: boolean;
|
||||
checkLinkCredibility?: boolean;
|
||||
}) {
|
||||
const components: ReactMarkdownOptions["components"] = useMemo(() => {
|
||||
return {
|
||||
a: ({ href, children }) => (
|
||||
<Link href={href} checkLinkCredibility={checkLinkCredibility}>
|
||||
{children}
|
||||
</Link>
|
||||
),
|
||||
img: ({ src, alt }) => (
|
||||
<a href={src as string} target="_blank" rel="noopener noreferrer">
|
||||
<Image className="rounded" src={src as string} alt={alt ?? ""} />
|
||||
</a>
|
||||
),
|
||||
};
|
||||
}, [checkLinkCredibility]);
|
||||
|
||||
const rehypePlugins = useMemo(() => {
|
||||
if (animated) {
|
||||
return [rehypeKatex, rehypeSplitWordsIntoSpans];
|
||||
@@ -52,13 +57,7 @@ export function Markdown({
|
||||
return [rehypeKatex];
|
||||
}, [animated]);
|
||||
return (
|
||||
<div
|
||||
className={cn(
|
||||
className,
|
||||
"prose dark:prose-invert prose-p:my-0 prose-img:mt-0 flex flex-col gap-4",
|
||||
)}
|
||||
style={style}
|
||||
>
|
||||
<div className={cn(className, "prose dark:prose-invert")} style={style}>
|
||||
<ReactMarkdown
|
||||
remarkPlugins={[remarkGfm, remarkMath]}
|
||||
rehypePlugins={rehypePlugins}
|
||||
|
||||
@@ -19,6 +19,7 @@ export function Tooltip({
|
||||
open,
|
||||
side,
|
||||
sideOffset,
|
||||
delayDuration = 750,
|
||||
}: {
|
||||
className?: string;
|
||||
style?: CSSProperties;
|
||||
@@ -27,10 +28,11 @@ export function Tooltip({
|
||||
open?: boolean;
|
||||
side?: "left" | "right" | "top" | "bottom";
|
||||
sideOffset?: number;
|
||||
delayDuration?: number;
|
||||
}) {
|
||||
return (
|
||||
<TooltipProvider>
|
||||
<ShadcnTooltip delayDuration={750} open={open}>
|
||||
<ShadcnTooltip delayDuration={delayDuration} open={open}>
|
||||
<TooltipTrigger asChild>{children}</TooltipTrigger>
|
||||
<TooltipContent
|
||||
className={cn(className)}
|
||||
|
||||
@@ -78,16 +78,12 @@ const taskItem = TaskItem.configure({
|
||||
});
|
||||
|
||||
const horizontalRule = HorizontalRule.configure({
|
||||
HTMLAttributes: {
|
||||
class: cx("mt-4 mb-6 border-t border-muted-foreground"),
|
||||
},
|
||||
HTMLAttributes: {},
|
||||
});
|
||||
|
||||
const starterKit = StarterKit.configure({
|
||||
bulletList: {
|
||||
HTMLAttributes: {
|
||||
class: cx("list-disc list-outside leading-3 -mt-2"),
|
||||
},
|
||||
HTMLAttributes: {},
|
||||
},
|
||||
orderedList: {
|
||||
HTMLAttributes: {
|
||||
@@ -95,9 +91,7 @@ const starterKit = StarterKit.configure({
|
||||
},
|
||||
},
|
||||
listItem: {
|
||||
HTMLAttributes: {
|
||||
class: cx("leading-normal -mb-2"),
|
||||
},
|
||||
HTMLAttributes: {},
|
||||
},
|
||||
blockquote: {
|
||||
HTMLAttributes: {
|
||||
@@ -107,7 +101,6 @@ const starterKit = StarterKit.configure({
|
||||
codeBlock: false,
|
||||
code: {
|
||||
HTMLAttributes: {
|
||||
class: cx("rounded-md bg-muted px-1.5 py-1 font-mono font-medium"),
|
||||
spellcheck: "false",
|
||||
},
|
||||
},
|
||||
|
||||
@@ -18,6 +18,7 @@ export async function* chatStream(
|
||||
auto_accepted_plan: boolean;
|
||||
max_plan_iterations: number;
|
||||
max_step_num: number;
|
||||
max_search_results?: number;
|
||||
interrupt_feedback?: string;
|
||||
enable_background_investigation: boolean;
|
||||
mcp_settings?: {
|
||||
@@ -61,12 +62,14 @@ async function* chatReplayStream(
|
||||
auto_accepted_plan: boolean;
|
||||
max_plan_iterations: number;
|
||||
max_step_num: number;
|
||||
max_search_results?: number;
|
||||
interrupt_feedback?: string;
|
||||
} = {
|
||||
thread_id: "__mock__",
|
||||
auto_accepted_plan: false,
|
||||
max_plan_iterations: 3,
|
||||
max_step_num: 1,
|
||||
max_search_results: 3,
|
||||
interrupt_feedback: undefined,
|
||||
},
|
||||
options: { abortSignal?: AbortSignal } = {},
|
||||
@@ -157,6 +160,7 @@ export async function fetchReplayTitle() {
|
||||
auto_accepted_plan: false,
|
||||
max_plan_iterations: 3,
|
||||
max_step_num: 1,
|
||||
max_search_results: 3,
|
||||
},
|
||||
{},
|
||||
);
|
||||
|
||||
@@ -13,6 +13,7 @@ const DEFAULT_SETTINGS: SettingsState = {
|
||||
enableBackgroundInvestigation: false,
|
||||
maxPlanIterations: 1,
|
||||
maxStepNum: 3,
|
||||
maxSearchResults: 3,
|
||||
},
|
||||
mcp: {
|
||||
servers: [],
|
||||
@@ -25,6 +26,7 @@ export type SettingsState = {
|
||||
enableBackgroundInvestigation: boolean;
|
||||
maxPlanIterations: number;
|
||||
maxStepNum: number;
|
||||
maxSearchResults: number;
|
||||
};
|
||||
mcp: {
|
||||
servers: MCPServerMetadata[];
|
||||
|
||||
@@ -104,6 +104,7 @@ export async function sendMessage(
|
||||
settings.enableBackgroundInvestigation ?? true,
|
||||
max_plan_iterations: settings.maxPlanIterations,
|
||||
max_step_num: settings.maxStepNum,
|
||||
max_search_results: settings.maxSearchResults,
|
||||
mcp_settings: settings.mcpSettings,
|
||||
},
|
||||
options,
|
||||
@@ -377,3 +378,14 @@ export function useLastFeedbackMessageId() {
|
||||
);
|
||||
return waitingForFeedbackMessageId;
|
||||
}
|
||||
|
||||
export function useToolCalls() {
|
||||
return useStore(
|
||||
useShallow((state) => {
|
||||
return state.messageIds
|
||||
?.map((id) => getMessage(id)?.toolCalls)
|
||||
.filter((toolCalls) => toolCalls != null)
|
||||
.flat();
|
||||
}),
|
||||
);
|
||||
}
|
||||
|
||||
@@ -4,6 +4,10 @@
|
||||
color: inherit;
|
||||
}
|
||||
|
||||
.ProseMirror {
|
||||
line-height: 1.75;
|
||||
}
|
||||
|
||||
.ProseMirror .is-editor-empty:first-child::before {
|
||||
content: attr(data-placeholder);
|
||||
float: left;
|
||||
|
||||
Reference in New Issue
Block a user