langgraph-agent-toolkit 0.1.2__tar.gz → 0.3.0__tar.gz

langgraph_agent_toolkit-0.3.0/.coveragerc

@@ -0,0 +1,6 @@
+[run]
+omit =
+    examples/*
+    scripts/*
+    tests/*
+    langgraph_agent_toolkit/agents/blueprints/*

langgraph_agent_toolkit-0.3.0/.env.example

@@ -0,0 +1,115 @@
+# Web server configuration
+HOST=0.0.0.0
+PORT=8080
+
+# Application mode. If the value is "dev", it will enable uvicorn reload
+ENV_MODE=development
+
+# Authentication secret, HTTP bearer token header is required if set
+AUTH_SECRET=
+
+# Observability backend
+# OBSERVABILITY_BACKEND=langfuse
+
+# Langfuse configuration
+# LANGFUSE_SECRET_KEY=
+# LANGFUSE_PUBLIC_KEY=
+# LANGFUSE_HOST=http://langfuse-web:3000
+
+# Langsmith configuration
+# LANGSMITH_TRACING=true
+# LANGSMITH_API_KEY=
+# LANGSMITH_PROJECT=default
+# LANGSMITH_ENDPOINT=https://api.smith.langchain.com
+
+# Database type.
+# If the value is "postgres", then it will require Postgresql related environment variables.
+# If the value is "sqlite", then you can configure optional file path via SQLITE_DB_PATH
+MEMORY_BACKEND=postgres
+
+# If DATABASE_TYPE=sqlite (Optional)
+SQLITE_DB_PATH=
+
+# If DATABASE_TYPE=postgres
+POSTGRES_USER=
+POSTGRES_PASSWORD=
+POSTGRES_HOST=
+POSTGRES_PORT=
+POSTGRES_DB=agents
+# Connection pool settings (optional)
+POSTGRES_POOL_SIZE=10
+POSTGRES_MIN_SIZE=3
+POSTGRES_MAX_IDLE=5
+
+# Agent URL: used in Streamlit app - if not set, defaults to http://{HOST}:{PORT}
+# AGENT_URL=http://0.0.0.0:8080
+
+# Use a fake model for testing
+USE_FAKE_MODEL=false
+
+# OpenAI Settings
+OPENAI_API_KEY=
+OPENAI_API_BASE_URL=
+OPENAI_API_VERSION=
+OPENAI_MODEL_NAME=
+
+# Azure OpenAI Settings
+AZURE_OPENAI_API_KEY=
+AZURE_OPENAI_ENDPOINT=
+AZURE_OPENAI_API_VERSION=
+AZURE_OPENAI_MODEL_NAME=
+AZURE_OPENAI_DEPLOYMENT_NAME=
+
+# Anthropic Settings
+ANTHROPIC_API_KEY=
+ANTHROPIC_MODEL_NAME=
+
+ # Google VertexAI Settings
+GOOGLE_VERTEXAI_MODEL_NAME=
+GOOGLE_VERTEXAI_API_KEY=
+
+# Google GenAI Settings
+GOOGLE_GENAI_MODEL_NAME=
+GOOGLE_GENAI_API_KEY=
+
+# Bedrock Settings
+AWS_BEDROCK_MODEL_NAME=
+
+# DeepSeek Settings
+DEEPSEEK_MODEL_NAME=
+DEEPSEEK_API_KEY=
+
+# Ollama Settings
+OLLAMA_MODEL_NAME=
+OLLAMA_BASE_URL=
+
+# Model configurations - use multiline format with line continuation for readability
+# It can be useful if you want to use different models for different agents or use different models from different providers.
+MODEL_CONFIGS={\
+  "gpt4o": {\
+    "provider": "azure_openai",\
+    "name": "gpt-4o",\
+    "api_key": "azure-key-123",\
+    "endpoint": "https://your-resource.openai.azure.com/",\
+    "api_version": "2023-05-15",\
+    "deployment": "gpt4o-deployment",\
+    "temperature": 0.7\
+  },\
+  "gpt4o-mini": {\
+    "provider": "azure_openai",\
+    "name": "gpt-4o-mini",\
+    "api_key": "azure-key-123",\
+    "endpoint": "https://your-resource.openai.azure.com/",\
+    "api_version": "2023-05-15",\
+    "deployment": "gpt4o-mini-deployment"\
+  },\
+  "gemini": {\
+    "provider": "google_genai",\
+    "name": "gemini-pro",\
+    "api_key": "google-key-123",\
+    "temperature": 0.7\
+  }\
+}
+
+# Amazon Bedrock Knowledge Base ID
+AWS_KB_ID=

{langgraph_agent_toolkit-0.1.2 → langgraph_agent_toolkit-0.3.0}/.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +1,5 @@
+# PR Description
+
 ## Summary
 
 <!-- Provide a concise summary "Why are the changes needed"?

{langgraph_agent_toolkit-0.1.2 → langgraph_agent_toolkit-0.3.0}/.github/workflows/release.yml

@@ -13,7 +13,7 @@ jobs:
           fetch-depth: 0
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
           version: "0.6.12"
           enable-cache: true

{langgraph_agent_toolkit-0.1.2 → langgraph_agent_toolkit-0.3.0}/.github/workflows/test.yml

@@ -34,7 +34,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
           version: "0.6.12"
       - name: Install dependencies with uv
@@ -135,7 +135,7 @@ jobs:
         with:
           python-version-file: "pyproject.toml"
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
           version: "0.6.12"
       - name: Install ONLY CLIENT dependencies with uv

{langgraph_agent_toolkit-0.1.2 → langgraph_agent_toolkit-0.3.0}/.pre-commit-config.yaml

@@ -27,11 +27,11 @@ repos:
   - repo: https://github.com/nbQA-dev/nbQA
     rev: 1.9.1
     hooks:
-      - id: nbqa-ruff-format
-        additional_dependencies: [ruff==0.11.4]
       - id: nbqa-ruff
         additional_dependencies: [ruff==0.11.4]
-        args: ["--fix", "--show-source"]
+        args: ["--fix", "--show-files"]
+      - id: nbqa-ruff-format
+        additional_dependencies: [ruff==0.11.4]
 
   - repo: https://github.com/kynan/nbstripout
     rev: 0.8.1

{langgraph_agent_toolkit-0.1.2 → langgraph_agent_toolkit-0.3.0}/CHANGELOG.md

@@ -6,6 +6,31 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to
 [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.0]
+
+### Added
+
+- `MODEL_CONFIGS` to unify LLM env variables
+- New blueprint with AWS KB
+
+### Fixed
+
+- Streaming messages handling
+- Refactored code structure for better maintainability
+- Optional dependencies
+- API exception handling
+
+## [0.2.0]
+
+### Fixed
+
+- Refactored code structure for better maintainability
+- Refactored Model factory
+
+### Removed
+
+- Removed AllModels and added environment variables for different providers
+
 ## [0.1.2]
 
 ### Added

langgraph_agent_toolkit-0.1.2/README.md → langgraph_agent_toolkit-0.3.0/PKG-INFO

@@ -1,3 +1,98 @@
+Metadata-Version: 2.4
+Name: langgraph-agent-toolkit
+Version: 0.3.0
+Summary: Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit
+Project-URL: repository, https://github.com/kryvokhyzha/langgraph-agent-toolkit
+Project-URL: PyPI, https://pypi.org/project/langgraph-agent-toolkit
+Author-email: Roman Kryvokhyzha <kriwohizha@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: agents,blueprint,fastapi,langgraph,litellm,streamlit
+Classifier: Development Status :: 4 - Beta
+Classifier: Framework :: FastAPI
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: <3.14,>=3.11
+Requires-Dist: duckduckgo-search>=7.3.0
+Requires-Dist: fastapi~=0.115.5
+Requires-Dist: grpcio>=1.68.0
+Requires-Dist: httpx~=0.28.1
+Requires-Dist: jinja2~=3.1.6
+Requires-Dist: jiter~=0.9.0
+Requires-Dist: joblib~=1.4.2
+Requires-Dist: langchain-community~=0.3.21
+Requires-Dist: langchain-core~=0.3.52
+Requires-Dist: langfuse~=2.60.3
+Requires-Dist: langgraph-checkpoint-postgres~=2.0.19
+Requires-Dist: langgraph-checkpoint-sqlite~=2.0.6
+Requires-Dist: langgraph-cli[inmem]~=0.2.3
+Requires-Dist: langgraph-supervisor~=0.0.16
+Requires-Dist: langgraph~=0.3.30
+Requires-Dist: langsmith~=0.3.31
+Requires-Dist: loguru~=0.7.3
+Requires-Dist: multidict>6.3.2
+Requires-Dist: numpy~=1.26.4; python_version <= '3.12'
+Requires-Dist: numpy~=2.2.3; python_version >= '3.13'
+Requires-Dist: pandas~=2.2.3
+Requires-Dist: psycopg[binary,pool]~=3.2.4
+Requires-Dist: pyarrow>=19.0.1
+Requires-Dist: pydantic-settings~=2.9.1
+Requires-Dist: pydantic~=2.11.1
+Requires-Dist: pyowm~=3.3.0
+Requires-Dist: python-dotenv~=1.1.0
+Requires-Dist: rootutils>=1.0.7
+Requires-Dist: setuptools>=75.6.0
+Requires-Dist: streamlit~=1.44.1
+Requires-Dist: uvicorn~=0.34.0
+Requires-Dist: watchdog~=6.0.0
+Provides-Extra: all-backends
+Requires-Dist: azure-functions~=1.23.0; extra == 'all-backends'
+Requires-Dist: gunicorn~=23.0.0; extra == 'all-backends'
+Requires-Dist: mangum~=0.19.0; extra == 'all-backends'
+Requires-Dist: uvicorn~=0.34.2; extra == 'all-backends'
+Provides-Extra: all-llms
+Requires-Dist: langchain-anthropic~=0.3.12; extra == 'all-llms'
+Requires-Dist: langchain-aws~=0.2.22; extra == 'all-llms'
+Requires-Dist: langchain-deepseek~=0.1.3; extra == 'all-llms'
+Requires-Dist: langchain-google-genai~=2.1.4; extra == 'all-llms'
+Requires-Dist: langchain-google-vertexai~=2.0.21; extra == 'all-llms'
+Requires-Dist: langchain-groq~=0.3.2; extra == 'all-llms'
+Requires-Dist: langchain-ollama~=0.3.2; extra == 'all-llms'
+Requires-Dist: langchain-openai~=0.3.12; extra == 'all-llms'
+Provides-Extra: anthropic
+Requires-Dist: langchain-anthropic~=0.3.12; extra == 'anthropic'
+Provides-Extra: aws
+Requires-Dist: langchain-aws~=0.2.22; extra == 'aws'
+Provides-Extra: aws-backend
+Requires-Dist: mangum~=0.19.0; extra == 'aws-backend'
+Provides-Extra: azure-backend
+Requires-Dist: azure-functions~=1.23.0; extra == 'azure-backend'
+Provides-Extra: deepseek
+Requires-Dist: langchain-deepseek~=0.1.3; extra == 'deepseek'
+Provides-Extra: google-genai
+Requires-Dist: langchain-google-genai~=2.1.4; extra == 'google-genai'
+Provides-Extra: google-vertexai
+Requires-Dist: langchain-google-vertexai~=2.0.21; extra == 'google-vertexai'
+Provides-Extra: groq
+Requires-Dist: langchain-groq~=0.3.2; extra == 'groq'
+Provides-Extra: gunicorn-backend
+Requires-Dist: gunicorn~=23.0.0; extra == 'gunicorn-backend'
+Requires-Dist: uvicorn[standard]~=0.34.2; extra == 'gunicorn-backend'
+Provides-Extra: ollama
+Requires-Dist: langchain-ollama~=0.3.2; extra == 'ollama'
+Provides-Extra: openai
+Requires-Dist: langchain-openai~=0.3.12; extra == 'openai'
+Provides-Extra: uvicorn-backend
+Requires-Dist: uvicorn~=0.34.2; extra == 'uvicorn-backend'
+Description-Content-Type: text/markdown
+
 # 🧰 Langgraph Agent Toolkit
 
 [![build status](https://github.com/kryvokhyzha/langgraph-agent-toolkit/actions/workflows/test.yml/badge.svg)](https://github.com/kryvokhyzha/langgraph-agent-toolkit/actions/workflows/test.yml)
@@ -28,6 +123,27 @@ Features include:
   support
 - Complete template for building and deploying your own LangGraph-based agents
 
+## 📑 Contents
+
+- [Introduction](#-introduction)
+- [Quickstart](#-quickstart)
+- [Installation Options](#-installation-options)
+- [Architecture](#architecture)
+- [Key Features](#-key-features)
+- [Environment Setup](#environment-setup)
+  - [Creating Your `.env` File](#-creating-your-env-file)
+  - [LiteLLM Configuration](#-litellm-configuration)
+- [Project Structure](#-project-structure)
+- [Setup and Usage](#setup-and-usage)
+  - [Building Your Own Agent](#-building-your-own-agent)
+  - [Docker Setup](#-docker-setup)
+  - [Using the AgentClient](#-using-the-agentclient)
+  - [Development with LangGraph Studio](#-development-with-langgraph-studio)
+  - [Local Development Without Docker](#-local-development-without-docker)
+- [Useful Resources](#-useful-resources)
+- [Development and Contributing](#-development-and-contributing)
+- [License](#-license)
+
 ## 🚀 Quickstart
 
 1. Create a `.env` file based on [`.env.example`](./.env.example)
@@ -54,15 +170,41 @@ Features include:
    pip install langgraph-agent-toolkit
    ```
 
+   ℹ️ You can check available extras in
+   [Installation Options](#-installation-options) section or directly in
+   [pyproject.toml](pyproject.toml) file.
+
 4. **Option 3: Run with Docker**
 
    ```sh
    docker compose watch
    ```
 
+## 📦 Installation Options
+
+The toolkit supports multiple installation options using "extras" to include
+just the dependencies you need:
+
+### Available Extras
+
+```sh
+# LLM Provider Extras
+pip install "langgraph-agent-toolkit[openai,uvicorn-backend]"        # OpenAI and Uvicorn backend
+pip install "langgraph-agent-toolkit[anthropic,aws-backend]"         # Anthropic and AWS Lambda backend
+
+# Also available: google-vertexai, aws, ollama, groq, deepseek
+pip install "langgraph-agent-toolkit[all-llms,ll-backends]"          # All LLM providers and all backends
+
+# Client-Only Installation
+pip install "langgraph-agent-toolkit[client]"                        # Just the client and Streamlit app
+```
+
+<a name="architecture"></a>
+
 ## 🏗️ Architecture
 
-<img src="docs/media/agent_architecture.png" width="800">
+<!-- <img src="docs/media/agent_architecture.png" width="800"> -->
+<img src="https://github.com/kryvokhyzha/langgraph-agent-toolkit/blob/main/docs/media/agent_architecture.png?raw=true" width="800">
 
 ## ✨ Key Features
 
@@ -97,6 +239,8 @@ Features include:
    - Prompt management system
    - LiteLLM proxy integration
 
+<a name="environment-setup"></a>
+
 ## ⚙️ Environment Setup
 
 ### 📝 Creating Your `.env` File
@@ -112,12 +256,69 @@ Features include:
    **🔑 LLM API Configuration**
 
    ```env
-   # LiteLLM configuration
-   MODEL_NAME="gpt4o"                         # LiteLLM model name
-   MODEL_BASE_URL=http://litellm:4000/v1      # LiteLLM endpoint
-   MODEL_API_KEY=sk-any-string                # LiteLLM master key
+   # OpenAI Settings
+   OPENAI_API_KEY=sk-xxxxxxxxxxxxx
+   OPENAI_API_BASE_URL=http://litellm:4000/v1      # Can be OpenAI API or LiteLLM proxy
+   OPENAI_API_VERSION=2025-01-01
+   OPENAI_MODEL_NAME=gpt-4o-mini
+
+   # Azure OpenAI Settings (Optional)
+   AZURE_OPENAI_API_KEY=
+   AZURE_OPENAI_ENDPOINT=
+   AZURE_OPENAI_API_VERSION=
+   AZURE_OPENAI_MODEL_NAME=
+   AZURE_OPENAI_DEPLOYMENT_NAME=
+
+   # Anthropic Settings (Optional)
+   ANTHROPIC_API_KEY=
+   ANTHROPIC_MODEL_NAME=
+
+   # Other provider settings are also available:
+   # - Google VertexAI
+   # - Google GenAI
+   # - AWS Bedrock
+   # - DeepSeek
+   # - Ollama
+   ```
+
+   **🔀 Multi-Provider Model Configuration**
+
+   ```env
+   # Configure multiple models from different providers in a single environment variable
+   MODEL_CONFIGS={\
+     "gpt4o": {\
+       "provider": "azure_openai",\
+       "name": "gpt-4o",\
+       "api_key": "azure-key-123",\
+       "endpoint": "https://your-resource.openai.azure.com/",\
+       "api_version": "2023-05-15",\
+       "deployment": "gpt4o-deployment",\
+       "temperature": 0.7\
+     },\
+     "gpt4o-mini": {\
+       "provider": "azure_openai",\
+       "name": "gpt-4o-mini",\
+       "api_key": "azure-key-123",\
+       "endpoint": "https://your-resource.openai.azure.com/",\
+       "api_version": "2023-05-15",\
+       "deployment": "gpt4o-mini-deployment"\
+     },\
+     "gemini": {\
+       "provider": "google_genai",\
+       "name": "gemini-pro",\
+       "api_key": "google-key-123",\
+       "temperature": 0.7\
+     }\
+   }
    ```
 
+   This configuration allows you to:
+
+   - Define multiple models with different providers in one place
+   - Reference them by logical names in your application
+   - Set provider-specific parameters for each model
+   - Switch between models without changing code
+
    **🗄️ Database Configuration**
 
    ```env
@@ -193,13 +394,20 @@ Features include:
      redis_password: os.environ/REDIS_AUTH
    ```
 
-3. Setup LiteLLM environment:
+3. Setup service environment files:
+
+   Each service has its own environment file:
 
    ```sh
    cp configs/litellm/.litellm.env.example configs/litellm/.litellm.env
+   cp configs/redis/.redis.env.example configs/redis/.redis.env
+   cp configs/postgres/.postgres.env.example configs/postgres/.postgres.env
+   cp configs/minio/.minio.env.example configs/minio/.minio.env
+   cp configs/clickhouse/.clickhouse.env.example configs/clickhouse/.clickhouse.env
+   cp configs/langfuse/.langfuse.env.example configs/langfuse/.langfuse.env
    ```
 
-   Edit to include:
+   For example, edit LiteLLM environment:
 
    ```env
    LITELLM_MASTER_KEY=sk-your-master-key  # Create a strong key here
@@ -208,7 +416,8 @@ Features include:
    STORE_MODEL_IN_DB=True
    ```
 
-> **Note**: LiteLLM relies on Redis for request caching and rate limiting.
+> [!NOTE]  
+> LiteLLM relies on Redis for request caching and rate limiting.
 
 ## 📂 Project Structure
 
@@ -224,6 +433,8 @@ The repository contains:
 - `docker/`: Docker configurations
 - `tests/`: Test suite
 
+<a name="setup-and-usage"></a>
+
 ## 🛠️ Setup and Usage
 
 1. Clone the repository:
@@ -248,7 +459,7 @@ To customize the agent:
 
 ### 🐳 Docker Setup
 
-The `docker-compose.yaml` defines these services:
+The `docker-compose.yaml` defines these services with enhanced security:
 
 - `backend-agent-service`: FastAPI service
 - `frontend-streamlit-app`: Streamlit chat interface
@@ -276,7 +487,7 @@ enables live reloading:
    - 🔌 Agent API: `http://0.0.0.0:8080`
    - 📚 API docs: `http://0.0.0.0:8080/docs`
    - 📊 Langfuse dashboard: `http://0.0.0.0:3000`
-   - 🤖 LiteLLM API: `http://0.0.0.0:4000`
+   - 🤖 LiteLLM API: `http://0.0.0.0:4000` (accessible from any host)
 
 4. Stop services: