Chak AI 轻量级LLM网关

Install all optional dependencies

pip install chakpy[all] ```

Installation

```bash

Basic installation (SDK only)

pip install chakpy

Build an Agent in 3 Lines

Drop in tools, describe your task — chak drives the multi-step loop automatically.

```python import chak from chak.tools.std import Python, FileSystem

conv = chak.Conversation( "anthropic/claude-sonnet-4-6", api_key="...", tools=[Python(), FileSystem()], )

await conv.asend( "Analyse sales.csv: top 10 products by revenue. Write a Markdown report to report.md" )

🌖 Quick Start

Usage - exactly like regular tools

tools = [MegaSkill()] conv = Conversation("bailian/qwen-plus", tools=tools)

Basic Usage

Simple Data Extraction

```python from pydantic import BaseModel, Field from chak import Conversation

class User(BaseModel): """User information""" name: str = Field(description="User's full name") email: str = Field(description="User's email address") age: int = Field(description="User's age")

conv = Conversation("openai/gpt-4o", api_key="YOUR_KEY")

Complete Example

See full working examples: - Basic Structured Output: examples/structured_output_simple.py - Multimodal Structured Output: examples/structured_output_multimodal.py

Basic Usage

Single Image

```python from chak import Conversation, Image

conv = Conversation("openai/gpt-4o", api_key="YOUR_KEY")

Complete Examples

See full working examples:

• Images: examples/multimodal_chat_image.py
• Single image analysis
• Multiple image comparison
• Streaming with images
• Audio input (when supported)
• Advanced multimodal messages

• Documents: examples/multimodal_chat_documents.py
• PDF document analysis
• Word document processing
• Plain text and markdown files
• CSV data analysis
• Excel spreadsheet processing
• Web link content analysis
• Streaming with documents

Basic Usage

```python from chak import Conversation

conv = Conversation("openai/gpt-4o-mini", api_key="YOUR_KEY")

Use Cases

The custom field is completely flexible - use it however your application needs:

• Frontend rendering: Pass UI instructions (forms, charts, widgets)
• Tracking: Store session IDs, user IDs, request metadata
• Routing: Add routing hints or processing flags
• Analytics: Attach tracking data for logging
• Anything else: It's your data, structure it your way

Example: examples/custom_payload_demo.py - Demo showing custom data used for dynamic form rendering

---

Logging Configuration

Control log output at runtime:

import chak

chak.set_log_level("DISABLE") # Disable all logs (production)
chak.set_log_level("ERROR")   # Only errors
chak.set_log_level("WARNING") # Warnings + errors
chak.set_log_level("INFO")    # Default, shows tool execution
chak.set_log_level("DEBUG")   # Detailed logs with file:line

Or use environment variables (set before importing):

export CHAK_LOG_LEVEL=ERROR
export CHAK_LOG_TO_FILE=true      # Optional: enable file logging
export CHAK_LOG_FILE=logs/chak.log

Local Server Mode (Optional)

⚠️ chak is primarily an SDK. The built-in local server is intended for local development and prototyping only, and is not recommended or hardened for production use.

Start a local gateway service with 2 lines of code:

1. Create Configuration File

```yaml

chak-config.yaml

api_keys: # Simple format - use default base_url openai: ${OPENAI_API_KEY} # Read from environment variable (recommended) bailian: "sk-your-api-key-here" # Plain text (for development/testing) # Custom base_url (requires quotes) "ollama@http://localhost:11434": "ollama" "vllm@http://192.168.1.100:8000": "dummy-key"

server: host: "0.0.0.0" port: 8000 ```

🌱 Minimalist API Design

No complex configurations, no learning curve. chak is designed to be intuitive:

```python

Use as SDK - connect to any LLM with a simple URI

conv = chak.Conversation( "openai/gpt-4o-mini", api_key="YOUR_KEY", event=True, # Enable event streaming for real-time tool call observability reasoning=True # Enable reasoning mode for compatible models ) response = conv.send("Hello!")

Default: best for IO-bound tasks (API calls, DB queries)

conv = chak.Conversation( "openai/gpt-4o", tools=[...], tool_executor=chak.ToolExecutor.ASYNCIO # default )

Compare multiple images

response = await conv.asend( "What are the differences between these images?", attachments=[ Image("https://example.com/image1.jpg"), Image("./local/image2.png", MimeType.PNG), Image("data:image/webp;base64,...", MimeType.WEBP) ] )

#### Audio Files

response = await conv.asend( "What is being said in this audio?", attachments=[Audio("https://example.com/speech.wav", MimeType.WAV)] )

#### Documents

Send image with question

response = await conv.asend( "What's in this image?", attachments=[Image("photo.jpg")] # local path, URL, or base64 )