bolade
162 lines
3.7 KiB
Markdown
162 lines
3.7 KiB
Markdown
# LangChain v1.0 Migration Notes
|
|
|
|
## What Changed
|
|
|
|
The codebase has been updated to use **LangChain v1.0** API, which introduced breaking changes from v0.x.
|
|
|
|
## Key Changes Made
|
|
|
|
### 1. Agent Creation API
|
|
|
|
**Before (v0.x):**
|
|
|
|
```python
|
|
from langchain.agents import AgentExecutor, create_openai_tools_agent
|
|
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
|
|
from langchain_core.tools import Tool
|
|
|
|
# Create tools as Tool objects
|
|
tools = [
|
|
Tool(name="navigate", func=navigate_wrapper, description="..."),
|
|
# ... more tools
|
|
]
|
|
|
|
# Create prompt with MessagesPlaceholder
|
|
prompt = ChatPromptTemplate.from_messages([...])
|
|
|
|
# Create agent and executor
|
|
agent = create_openai_tools_agent(llm, tools, prompt)
|
|
agent_executor = AgentExecutor(agent=agent, tools=tools, ...)
|
|
|
|
# Execute
|
|
result = await agent_executor.ainvoke({"input": task})
|
|
```
|
|
|
|
**After (v1.0):**
|
|
|
|
```python
|
|
from langchain.agents import create_agent
|
|
|
|
# Create tools as simple functions with docstrings
|
|
def navigate(url: str) -> str:
|
|
"""Navigate to a URL. Input should be a valid URL."""
|
|
return asyncio.run(self.browser.navigate(url))
|
|
|
|
tools = [navigate, click, type_text, ...] # Just functions!
|
|
|
|
# Create agent directly
|
|
agent = create_agent(
|
|
model="gpt-4o-mini",
|
|
tools=tools,
|
|
system_prompt="Your instructions here"
|
|
)
|
|
|
|
# Execute with messages format
|
|
result = await agent.ainvoke(
|
|
{"messages": [{"role": "user", "content": task}]}
|
|
)
|
|
```
|
|
|
|
### 2. Tool Definition
|
|
|
|
**Before:**
|
|
|
|
- Tools were defined as `Tool` objects
|
|
- Required explicit `name`, `func`, and `description` parameters
|
|
|
|
**After:**
|
|
|
|
- Tools are simple Python functions
|
|
- Function docstring becomes the tool description
|
|
- Function name becomes the tool name
|
|
- Much simpler and cleaner!
|
|
|
|
### 3. Response Format
|
|
|
|
**Before:**
|
|
|
|
```python
|
|
result = await agent_executor.ainvoke({"input": task})
|
|
output = result.get("output")
|
|
```
|
|
|
|
**After:**
|
|
|
|
```python
|
|
result = await agent.ainvoke({"messages": [{"role": "user", "content": task}]})
|
|
output = result["messages"][-1].content
|
|
```
|
|
|
|
### 4. Pydantic Models
|
|
|
|
Also updated Pydantic models to use v2.0 syntax:
|
|
|
|
**Before:**
|
|
|
|
```python
|
|
class Settings(BaseSettings):
|
|
field: str
|
|
|
|
class Config:
|
|
env_file = ".env"
|
|
```
|
|
|
|
**After:**
|
|
|
|
```python
|
|
from pydantic import ConfigDict
|
|
|
|
class Settings(BaseSettings):
|
|
model_config = ConfigDict(env_file=".env")
|
|
|
|
field: str
|
|
```
|
|
|
|
## Benefits of v1.0
|
|
|
|
1. **Simpler API**: Less boilerplate code
|
|
2. **Better Tool Definition**: Functions with docstrings vs Tool objects
|
|
3. **Built on LangGraph**: Better durability and streaming support
|
|
4. **Cleaner Code**: More intuitive and Pythonic
|
|
5. **Better Performance**: Optimized execution
|
|
|
|
## Migration Checklist
|
|
|
|
- [x] Replace `create_openai_tools_agent` with `create_agent`
|
|
- [x] Remove `AgentExecutor` usage
|
|
- [x] Convert `Tool` objects to simple functions
|
|
- [x] Update invocation format to use messages
|
|
- [x] Update response parsing
|
|
- [x] Fix Pydantic v2.0 deprecations
|
|
- [x] Test all functionality
|
|
|
|
## Running the Application
|
|
|
|
The application now works with LangChain v1.0:
|
|
|
|
```bash
|
|
# Install dependencies
|
|
uv pip install -e .
|
|
playwright install chromium
|
|
|
|
# Set up environment
|
|
cp .env.example .env
|
|
# Edit .env and add OPENAI_API_KEY
|
|
|
|
# Run
|
|
python main.py
|
|
```
|
|
|
|
## Documentation
|
|
|
|
- [LangChain v1.0 Overview](https://docs.langchain.com/oss/python/langchain/overview)
|
|
- [Migration Guide](https://docs.langchain.com/oss/python/migrate/langchain-v1)
|
|
- [Release Notes](https://docs.langchain.com/oss/python/releases/langchain-v1)
|
|
|
|
## Issues Fixed
|
|
|
|
- ✅ `ImportError: cannot import name 'AgentExecutor'` - Fixed by using new API
|
|
- ✅ Pydantic deprecation warnings - Fixed by using ConfigDict
|
|
- ✅ All imports working correctly
|
|
- ✅ Application runs successfully
|