langchain-ai/react-agent-tool-server
1
0
Fork 0
mirror of https://github.com/langchain-ai/react-agent-tool-server.git synced 2026-07-01 18:28:34 -04:00
Code Issues 2 Packages Projects Releases Wiki Activity

remove o1 models as they don't support system message (#5)

Browse Source
This commit is contained in:
Eugene Yurtsev
2025-03-12 18:11:25 -04:00
committed by GitHub
parent 103b91ec6c
commit 9f05c58316
2 changed files with 9 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+8 -4
View File
@@ -74,8 +74,12 @@ If you already have a tool server running, you can launch the ReAct agent with t
# Specify at least one chat model API key!
export ANTHROPIC_API_KEY="..."
export OPENAI_API_KEY="..."
# Specify the tool server URL and API key
TOOL_SERVER_API_KEY="Authorization header token" # This depends on how you have configured the tool server, and whether you have enabled authentication. if there's no authentication, just put a random string here.
TOOL_SERVER_URL=http://localhost:8000 TOOL_SERVER_API_KEY=$TOOL_SERVER_API_KEY uv run langgraph dev
```
# If you enabled auth on the tool server, set the API key.
# If you disabled auth, you set it to a non empty placeholder string.
export TOOL_SERVER_API_KEY="Authorization header token"
# Set the tool server URL
export TOOL_SERVER_URL="http://localhost:8000"
# Launch the ReAct agent
uv run langgraph dev
````
src/react_agent/configuration.py
+1 -1
View File
@@ -57,7 +57,7 @@ def identify_available_model_providers() -> list[str]:
PROVIDER_TO_MODELS = {
"openai": ["openai/o1", "openai/gpt-4o-mini", "openai/o1-mini", "openai/o3-mini"],
"openai": ["openai/gpt-4o-mini", "openai/o3-mini"],
"anthropic": [
"anthropic/claude-3-7-sonnet-latest",
"anthropic/claude-3-5-haiku-latest",