Integration

LangChain and other frameworks

Whatever framework your application is built with, it connects to BaseLLM through the OpenAI-compatible chat endpoint.

Connect through the OpenAI-compatible endpoint

Instead of calling the model provider directly, your application sends requests to BaseLLM's OpenAI-compatible chat endpoint. Authentication uses a project API key; the key identifies the project, not the person.

POST <basellm-endpoint>/api/v1/chat/completions
# Project API key: in the form sk-ffm-…
X-FFM-User: <end-user-id>
X-FFM-Session: <session-id>

Coming soon

Framework-specific integrations are coming soon. BaseLLM doesn't replace your existing frameworks; it connects to them as a gateway and governance layer.

FrameworkUpcoming integration
LangChainCallback / tracing integration
LangGraphCheckpoint and state integration
CrewAITool registry integration
AutoGenTool execution proxy
Semantic KernelPlugin gateway
HaystackPipeline wrapper