To explore production traces and metrics in Langfuse, you need to integrate your application with Langfuse.
- Capture traces of your application
- Add scores to these traces to measure/evaluate quality of outputs
There are currently four main ways to integrate with Langfuse:
|Langchain||JS/TS, Python||Automated instrumentation by passing callback handler to Langchain application.|
|SDK||JS/TS, Python||Manual instrumentation using the SDKs for full flexibility.|
|OpenAI||Python||Automated instrumentation using drop-in replacement of OpenAI SDK.|
|API||Directly call the public API. OpenAPI spec available.|
In addition, Langfuse is natively integrated with the following projects/packages:
|Flowise||JS/TS no-code builder for customized LLM flows.|
|Langflow||Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.|
|LiteLLM||Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs).|
Unsure which integration to choose? Ask us on Discord or in the chat.