Langfuse Integrations Overview
Integrate your application with Langfuse to explore production traces and metrics.
Objective:
- Capture traces of your application
- Add scores to these traces to measure/evaluate quality of outputs
Main Integrations
| Integration | Supports | Description |
|---|---|---|
| SDK | Python, JS/TS | Manual instrumentation using the SDKs for full flexibility. |
| OpenAI | Python, JS/TS | Automated instrumentation using drop-in replacement of OpenAI SDK. |
| Langchain | Python, JS/TS | Automated instrumentation by passing callback handler to Langchain application or using OpenTelemetry. |
| LlamaIndex | Python, JS/TS | Automated instrumentation via LlamaIndex callback system. |
| Haystack | Python | Automated instrumentation via Haystack content tracing system. |
| LiteLLM | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |
| Vercel AI SDK | JS/TS | TypeScript toolkit designed to help developers build AI-powered applications with React, Next.js, Vue, Svelte, Node.js. |
| API | Directly call the public API. OpenAPI spec available. |
Packages integrated with Langfuse
| Name | Type | Description |
|---|---|---|
| Instructor | Library | Library to get structured LLM outputs (JSON, Pydantic) |
| DSPy | Library | Framework that systematically optimizes language model prompts and weights |
| Mirascope | Library | Python toolkit for building LLM applications. |
| Pydantic AI | Library | Pydantic integration for LLM applications. |
| Ollama | Model (local) | Easily run open source LLMs on your own machine. |
| OpenAI Agents SDK | Library | Agents framework by OpenAI SDK. |
| Amazon Bedrock | Model | Run foundation and fine-tuned models on AWS. |
| Google Vertex AI and Gemini | Model | Grants access to Google’s own series of Gemini models as well as various models via the Vertex Model Garden (e.g. Claude3) |
| AutoGen | Agent Framework | Open source LLM platform for building distributed agents. |
| Flowise | Chat/Agent UI | JS/TS no-code builder for customized LLM flows. |
| Langflow | Chat/Agent UI | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
| Dify | Chat/Agent UI | Open source LLM app development platform with no-code builder. |
| OpenWebUI | Chat/Agent UI | Self-hosted LLM Chat web ui supporting various LLM runners including self-hosted and local models. |
| Promptfoo | Tool | Open source LLM testing platform. |
| LobeChat | Chat/Agent UI | Open source chatbot platform. |
| Vapi | Platform | Open source voice AI platform. |
| Inferable | Agents | Open source LLM platform for building distributed agents. |
| Gradio | Chat/Agent UI | Open source Python library to build web interfaces like Chat UI. |
| Goose | Agents | Open source LLM platform for building distributed agents. |
| smolagents | Agents | Open source AI agents framework. |
| CrewAI | Agents | Multi agent framework for agent collaboration and tool use. |
| Spring AI | Library | Spring-based framework for AI development with built-in OTel tracing for AI calls. |
| Quarkus LangChain4j | Library | A Quarkus based integration of LangChain4j for AI development with built-in OTel tracing for AI calls |
| Firecrawl | Web Scraping | Web scraper that allows you to turn entire websites into LLM-ready markdown. |
| OpenRouter | Framework | OpenAI-compatible completion API to +280 language models |
| xAI / Grok | Model | xAI’s Grok models |
| Cohere | Model | Cohere’s models |
| Fireworks AI | Model | Fireworks AI’s models |
| Novita AI | Model | Deployment for open source and specialized models |
| Cleanlab | Model / Framework | Automated Evaluations |
Unsure which integration to choose? Ask us on Discord or in the chat.
⭐️
Stay updated: Star Langfuse on GitHub to get instant notifications about new releases.
Request a new integration
We use GitHub Discussions to track interest in new integrations. Please upvote/add to the list below if you’d like to see a new integration.
End to end examples
If you want to see how things work together, you can look at the end-to-end examples below. They are Jupyter notebooks that you can easily run in Google Colab or locally.
Generally, we recommend reading the get started guides for each integration first.
Integrations
Example Bedrock AgentsExample Decorator Openai LangchainExample - Tracing and Evaluation for the OpenAI-Agents SDKExample - Trace and Evaluate LangGraph AgentsObservability and Metrics for Amazon BedrockIntegration Azure Openai LangchainIntegration Deepseek Openai SdkIntegration DspyObservability and Metrics for Google Vertex AI and GeminiOpen Source LLM Observability for GradioIntegration Groq SdkIntegration HaystackIntegration Huggingface Openai SdkObservability & Tracing for InstructorIntegration LangchainOpen Source Observability for LangGraphLangserve IntegrationIntegration Litellm ProxyIntegration Llama-indexIntegration Llama-index InstrumentationIntegration Llama-index Milvus-liteMonitoring LlamaIndex applications with PostHog and LangfuseIntegration MirascopeIntegration Mistral SdkOllama Observability and Tracing for local LLMs using LangfuseTrace the OpenAI Agents SDK with LangfuseOSS Observability for OpenAI Assistants APIIntegration Openai SdkObserve OpenAI Structured Outputs with LangfuseTrace Pydantic AI agents with OpenTelemetryObservability for Semantic Kernel with LangfuseJs Integration LangchainJs Integration Litellm ProxyJs Integration OpenaiLangfuse JS/TS SDKMLflow Integration via OpenTelemetryOpenLIT Integration via OpenTelemetryOtel Integration Openllmetry