GitHub - Scale3-Labs/langtrace: Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊
Apr 25, 2024 - github.com
Langtrace is an open-source observability software that allows users to capture, debug, and analyze traces and metrics from applications that use LLM APIs, Vector Databases, and LLM-based Frameworks. The software adheres to Open Telemetry Standards (OTEL) and is currently developing semantic conventions for the traces generated by the project. Users can either use the managed SaaS version of Langtrace or host it locally. The software supports integrations with various vendors including OpenAI, Anthropic, Azure OpenAI, Langchain, LlamaIndex, Pinecone, and ChromaDB.
Langtrace encourages contributions from developers and provides a Slack workspace for collaboration. The software uses NextJS for the frontend and APIs, PostgresDB as a metadata store, and Clickhouse DB for storing spans, metrics, logs, and traces. Langtrace is licensed under the AGPL 3.0 License, while its SDKs are licensed under the Apache 2.0 License. The company also provides a security email for reporting vulnerabilities and has a section for frequently asked questions.
Key takeaways:
Langtrace is an open-source observability software that captures, debugs, and analyzes traces and metrics from applications that use LLM APIs, Vector Databases, and LLM based Frameworks.
The software adheres to Open Telemetry Standards (OTEL) and is currently developing semantic conventions for the traces generated by the project.
Langtrace can be used as a managed SaaS version or can be self-hosted, requiring the running of three services: a Next.js app, a Postgres database, and a Clickhouse database.
Langtrace supports automatic capture of traces from various vendors including OpenAI, Anthropic, Azure OpenAI, Langchain, LlamaIndex, Pinecone, and ChromaDB.
