library · inferred from evidence
LangChain
A library mentioned as a source of unhashable types (e.g., Document lists).
- OpenAIEmbeddings fails against Azure OpenAI: Too many inputs for model
Shows how to fix openAIEmbeddings fails against Azure OpenAI: Too many inputs for model. Use it when you hit this exact problem. Skip it when your error message or symptom looks different.
- Diagnose: tool schema sent to the model includes config or runtime parameters
Shows how to fix diagnose: tool schema sent to the model includes config or runtime parameters. Use it when you hit this exact problem. Skip it when your error message or symptom looks different.
- ModelRateLimitError: handling provider rate limits without hammering the API
Rate limit errors are retryable, and LangChain retries 429s automatically up to 6 times by default. If you still get ModelRateLimitError, you need to slow down at the source with a rate limiter, reduce concurrency, or spread load across pro
- Connection resilience: what LangChain retries automatically and what it does not
Chat models retry failed requests with exponential backoff automatically: up to 6 times for network errors, 429 rate limits, and 5xx server errors. 401 and 404 are never retried. Tune with max_retries and timeout.
- Pinecone diagnosis: LangChain vector store fails on a missing index
Symptom: PineconeVectorStore construction succeeds but the first operation fails. LangChain never creates the index; create it first with matching dimension.
- Issue with configuring Hugging Face credentials for local n8n
N8n: issue with configuring Hugging Face credentials for local n8n. The verified fix is Fixed via PR #18047 after the langchain upgrade merged - member janober confirmed 'Fix got released with n8n@1.107.0'. Use this when you hit the symptom