LangChain: Embeddings & Vector Stores (Not Supported)

LangChain: Embeddings & Vector Stores (Not Supported)

The following LangChain nodes are not supported on indie.money:

• Embeddings OpenAI (embeddingsOpenAi) - Vector Store Pinecone (vectorStorePinecone) - Vector Store Qdrant (vectorStoreQdrant) - Vector Store Supabase (vectorStoreSupabase) - Vector Store In-Memory (vectorStoreInMemory) - Vector Store Redis (vectorStoreRedis) - Vector Store Weaviate (vectorStoreWeaviate) - Vector Store Chroma (vectorStoreChroma) - Vector Store Milvus (vectorStoreMilvus) - Vector Store Zep (vectorStoreZep) - Document Loaders (PDF, CSV, HTML, etc.) - Text Splitters - Retrieval QA Chain

Why Not Supported

These nodes require:

• Node.js-specific npm packages (e.g., native database drivers) that use APIs unavailable in Workers
• Persistent file system access for document loading
• Note: Embeddings themselves are fetched from external APIs — the limitation is in the n8n node implementations, not in calling embedding APIs. You can call OpenAI's embedding API directly via the HTTP Request node.

Workarounds

• Use OpenRouter Chat Model with the Agent Node for most RAG-like use cases (pass context directly in the prompt) - Pre-process documents externally and pass the text to your agent via HTTP webhook - For vector search: use Pinecone or Qdrant REST APIs via the HTTP Request node

Related

• Memory Buffer Window - Known Limitations - LangChain: External Memory (Not Supported)