langchain-docs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RRF_K | No | RRF smoothing constant. | 60 |
| MCP_HOST | No | Host to bind for HTTP transports. | 127.0.0.1 |
| MCP_PORT | No | Port to bind for HTTP transports. | 8000 |
| RECALL_K | No | Number of results recalled per retrieval path. | 8 |
| LLM_MODEL | No | LLM model for query rewriting. | deepseek-ai/DeepSeek-V4-Flash |
| MILVUS_DB | No | Milvus database name. | langchain_docs_db |
| MIN_SCORE | No | Minimum reranking score threshold. | 0.3 |
| CHUNK_SIZE | No | Chunk size for document splitting. | 800 |
| MILVUS_URI | No | Milvus server URI. | http://localhost:19530 |
| EMBED_MODEL | No | Embedding model name. | Qwen/Qwen3-Embedding-4B |
| RERANK_MODEL | No | Reranking model name. | BAAI/bge-reranker-v2-m3 |
| UPSERT_BATCH | No | Milvus upsert batch size. | 200 |
| CHUNK_OVERLAP | No | Chunk overlap. | 100 |
| MCP_TRANSPORT | No | MCP transport: stdio, streamable-http, or sse. | stdio |
| LLMS_INDEX_URL | No | llms.txt index URL used by get_document. | https://docs.langchain.com/oss/python/langchain/llms.txt |
| OPENAI_API_KEY | No | Upstream API key for vectorization, query rewriting, and reranking. Required unless using BYOK mode where clients supply their own key via X-Api-Key or Authorization headers. | |
| QUERY_VARIANTS | No | Number of English query variants to generate for Chinese questions. | 3 |
| LLMS_INDEX_URLS | No | Comma-separated URLs of llms.txt indexes for ingestion. | https://docs.langchain.com/oss/python/langchain/llms.txt |
| OPENAI_BASE_URL | No | OpenAI-compatible API base URL. | https://api.siliconflow.cn/v1 |
| MILVUS_COLLECTION | No | Milvus collection name. | langchain_docs_llms_v1 |
| RERANK_CANDIDATES | No | Maximum number of candidates sent to reranking. | 12 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues