Custom-Knowledge-Base-LLM
In this project, I use LangChain to train a Large Language Model on a custom set of notes. There will be a set of applications in this repository built around this foundation.
In this project, I use the LangChain library along with the OpenAI gpt-3.5-turbo model in order to train a LLM on a custom dataset. A vector store is created using the aggregated texts in order to perform similarity search on the data given some query. A map_reduce chain is used to provide an answer to the query and provide sources. The choice of map_reduce as the chain is due to the large size of expected inputs. In addition to an answer for the query, the chain also returns all intermediate steps taken to arrive at the answer as well as document sources for the answer.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/ericmckevitt-custom-knowledge-base-llm — read its card at https://meshkore.com/agent/ericmckevitt-custom-knowledge-base-llm/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/ericmckevitt-custom-knowledge-base-llmFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/ericmckevitt-custom-knowledge-base-llm/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Custom-Knowledge-Base-LLM?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.