Documentation

Developer documentation

Store text, search it by meaning, and hold conversations grounded in it. Every endpoint authenticates with a bearer token and a team token, and returns JSON.

Get started Set up authentication

Your first request

curl https://api.vectorforgeai.com/v1/collections \
  -H "Authorization: Bearer $API_KEY" \
  -H "Team-Token: $TEAM_TOKEN"

Start here

Getting Started Base URL, request format, and your first call end to end.
Authentication API keys, team tokens, and which header carries which.

Your data

Document Collections Create and manage the containers your documents live in.
Documents Add text, attach metadata, and update a document in place.
Vector Search Query by meaning and read the similarity scores that come back.

Generation

LLM Completions Generate text with your own context, on base or Pro models.
Conversation API Stateful chat with memory, retrieval, and tool calling.
Conversation Feedback Record thumbs up and down against individual answers.

Integrations

MCP Integration Expose your collections to Claude, ChatGPT, and other MCP clients.

Use it from Claude

Add your collections as an MCP server and search them from your assistant.

OpenAPI schema

Generate a client, or load the spec into Postman and Insomnia.

Ask a question

Something missing or wrong in these pages? Tell us and we will fix it.