Skip to main content
POST
/
api
/
v1
/
chat
/
completions
"<any>"
OpenAI-compatible chat completions endpoint with intelligent context injection, unlimited context through memory management, streaming support, and tool calling capabilities.

​
Key Features

  • Unlimited Context: Intelligent memory management breaks through token limits
  • Auto Context Injection: Retrieves relevant memories and knowledge automatically
  • Streaming Support: Real-time responses with SSE
  • Tool Calling: Function execution and tool integration
  • Cost Optimization: Context optimization reduces API costs
  • Diagnostic Headers: Monitoring and debugging information

​
Context Headers

  • x-user-id: User identifier for memory retrieval
  • x-conversation-id: Conversation identifier for context continuity
  • x-session-id: Session identifier for session-based context
  • x-workspace-id: Workspace identifier for multi-tenant support
  • x-collection-ids: JSON array of collection IDs for knowledge retrieval

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

​
X-Workspace-Id
string | null

The workspace ID

Response

Successful Response

The response is of type any.