> ## Documentation Index > Fetch the complete documentation index at: https://docs.co-mind.ai/llms.txt > Use this file to discover all available pages before exploring further. # Chat with knowledge bases > OpenAI-compatible chat endpoint with knowledge base RAG support (stateless) ## OpenAPI ````yaml /openapi.yaml post /v1/knowledgebase/chat/completions openapi: 3.1.0 info: title: Co-mind.ai Private AI Platform API version: 1.2.4 description: > Co-mind.ai Private AI Platform API. ## Features - OpenAI-compatible endpoints - Tool/function calling support - Streaming responses - Multiple backend support - Personal Access Tokens (PAT) for programmatic access ## Authentication The API supports two authentication methods: **1. JWT Authentication** — Login with email/password to get short-lived access tokens. Use for interactive sessions (web apps, Postman). **2. Personal Access Tokens (PAT)** — Long-lived tokens for programmatic/API access. Create via `POST /v1/api-tokens` after authenticating with JWT. PAT format: `cmnd_.` Both methods use the `Authorization: Bearer ` header. contact: email: support@co-mind.ai servers: - url: http://co-mind-platform-host description: Co-mind.ai AI Platform security: - BearerAuth: [] tags: - name: Public description: Public endpoints (no authentication required) - name: Authentication description: JWT login, refresh, logout, and user info - name: API Tokens description: Personal Access Token (PAT) management - name: Chat description: OpenAI-compatible chat completions - name: Knowledge Base description: Knowledge base management and RAG-enhanced chat - name: Completions description: Text completion endpoints - name: Embeddings description: Text embedding generation - name: Discovery description: Model and backend discovery endpoints - name: Echo Engine description: Audio transcription (STT), health, and metrics - name: Echo Engine - Recordings description: Recording CRUD and job linking - name: Echo Engine - TTS description: Text-to-speech synthesis - name: Sanitizer Admin description: Security policy management, health, and testing - name: Document Analyzer description: Document analysis, extraction, and review workflows - name: Researcher description: Web search, research sessions, analysis, and synthesis - name: Directory Admin description: LDAP/AD identity provider configuration and sync - name: Entra Admin description: Microsoft Entra ID (Azure AD) configuration - name: Tenant Admin description: Tenant/organization management - name: Tenant API Keys description: Provider API key management per tenant - name: Sub-org Management description: Sub-organization management - name: Service Endpoints description: SSO config discovery, OAuth token exchange - name: Audit Logs description: Audit log querying and aggregation - name: Quota description: Usage quota tracking paths: /v1/knowledgebase/chat/completions: post: tags: - Knowledge Base summary: Chat with knowledge bases description: >- OpenAI-compatible chat endpoint with knowledge base RAG support (stateless) operationId: knowledgeBaseChatCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/KnowledgeBaseChatCompletionRequest' responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/KnowledgeBaseChatCompletionResponse' '400': $ref: '#/components/responses/BadRequest' '429': $ref: '#/components/responses/RateLimitExceeded' components: schemas: KnowledgeBaseChatCompletionRequest: type: object required: - model - messages - knowledgebase_ids properties: model: type: string example: gpt-4o-mini messages: type: array items: $ref: '#/components/schemas/ChatMessage' knowledgebase_ids: type: array items: type: string description: Knowledge base IDs to use for context example: - kb_abc123 - kb_def456 temperature: type: number minimum: 0 maximum: 2 default: 1 max_tokens: type: integer minimum: 1 top_p: type: number minimum: 0 maximum: 1 default: 1 stream: type: boolean default: false KnowledgeBaseChatCompletionResponse: type: object properties: id: type: string example: chatcmpl-abc123 object: type: string example: chat.completion created: type: integer model: type: string choices: type: array items: type: object properties: index: type: integer message: $ref: '#/components/schemas/ChatMessage' finish_reason: type: string enum: - stop - length - tool_calls - content_filter usage: $ref: '#/components/schemas/Usage' knowledge_base_context: type: object properties: sources: type: array items: type: object properties: knowledgebase_id: type: string document_id: type: string title: type: string content: type: string page: type: integer relevance_score: type: number ChatMessage: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool content: type: string name: type: string Usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer Error: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string responses: BadRequest: description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Invalid request parameters type: invalid_request_error code: bad_request RateLimitExceeded: description: Rate limit exceeded headers: Retry-After: schema: type: integer description: Seconds to wait before retrying x-ratelimit-limit-requests: schema: type: integer x-ratelimit-remaining-requests: schema: type: integer x-ratelimit-reset-requests: schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Rate limit exceeded type: rate_limit_exceeded code: rate_limit_exceeded securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT or PAT description: > Bearer token authentication. Supports two token types: - **JWT Access Token** — obtained via `POST /v1/auth/login` - **Personal Access Token (PAT)** — created via `POST /v1/api-tokens`, format: `cmnd_.` ````