openapi: 3.2.0
info:
  title: LiteLLM Rag API
  description: 'Proxy Server to call 100+ LLMs in the OpenAI format. **Customize Swagger Docs**


    👉 ```LiteLLM Admin Panel on /ui```. Create, Edit Keys with SSO. Having issues? Try ```Fallback Login```


    💸 ```LiteLLM Model Cost Map```.


    🔎 ```LiteLLM Model Hub```. See available models on the proxy. **Docs**'
  version: 1.102.1
tags:
- name: Rag
paths:
  /rag/ingest:
    post:
      tags:
      - Rag
      summary: Rag Ingest
      description: 'RAG Ingest endpoint - all-in-one document ingestion pipeline.


        Supports form upload (for files) or JSON body (for URLs).


        ## Form upload (for files):

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/ingest" \

        -H "Authorization: Bearer sk-1234" \

        -F file="@document.pdf" \

        -F ''ingest_options={"vector_store": {"custom_llm_provider": "openai"}}''

        ```


        ## JSON body (for URLs):

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/ingest" \

        -H "Authorization: Bearer sk-1234" \

        -H "Content-Type: application/json" \

        -d ''{

        "file_url": "https://example.com/document.pdf",

        "ingest_options": {"vector_store": {"custom_llm_provider": "openai"}}

        }''

        ```


        ## Bedrock:

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/ingest" \

        -H "Authorization: Bearer sk-1234" \

        -F file="@document.pdf" \

        -F ''ingest_options={"vector_store": {"custom_llm_provider": "bedrock"}}''

        ```'
      operationId: rag_ingest_rag_ingest_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /v1/rag/ingest:
    post:
      tags:
      - Rag
      summary: Rag Ingest
      description: 'RAG Ingest endpoint - all-in-one document ingestion pipeline.


        Supports form upload (for files) or JSON body (for URLs).


        ## Form upload (for files):

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/ingest" \

        -H "Authorization: Bearer sk-1234" \

        -F file="@document.pdf" \

        -F ''ingest_options={"vector_store": {"custom_llm_provider": "openai"}}''

        ```


        ## JSON body (for URLs):

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/ingest" \

        -H "Authorization: Bearer sk-1234" \

        -H "Content-Type: application/json" \

        -d ''{

        "file_url": "https://example.com/document.pdf",

        "ingest_options": {"vector_store": {"custom_llm_provider": "openai"}}

        }''

        ```


        ## Bedrock:

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/ingest" \

        -H "Authorization: Bearer sk-1234" \

        -F file="@document.pdf" \

        -F ''ingest_options={"vector_store": {"custom_llm_provider": "bedrock"}}''

        ```'
      operationId: rag_ingest_v1_rag_ingest_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /rag/query:
    post:
      tags:
      - Rag
      summary: Rag Query
      description: 'RAG Query endpoint - search vector store, optionally rerank, and generate LLM response.


        This endpoint:

        1. Extracts the query from the last user message

        2. Searches the vector store for relevant context

        3. Optionally reranks the results

        4. Generates an LLM response with the retrieved context


        ## Example Request:

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/query" \

        -H "Authorization: Bearer sk-1234" \

        -H "Content-Type: application/json" \

        -d ''{

        "model": "gpt-4o-mini",

        "messages": [{"role": "user", "content": "What is LiteLLM?"}],

        "retrieval_config": {

        "vector_store_id": "vs_abc123",

        "custom_llm_provider": "openai",

        "top_k": 5

        }

        }''

        ```


        ## With Reranking:

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/query" \

        -H "Authorization: Bearer sk-1234" \

        -H "Content-Type: application/json" \

        -d ''{

        "model": "gpt-4o-mini",

        "messages": [{"role": "user", "content": "What is LiteLLM?"}],

        "retrieval_config": {

        "vector_store_id": "vs_abc123",

        "custom_llm_provider": "openai",

        "top_k": 10

        },

        "rerank": {

        "enabled": true,

        "model": "cohere/rerank-english-v3.0",

        "top_n": 3

        }

        }''

        ```'
      operationId: rag_query_rag_query_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
  /v1/rag/query:
    post:
      tags:
      - Rag
      summary: Rag Query
      description: 'RAG Query endpoint - search vector store, optionally rerank, and generate LLM response.


        This endpoint:

        1. Extracts the query from the last user message

        2. Searches the vector store for relevant context

        3. Optionally reranks the results

        4. Generates an LLM response with the retrieved context


        ## Example Request:

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/query" \

        -H "Authorization: Bearer sk-1234" \

        -H "Content-Type: application/json" \

        -d ''{

        "model": "gpt-4o-mini",

        "messages": [{"role": "user", "content": "What is LiteLLM?"}],

        "retrieval_config": {

        "vector_store_id": "vs_abc123",

        "custom_llm_provider": "openai",

        "top_k": 5

        }

        }''

        ```


        ## With Reranking:

        ```bash

        curl -X POST "http://localhost:4000/v1/rag/query" \

        -H "Authorization: Bearer sk-1234" \

        -H "Content-Type: application/json" \

        -d ''{

        "model": "gpt-4o-mini",

        "messages": [{"role": "user", "content": "What is LiteLLM?"}],

        "retrieval_config": {

        "vector_store_id": "vs_abc123",

        "custom_llm_provider": "openai",

        "top_k": 10

        },

        "rerank": {

        "enabled": true,

        "model": "cohere/rerank-english-v3.0",

        "top_n": 3

        }

        }''

        ```'
      operationId: rag_query_v1_rag_query_post
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      security:
      - APIKeyHeader: []
components:
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      description: Bearer token
      in: header
      name: x-litellm-api-key