OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Rag API

Rag API is a Python FastAPI service that uses LangChain to index documents and retrieve their embeddings from a vector database, organizing files by file ID for targeted retrieval.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag API — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an application needs a backend API for document indexing and file-ID-based embedding retrieval, especially when file metadata is available to narrow queries.

Who it is for

  • Developers integrating file-scoped document retrieval into an application.
  • LibreChat integrators working with document embeddings and file metadata.
  • Teams operating a Python API alongside PostgreSQL/pgvector or a documented alternative vector store.

Documented uses

  • Add documents to an embedding-backed store.
  • Retrieve document content using file-level identifiers for targeted queries.
  • Retrieve or delete stored documents through API methods.
  • Connect a RAG application to a vector store through an asynchronous service.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed.

  • PostgreSQL/pgvector is the default vector database; the README also documents Atlas MongoDB configuration.
  • The local setup requires database configuration and an embedding-provider key when using the default OpenAI embedding settings.
  • The project documents asynchronous ingestion and configurable batching, queue size and per-file parallel execution.
  • For entity-owned content, callers need to account for entity IDs in deletion and for upstream authorization of entity access.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Rag API locally

Prepare the documented local API installation and start the service.

Before you start

  • Python and a virtual environment are recommended.
  • A PostgreSQL database configured for pgvector, either an existing setup or one started separately.
  • A configured .env file, including DB_HOST and, when using the default embedding settings, RAG_OPENAI_API_KEY.

Steps

  1. Configure the .env file using the README's environment-variable guidance.

  2. Set up PostgreSQL/pgvector, using an existing database or the documented database-only Docker Compose option.

  3. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Start the service with uvicorn main:app.

Expected outcome

The documented local setup starts the FastAPI service against a configured PostgreSQL/pgvector database.

Guide limitations

  • The README requires an OpenAI API key for embeddings when using default settings.
  • This guide covers setup and startup, not a document-ingestion or retrieval request.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Rag APIAdd documents to an embedding-backed store.ServerThe repository is public and identifies the project as MIT-licensed.
MettisIndex text documents through an HTTP endpoint.Linux, Self-hosted, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
LibreChat-AI/rag-api · Official homepage title · retained in its source language
How we review sourcesSuggest a correction