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

Rag Search

Rag Search is a Python FastAPI service that exposes a RAG search endpoint combining a configured search provider, OpenAI-compatible model and embedding settings, and a Zilliz vector database. Its request options include reranking, detailed-result selection and score-based filtering.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag Search — 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 self-hosted endpoint that combines configured web search and vector retrieval, with request-level controls over result refinement.

Who it is for

  • Developers building AI applications that need a retrieval API.
  • Teams running a self-hosted search backend over a configured Zilliz vector collection.

Documented uses

  • Retrieve relevant information for a query using configured web search and vector retrieval.
  • Refine results through reranking and minimum-score filtering.
  • Return a limited set of detailed results from a larger search result set.
Before you choose

Requirements & limits

The documented primary workflow is self-hosted: configure environment variables, install Python dependencies and run the FastAPI server. The example request uses bearer API-key authentication.

  • The documented vector database is Zilliz, and configuration requires its URI, token, collection and vector dimension.
  • Model and embedding settings include a configurable base URL and model names; a particular alternative provider is not demonstrated.
  • The example uses Google search, while other search-provider options are not documented.
  • The README shows request parameters but not a response schema or collection provisioning workflow.
  • The repository is public and lists the Apache-2.0 license.

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 the local FastAPI service and send a RAG search request

Configure the documented providers, start the API locally and submit the README's example request.

Before you start

  • Python environment with pip and Uvicorn available.
  • Values for the documented Serper, OpenAI-compatible, Zilliz and authentication settings.
  • The project files, including requirements.txt.

Steps

  1. Create a .env file in the project root and set the documented Serper, OpenAI, Zilliz and authentication variables.

  2. Install the project dependencies with pip install -r requirements.txt.

  3. Start the service with uvicorn main:app --reload --port 8069.

  4. Send a POST request to /rag-search with a bearer API key, query and supported request options such as search_n, is_reranking, is_detail and is_filter.

Expected outcome

A locally running FastAPI service can receive a RAG search request using the configured search and vector database settings.

Guide limitations

  • The README supplies example request fields but does not document the response schema.
  • The example names Google as the search provider; support for other providers is not demonstrated.
  • The setup instructions do not describe provisioning or populating the Zilliz collection.
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 SearchRetrieve relevant information for a query using configured web search and vector retrieval.Self-hosted, ServerThe documented primary workflow is self-hosted: configure environment variables, install Python dependencies and run the FastAPI server. The example request uses bearer API-key authentication.
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
15 October 2026
Original website title
thinkany-ai/rag-search · Official homepage title · retained in its source language
How we review sourcesSuggest a correction