OpenViSTAI · Agents · Blockchain · Crypto
Menu
RAG & Knowledge Systems

Flamehaven Filesearch

Flamehaven Filesearch is a Python application for self-hosted retrieval-augmented search across document collections. It supports BM25 keyword, semantic and hybrid retrieval, and connects searches to several LLM providers.

Independent OpenViST project profile, based on linked sources.

Flamehaven Filesearch — 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 a self-hosted document-search service needs configurable retrieval, LLM providers and application integrations.

Who it is for

  • Teams building searchable collections from internal documents.
  • Developers integrating document retrieval into Python applications, REST services or agent frameworks.
  • Operators who want to configure a local Ollama provider or a cloud LLM provider.

Documented uses

  • Ingest supported documents into a named searchable store.
  • Find relevant material with keyword, semantic or hybrid search.
  • Generate answers with an LLM provider and link results to source documents and chunks.
  • Expose document search to another application through the Python SDK or REST API.
Before you choose

Requirements & limits

  • Docker and Python package installation are both documented deployment paths.
  • The README lists Gemini, OpenAI, Anthropic Claude, Ollama and OpenAI-compatible providers; each requires provider-specific configuration.
  • The core package covers a subset of file parsing; PDF and office-document parsers and image OCR are optional extras, with Tesseract required for OCR.
  • SQLite is listed as the default storage, while PostgreSQL with pgvector and Redis caching are optional.
  • The repository specifies an MIT 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

Install the Python package and configure a provider

Prepare a Python installation with the REST API extra and credentials for one supported LLM provider.

Before you start

  • Python 3.8 or later, as stated in the repository README.
  • A configured provider credential; the documented Gemini option uses GEMINI_API_KEY.
  • For the REST API server installed from Python, the api extra provides FastAPI and uvicorn.

Steps

  1. Install the package with the command below.

    Documented command
    pip install flamehaven-filesearch[api]
  2. Set GEMINI_API_KEY for the default Gemini provider, or configure the documented variables for another provider.

  3. Set FLAMEHAVEN_ADMIN_KEY as required by the README configuration.

Expected outcome

The Python package and its REST API dependencies are installed, with the documented environment configuration prepared.

Guide limitations

  • These steps cover installation and configuration only; they do not demonstrate starting the server or completing an upload and search.
  • Other document parsers, image OCR, vector indexing and PostgreSQL support are listed as separate extras.
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

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
Flamehaven FilesearchIngest supported documents into a named searchable store.Docker, Self-hosted, Server
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
flamehaven01/Flamehaven-Filesearch · Official homepage title · retained in its source language