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

Local Llama

Local Llama is a self-hosted Python and Streamlit application that indexes PDF, TXT, DOCX and Markdown documents and answers questions using retrieved document passages and chat history. It uses Ollama for embeddings and answer generation, Haystack for retrieval-augmented generation, and persistent Chroma storage for reusing indexed documents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Local Llama — 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 you want a locally run document-chat workflow and have Ollama and the Python dependencies installed.

Who it is for

  • People who want to search and ask questions about personal document collections locally.
  • Users building an offline knowledge base from PDFs, text files, Word documents or Markdown.

Documented uses

  • Index documents into a reusable local collection.
  • Ask questions and receive answers grounded in retrieved document passages.
  • Continue using indexed documents across sessions.
Before you choose

Requirements & limits

The project is open source under the Apache 2.0 License. The documented workflow runs the application locally.

  • Supported inputs are PDF, TXT, DOCX and Markdown.
  • Ollama handles embeddings and generation; the README names nomic-embed-text and llama3:8b as models that can be changed.
  • Indexed documents are stored in persistent Chroma storage.
  • The README documents installation and launch steps but does not specify hardware requirements.

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 and launch Local Llama

Set up the documented local app and open its Streamlit interface.

Before you start

  • Ollama installed
  • Cloned Local Llama repository
  • Python and pip available to install the repository dependencies

Steps

  1. Install Ollama and clone the Local Llama repository.

  2. In the repository, install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  3. Pull the embedding model with ollama pull nomic-embed-text and the generation model with ollama pull llama3:8b.

  4. Start Ollama with ollama serve, then launch the app with the command below.

    Documented command
    python -m streamlit run local_llama_v3.py

Expected outcome

The Streamlit application is launched for uploading documents and chatting with them.

Guide limitations

  • The README does not give hardware requirements.
  • Alternative model compatibility requirements are not detailed.
Documentation 1 ↗
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
Local LlamaIndex documents into a reusable local collection.Linux, macOS, Self-hosted, WindowsThe project is open source under the Apache 2.0 License. The documented workflow runs the application locally.
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

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
jlonge4/local_llama · Official homepage title · retained in its source language
How we review sourcesSuggest a correction