DocOllama - Private Chat with Your Documents

Completely local RAG with chat UI

Installation

Clone the repo:

git clone [email protected]:justushar/DocOllama.git
cd DocOllama

Install the dependencies:

pip install -r requirements.txt

Fetch your LLM (llama3.1 by default):

ollama pull llama3.1:8b

Run the Ollama server

ollama serve

Start DocOllama:

streamlit run app.py

Architecture

Ingestor

Extracts text from PDF documents and creates chunks (using semantic and character splitter) that are stored in a vector databse

Retriever

Given a query, searches for similar documents, reranks the result and applies LLM chain filter before returning the response.

QA Chain

Combines the LLM with the retriever to answer a given user question

Tech Stack

• Ollama - run local LLM
• LangChain - build LLM-powered apps
• Qdrant - vector search/database
• FlashRank - fast reranking
• FastEmbed - lightweight and fast embedding generation
• Streamlit - build UI for data apps
• PDFium - PDF processing and text extraction