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

Docsense

DocSense is a Python web application that compares PDFs with cosine similarity scans and lets users query processed PDF content through a chatbot. It combines a Streamlit interface with FastAPI and LangChain, and documents Llama 3 through Ollama and Google Gemini as chatbot model options.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Docsense — 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 DocSense when a task involves textual similarity between PDFs or conversational exploration of PDF contents, rather than general document management.

Who it is for

  • People reviewing similarities between two PDF documents.
  • Users who want to ask questions about information in uploaded PDFs.
  • Developers exploring a self-hosted PDF comparison and question-answering application.

Documented uses

  • Compare two PDFs at document or sentence level and view a similarity score.
  • Choose a sentence-level scan that preprocesses text before comparison.
  • Load PDFs into a vector database and query their contents through a chatbot.
  • Prototype a local PDF chatbot using Llama 3 through Ollama.
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed. Its README documents a self-hosting workflow and a hosted Streamlit homepage.

  • Comparison supports Count Vectorizer, TF-IDF Vectorizer, and all-MiniLM-L6-v2 embedding choices.
  • The chatbot workflow offers Llama 3 through Ollama or Google Gemini; the setup instructions call for a Google API key in the environment configuration.
  • The documented stack includes Streamlit, FastAPI, LangChain, embeddings, and Chroma vector database.
  • The project is written in Python and provides a self-hosting setup in its README.

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 DocSense for local use

Prepare the project and launch its Streamlit application.

Before you start

  • Python environment with pip
  • A clone of the DocSense repository
  • Google API key for the documented environment configuration
  • Ollama and Llama 3 if using the local model route

Steps

  1. Clone the repository and change into its directory.

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

  3. Create a root-level .env file and add GOOGLE_API_KEY and DEPLOYED=False.

  4. For the local model option, install Ollama and Llama 3 using ollama run llama3.

  5. Launch the interface with streamlit run app.py.

Expected outcome

The Streamlit application is launched for its documented PDF comparison and chatbot workflows.

Guide limitations

  • The documented setup does not establish that every model route works without its corresponding service or credentials.
  • The repository README documents setup and launch steps; this is not a report of an execution test.
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
DocsenseCompare two PDFs at document or sentence level and view a similarity score.Self-hosted, WebThe repository is public and identifies the project as MIT-licensed. Its README documents a self-hosting workflow and a hosted Streamlit homepage.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
lakshya324/DocSense · Official homepage title · retained in its source language
How we review sourcesSuggest a correction