RRepoGEO

REPOGEO REPORT · LITE

mukulpatnaik/researchgpt

Default branch main · commit fcd84165 · scanned 6/27/2026, 5:03:17 PM

GitHub: 3,527 stars · 318 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface mukulpatnaik/researchgpt, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    llm, research-assistant, pdf-qa, fastapi, python, openai, embeddings, RAG, local-llm-app, self-hosted
  • highreadme#2
    Reposition README's opening to clarify project type and value

    Why:

    CURRENT
    ## **This repository is no longer actively maintained. A more advanced version of this project is available at chat.portal.so for free and will be open sourced soon.**

# ResearchGPT

This is a simple fastapi app that provides a clean interface to enable a conversation with any pdf. You can enter a link to a pdf hosted online or upload your own pdf. The app will then extract the text from the pdf, create embeddings from the text and use them with the openai api to generate a response to a question you ask. It will also return a source for the part of the text it used to generate the response and the page number.
    COPY-PASTE FIX
    # ResearchGPT: An Open-Source FastAPI Application for Local PDF Q&A with LLMs

This repository provides a simple, self-hostable FastAPI application that enables conversation with any PDF. It's designed for users looking to build or learn about local LLM-powered research assistants.

## **Note: This repository is no longer actively maintained. A more advanced version of this project is available at chat.portal.so for free and will be open sourced soon.**

The app extracts text from PDFs, creates embeddings, and uses them with the OpenAI API to generate responses to your questions, returning sources and page numbers. You can enter a link to an online PDF or upload your own.
  • mediumreadme#3
    Clarify the scope of the example video in the README

    Why:

    CURRENT
    ## Example 
(this video shows some features available on the live demo only )

https://user-images.githubusercontent.com/36257370/230793133-ecb579d3-47d9-4200-916a-9c5978a40b09.mp4
    COPY-PASTE FIX
    ## Example

This video demonstrates the core functionality of ResearchGPT, including features available in this open-source repository. (Note: Some advanced features shown are exclusive to the live demo at https://www.dara.chat).

https://user-images.githubusercontent.com/36257370/230793133-ecb579d3-47d9-4200-916a-9c5978a40b09.mp4

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface mukulpatnaik/researchgpt
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
ChatGPT
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. ChatGPT · recommended 1×
  2. Perplexity AI · recommended 1×
  3. Elicit · recommended 1×
  4. Semantic Scholar · recommended 1×
  5. Humata AI · recommended 1×
  • CATEGORY QUERY
    How can I use AI to chat with research papers and extract key information?
    you: not recommended
    AI recommended (in order):
    1. ChatGPT
    2. Perplexity AI
    3. Elicit
    4. Semantic Scholar
    5. Humata AI
    6. ChatPDF

    AI recommended 6 alternatives but never named mukulpatnaik/researchgpt. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a tool to build a local PDF question-answering system with LLMs.
    you: not recommended
    AI recommended (in order):
    1. LlamaIndex (run-llama/llama_index)
    2. LangChain (langchain-ai/langchain)
    3. Haystack (deepset-ai/haystack)
    4. PrivateGPT (imartinez/privateGPT)
    5. RAGatouille (m-bain/ragatouille)

    AI recommended 5 alternatives but never named mukulpatnaik/researchgpt. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of mukulpatnaik/researchgpt?
    pass
    AI named mukulpatnaik/researchgpt explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts mukulpatnaik/researchgpt in production, what risks or prerequisites should they evaluate first?
    pass
    AI named mukulpatnaik/researchgpt explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo mukulpatnaik/researchgpt solve, and who is the primary audience?
    pass
    AI named mukulpatnaik/researchgpt explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of mukulpatnaik/researchgpt. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/mukulpatnaik/researchgpt.svg)](https://repogeo.com/en/r/mukulpatnaik/researchgpt)
HTML
<a href="https://repogeo.com/en/r/mukulpatnaik/researchgpt"><img src="https://repogeo.com/badge/mukulpatnaik/researchgpt.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

mukulpatnaik/researchgpt — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite