Devanik21/LLM-powered-chatbot--DSAI-Club-

View on GitHub by @Devanik21

LLM chatbot built for the Data Science & AI Club — multi-turn conversation, configurable persona, streaming output, session export, and RAG/tool-use pattern demonstrations.

What's novel

LLM chatbot built for the Data Science & AI Club — multi-turn conversation, configurable persona, streaming output, session export, and RAG/tool-use pattern demonstrations.

Code Analysis

1 files read · 3 rounds

A single-file Streamlit application that ingests multiple document formats (PDF, DOCX, CSV, etc.), extracts text, and uses Google Gemini to perform analysis tasks like Q&A, summarization, and key point extraction with optional visualization.

Strengths

Solid multi-format document parsing implementation with clean function organization for text extraction; good use of Streamlit session state for configuration; functional visualization features using Seaborn.

Weaknesses

No error handling or retry logic visible; single-file architecture limits modularity and maintainability; README significantly misrepresents the project as a multi-backend conversational AI with memory when it's actually a document analyzer; no tests present.

Score Breakdown

Innovation

4 (25%)

Craft

39 (35%)

Traction

9 (15%)

Scope

31 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+0

Craft

Ci-3

Tests-4

Polish+0

Releases+0

Has License+5

Code Quality+12

Readme Quality+15

Recent Activity+7

Structure Quality+2

Commit Consistency+0

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+3

Early Traction+0

Devto Reactions+0

Community Contribs+0

Scope

Commits+5

Languages+3

Subsystems+0

Bloat Penalty+0

Completeness+5

Contributors+5

Authored Files+4

Readme Code Match+3

Architecture Depth+0

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

MIT