nooksandcrannieslgb937/ai-chatbot

View on GitHub by @nooksandcrannieslgb937

🤖 Automate document indexing and enable intelligent Q&A with this real-time Telegram bot using OpenAI GPT-4 and Pinecone for enhanced user interaction.

What's novel

🤖 Automate document indexing and enable intelligent Q&A with this real-time Telegram bot using OpenAI GPT-4 and Pinecone for enhanced user interaction.

Code Analysis

19 files read · 4 rounds

A RAG-based Telegram bot and REST API that indexes local documents (TXT, PDF, DOCX) into Pinecone vector database and answers user questions using OpenAI, with real-time file watching via watchdog.

Strengths

Clean separation of concerns with distinct service layers (knowledge, LLM, memory, vectorstore), proper use of async patterns, and a working file-watching pipeline that handles create/modify/delete events with hash-based deduplication.

Weaknesses

Critical embedding dimension mismatch (3072-dim vectors truncated to 2048) silently degrades retrieval quality, conversation memory is implemented but never actually used in the LLM prompt, and the README describes commands and features that don't exist in the code.

Score Breakdown

Innovation

3 (25%)

Craft

59 (35%)

Traction

8 (15%)

Scope

56 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+0

Concept Novelty+0

Craft

Ci-1

Tests+5

Polish+0

Releases+0

Has License+5

Code Quality+16

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+2

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+2

Scope

Commits+3

Languages+5

Subsystems+13

Bloat Penalty+0

Completeness+7

Contributors+6

Authored Files+12

Readme Code Match+3

Architecture Depth+7

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

MIT