Skip to main content

A retrieval-based QnA and code generation chatbot using sentence-transformer embeddings.

Project description

LunaAI

LunaAI is a retrieval-based QnA and code generation chatbot built using SentenceTransformer embeddings and cosine similarity.
It can answer natural language questions and retrieve highly relevant answers from a preloaded CSV dataset — no fine-tuning required.


🔧 Features

  • Embedding-based search using SentenceTransformers
  • Cosine similarity + fuzzy matching fallback
  • Loads embeddings and CSV from Google Drive
  • Clean CLI interface with feedback saving
  • Lightweight and fast — works offline after setup

🚀 Installation

pip install lunaai

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lunaai-0.1.0.tar.gz (4.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lunaai-0.1.0-py3-none-any.whl (4.6 kB view details)

Uploaded Python 3

File details

Details for the file lunaai-0.1.0.tar.gz.

File metadata

  • Download URL: lunaai-0.1.0.tar.gz
  • Upload date:
  • Size: 4.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for lunaai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 069ec23784d7b8ccb08b522d13bcf6a951634afd9a94c271e71010e635865e2a
MD5 b994664c6ab91d86654b7111dd56cddf
BLAKE2b-256 3f30c036264f029ec1c4a8ad01dad7d115f34f377a278231353cb50e1d57fb8b

See more details on using hashes here.

File details

Details for the file lunaai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: lunaai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 4.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for lunaai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 15403d066abe51b4a96e3d7563f0b2106c1aaa1282261cca2338af182c265be9
MD5 eaa7415a1c2626ad6813592901396636
BLAKE2b-256 32561f311ff6a95853dc0425987fd21ceb308a3f06c7b8fe49794a7a92ac1593

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page