Skip to main content

A module to facilitate local testing of RAG pipeline for multiple datatypes

Project description

multi_rag

This module facilitates testing RAG pipelines on Local machines with chroma_db, with text embeddings from 'bge-base-en-v1.5' and image embeddings from 'clip-vit-b-32'

Currently this module supports pdf, docx, xlsx, png, jpg, jpeg and txt file formats

User can give the path of the file to the embed function, which sets up the chroma_db/ folder for the embeddings while temp/ folder gets set up to mimic the actual database to store the data chunks.

Retrive function takes query as input and gives out a dictionary of 'text','tables','images'

query function takes query as input and returns the answer and retrieved data as output

One needs to have gemini api key to query, but embedding and retrieval part is completely local

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

multi_rag-0.1.1.tar.gz (6.4 kB view details)

Uploaded Source

Built Distribution

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

multi_rag-0.1.1-py3-none-any.whl (6.3 kB view details)

Uploaded Python 3

File details

Details for the file multi_rag-0.1.1.tar.gz.

File metadata

  • Download URL: multi_rag-0.1.1.tar.gz
  • Upload date:
  • Size: 6.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for multi_rag-0.1.1.tar.gz
Algorithm Hash digest
SHA256 347a05d55b23df87ad833b7084c2779637f34fd3f940078141b96941fca96cd6
MD5 47e265a0aeffedd143ba1762c241887f
BLAKE2b-256 dc335037936c86f0a4755a32b59f474d124d7fc383feec29bc192f7279253594

See more details on using hashes here.

Provenance

The following attestation bundles were made for multi_rag-0.1.1.tar.gz:

Publisher: python-publish.yml on Srimadhav2007/multirag

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file multi_rag-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: multi_rag-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 6.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for multi_rag-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 157f5167413abb4c6ca6afc7326bbd1d971b954dcc2e3c50c0472a39cf07a9e0
MD5 a729e8375f6315f3558ba5faf2b69cdf
BLAKE2b-256 00fcaa5c4debc46470b63817f2d5ee77ec7a95bef8589d59d2e3fa9c71b2096e

See more details on using hashes here.

Provenance

The following attestation bundles were made for multi_rag-0.1.1-py3-none-any.whl:

Publisher: python-publish.yml on Srimadhav2007/multirag

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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