Skip to main content

Multimodal Graph retrieval

Project description

Example Usage

from multimodal_rag import MultimodalRAG

# Initialize MultimodalRAG instance
mm_rag = MultimodalRAG(pdf_directory="/path/to/pdf_directory", output_directory="/path/to/output_directory")

# Preprocess documents
mm_rag.preprocess(directory="/path/to/pdf_directory", use_multiprocessing=True)

# Perform a multimodal query
query = "example query text"
search_results, result_paths = mm_rag.multimodal_query(query, k=5)

# Display results
print("Search Results:", search_results)
print("Result Paths:", result_paths)

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

multimodalgraphretrieval-0.0.1a0.tar.gz (4.8 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file multimodalgraphretrieval-0.0.1a0.tar.gz.

File metadata

File hashes

Hashes for multimodalgraphretrieval-0.0.1a0.tar.gz
Algorithm Hash digest
SHA256 30a591e61c1cbe7204150d274191b9aa437f259f7b937a50093a8166210e3982
MD5 a09d917033f26c693c127dff79792dc1
BLAKE2b-256 6aa63cd10ede9e5c5f3aae66e8835bf74c82624fa3dfa6bc52f0756acd377bae

See more details on using hashes here.

File details

Details for the file MultimodalGraphRetrieval-0.0.1a0-py3-none-any.whl.

File metadata

File hashes

Hashes for MultimodalGraphRetrieval-0.0.1a0-py3-none-any.whl
Algorithm Hash digest
SHA256 271e60bfa6f85e538627caf85d0d7c3e809b2831cde3a18429762b4b0b197c91
MD5 7156398df100883e5c68a5aada447015
BLAKE2b-256 bd9c1c11a26d39726474724e0614693e8e48c4c491d98792d8c662d767be0eb8

See more details on using hashes here.

Supported by

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