Media Tagging with Langchain

Makes it possible to use media_tagging library with Langchain supported multimodal LLMs.

Installation

pip install media-tagging-langchain

Usage

For a general purpose usage please refer to media_tagging usage documentation.

media-tagger ACTION MEDIA_PATHs \
  --media-type <MEDIA_TYPE> \
  --tagger langchain \
  --db-uri=<CONNECTION_STRING> \
  --writer <WRITER_TYPE> \
  --output <OUTPUT_FILE_NAME>

where:

• ACTION - either tag or describe.
• MEDIA_PATHs - names of files for tagging (can be urls) separated by spaces.

Instead of reading MEDIA_PATHs as positional arguments you can read them from a file using
--input FILENAME.CSV argument. Use --input.column_name=NAME_OF_COLUMN to specify column name in the file.

• <MEDIA_TYPE> - type of media (IMAGE, TEXT).
• <CONNECTION_STRING> - Optional connection string to the database with tagging results (i.e. sqlite:///tagging.db). If this parameter is set make sure that DB exists.
• <WRITER_TYPE> - writer identifier (check available options at garf-io library).
• <OUTPUT_FILE_NAME> - name of the file to store results of tagging (by default tagging_results).

Documentation

Explore full documentation on working with Langchain media tagging.

• Documentation