feat: add read signed url of the vector chunks

[mnvsk97]

• Add a function to fetch artifacts of the data directory by data dir fqn.
• Add function to get read signed URL of a data dir and local file path
• Add _signed_url in the Q/A API response to enable UI to reference and provide links to the source files.
• Handle metadata enrichment for stream and nonstream response types.
• Refactor MultiModalParser
  • Move default multi-modal parser prompt to constants
  • Move LLM instance creation to __init__
  • Remove unnecessary passing of instance objects like prompt, and llm between functions and use instance vars instead.
• Upgrade langchain-openai from 0.1.20 to 0.1.25 to fix issues introduced in feat: upgrade langchain libraries #371
• Remove unused libraries: openai and orjson
• Closes Parser Registry Problem #363

[S1LV3RJ1NX]

Need clarity on two things:

• Need to update chunk metadata with document metadata, if any for all the parsers
• How does caching work for parsers with same extension but different config, as the caching key is the file extension.

[mnvsk97]

Need clarity on two things:

• Need to update chunk metadata with document metadata, if any for all the parsers

• How does caching work for parsers with same extension but different config, as the caching key is the file extension.

1. Not sure about this, need an example.
2. I missed the part around config. I'll add an md5 hash of the config and extension.

[S1LV3RJ1NX]

Not sure about this, need an example.

@mnvsk97 - if you would check get_chunks function of any parser, it takes file_path and metadata (lets call this as doc_metadata for sake of explanation) as input argument. So when an individual document chunk generates it's own metadata, we should also add the doc_metadata to the chunk metadata.

Another thing that is missing is,
QueryController's required_metadata list should be updated to send pre-signed urls in the response.
https://github.com/mnvsk97/cognita/blob/16c20fb006e9065cc435439d77a44bd58e3981a6/backend/modules/query_controllers/base.py#L24

[mnvsk97]

Not sure about this, need an example.

@mnvsk97 - if you would check get_chunks function of any parser, it takes file_path and metadata (lets call this as doc_metadata for sake of explanation) as input argument. So when an individual document chunk generates it's own metadata, we should also add the doc_metadata to the chunk metadata.

Another thing that is missing is, QueryController's required_metadata list should be updated to send pre-signed urls in the response. https://github.com/mnvsk97/cognita/blob/16c20fb006e9065cc435439d77a44bd58e3981a6/backend/modules/query_controllers/base.py#L24

Resolved all the above mentioned points in the latest commits