Added Contextual AI Parser with Weaviate Recipe

[jinashrouniyar-268]

Description

This is a code recipe that uses Weaviate to perform RAG over PDF documents parsed by Contextual AI Parser.

In this notebook, we accomplish the following:

• Parse two distinct document types using Contextual AI Parser: research papers and table-rich documents
• Extract structured markdown with document hierarchy preservation and advanced table extraction
• Generate text embeddings with OpenAI
• Perform multi-modal RAG using Weaviate

Contribution Type

• Integration
• Weaviate feature
• Weaviate service

Promotion

• Company X handle: https://x.com/ContextualAI
• Company LinkedIn account: https://www.linkedin.com/company/contextualai/

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[orca-security-eu]

Orca Security Scan Summary

Status	Check	Issues by priority
Passed	Infrastructure as Code	0   13   34   39	View in Orca
Passed	SAST	0   0   0   0	View in Orca
Passed	Secrets	0   0   0   0	View in Orca
Passed	Vulnerabilities	0   0   0   0	View in Orca

🛡️ The following IaC misconfigurations have been detected

	NAME	FILE
	Controller creating containers without dropped capabilities	...a/docker-compose.yml	View in code
	Controller creating containers without dropped capabilities	...ker-compose-apis.yml	View in code
	Controller creating containers without dropped capabilities	...se-contextionary.yml	View in code
	Controller creating containers without dropped capabilities	...se-contextionary.yml	View in code
	Controller creating containers without dropped capabilities	...ose-transformers.yml	View in code
	Controller creating containers without dropped capabilities	...ose-transformers.yml	View in code
	Controller creating containers without dropped capabilities	...zeroshot/compose.yml	View in code
	Controller creating containers without dropped capabilities	...zeroshot/compose.yml	View in code
	Controller creating containers without dropped capabilities	...er-compose-clip.yaml	View in code
	Controller creating containers without dropped capabilities	...er-compose-clip.yaml	View in code
	Controller creating containers without dropped capabilities	...h/docker-compose.yml	View in code
	Controller creating containers without dropped capabilities	...se-t2v-snowflake.yml	View in code
	Controller creating containers without dropped capabilities	...se-t2v-snowflake.yml	View in code
	Container Traffic Not Bound To Host Interface	...a/docker-compose.yml	View in code
	Container Traffic Not Bound To Host Interface	...ker-compose-apis.yml	View in code
	Container Traffic Not Bound To Host Interface	...se-contextionary.yml	View in code
	Container Traffic Not Bound To Host Interface	...se-contextionary.yml	View in code
	Container Traffic Not Bound To Host Interface	...ose-transformers.yml	View in code
	Cpus Not Limited	...ose-transformers.yml	View in code
	Cpus Not Limited	...ose-transformers.yml	View in code
	Container Traffic Not Bound To Host Interface	...tion/knn/compose.yml	View in code
	Cpus Not Limited	...tion/knn/compose.yml	View in code
	Container Traffic Not Bound To Host Interface	...er-compose-clip.yaml	View in code
	Cpus Not Limited	...er-compose-clip.yaml	View in code
	Container Traffic Not Bound To Host Interface	...se-t2v-snowflake.yml	View in code
...	...	...	...

[erika-shorten]

This looks awesome @jinashrouniyar-268, thank you for the contribution!

[jinashrouniyar-268]

@erika-shorten I have marked this PR ready for review. This can now be merged to the main repo. Thanks

[weaviate-git-bot]

To avoid any confusion in the future about your contribution to Weaviate, we work with a Contributor License Agreement. If you agree, you can simply add a comment to this PR that you agree with the CLA so that we can merge.

beep boop - the Weaviate bot 👋🤖

PS:
Are you already a member of the Weaviate Forum?

[jinashrouniyar-268]

I agree with the Contributor License Agreement

[erika-shorten]

Hi @jinashrouniyar-268,
I added Weaviate Cloud as an option to your notebook. Everything else looks good to me, so I'll merge it now. Thanks for the contribution!