This notebook demonstrates how to leverage Clarifai-Unstructured integration for efficient pre-processing of unstructured data and ingestion into Clarifai App.
- Clarifai App can be used as destination connector within Unstructured.IO.
- This enables the capability to pre-process, partition, chunk your data before ingestion into Clarifai App, whcih acts as a vectorDB.
- You can build your RAG pipeline on top of clarifai App right away without needing much effort on ETL of your unstructured data.
| Notebook | Open in Colab |
|---|---|
| S3 bucket as source Example notebook |  |
| Dropbox as source Example notebook | |
| Github as source Example notebook | |
Check out the docs in the below reference links to deep dive into clarifai and langchain.
Unstructured.IO: https://unstructured-io.github.io/unstructured/introduction.html
Clarifai: https://www.clarifai.com
Clarifai Demo: https://clarifai.com/demo
Sign up for a free Account: https://clarifai.com/signup
Developer Guide: https://docs.clarifai.com
Clarifai Community: https://clarifai.com/explore
Python SDK Docs: https://docs.clarifai.com/python-sdk/api-reference