Open
Conversation
pradeepto
commented
Mar 7, 2026
pradeepto
commented
- Adding CLAUDE.md
- Adding docs/ARCHITECHTURE.md - Claude analysed and generated architecture description of unstructured data controller
- docs/LANGCHAIN_CHUNKING.md - Claude analysed and generated how langchain-go is used for 3 chunking strategies.
piyush-garg
reviewed
Mar 9, 2026
|
|
||
| ## System Architecture | ||
|
|
||
| The Unstructured Data Controller sits at the center of a larger Dataverse AI platform, orchestrating the end-to-end pipeline from raw document ingestion to processed, chunked data ready for retrieval-augmented generation (RAG) workflows. |
piyush-garg
reviewed
Mar 9, 2026
| Users upload documents in various formats (DOC, PDF, PPT, HTML, and other unstructured data formats) to supported data sources: | ||
|
|
||
| - **S3 Buckets** — Primary ingestion source. Documents are uploaded to a configured S3 bucket with a prefix matching the data product name. | ||
| - **Google Drive** — Planned integration for ingesting documents from Google Drive. |
piyush-garg
reviewed
Mar 9, 2026
| - Chunks converted documents using LangChain text splitters | ||
| - Uploads processed chunks to destination storage (Snowflake internal stages) | ||
|
|
||
| #### BYO Document Processing |
piyush-garg
reviewed
Mar 9, 2026
|
|
||
| The platform provides three core processing stages, each with multiple strategy options: | ||
|
|
||
| | Stage | Providers | Description | |
Contributor
There was a problem hiding this comment.
we dont have embeding and data cleaning, other two stages also have single providers - docling anf langchain
piyush-garg
reviewed
Mar 9, 2026
| | **Vector Embeddings Generation** | Gemini, models.corp | Generates vector embeddings from chunks for similarity search | | ||
| | **Data Cleaning** | LangChain | Cleans and normalizes text data before processing | | ||
|
|
||
| **Additional Processing Strategies** include Knowledge Graph construction and Agentic Graph RAG for more advanced document understanding and retrieval patterns. |
piyush-garg
reviewed
Mar 9, 2026
|
|
||
| ### Vector Database / Processed Documents Storage | ||
|
|
||
| Processed and chunked documents are stored in various backends: |
Contributor
There was a problem hiding this comment.
right now it is only s3 bucket
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.