Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat(document-search): add document processing with unstructured #5

Closed
mhordynski opened this issue Sep 12, 2024 · 0 comments · Fixed by #26
Closed

feat(document-search): add document processing with unstructured #5

mhordynski opened this issue Sep 12, 2024 · 0 comments · Fixed by #26
Assignees
@akonarski-ds
Labels
document search Changes to the document search package feature New feature or request integrations Changes in vendor integration
Milestone
Ragbits 0.1

Comments

@mhordynski
Copy link
Member

Feature description

In document-search module it should be possible to parse documents into elements using unstructured API.
Results of the parsing should be represented as Element objects and possible to store & retrieve from the vector_store.

Motivation

Unstuctured gives us possibility to quicly introduce multiple formats of the documents, thus improving overall usability of the application.

Additional context

Free API may be used to test this feature: https://docs.unstructured.io/api-reference/api-services/free-api
@mhordynski mhordynski added feature New feature or request document search Changes to the document search package labels Sep 12, 2024
@akonarski-ds akonarski-ds self-assigned this Sep 12, 2024
@mhordynski mhordynski moved this to Backlog in ragbits Sep 13, 2024
@micpst micpst added the integrations Changes in vendor integration label Sep 13, 2024
@micpst micpst added this to the Document search release milestone Sep 13, 2024
@akonarski-ds akonarski-ds mentioned this issue Sep 19, 2024
Merged
@mhordynski mhordynski linked a pull request Sep 23, 2024 that will close this issue
feat(document-search): add document processing with unstructured #26
Merged
@mhordynski mhordynski modified the milestones: Ragbits Document Search 0.1, Ragbits 0.1 Sep 23, 2024
@github-project-automation github-project-automation bot moved this from In review to Done in ragbits Sep 24, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@akonarski-ds akonarski-ds

Labels
document search Changes to the document search package feature New feature or request integrations Changes in vendor integration
Projects
ragbits
Status: Done
Milestone
Ragbits 0.1
Development

Successfully merging a pull request may close this issue.

feat(document-search): add document processing with unstructured deepsense-ai/ragbits
3 participants
@mhordynski @micpst @akonarski-ds