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

Create minimal indexing pipeline for Haystack 2.0 #6014

Closed

Timoeller opened this issue Oct 9, 2023 · 0 comments · Fixed by #6412

Assignees

Labels

Milestone

Contributor

Timoeller commented Oct 9, 2023 •

edited

Loading

Is your feature request related to a problem? Please describe.
We want to showcase indexing pipeline in v2.

Describe the solution you'd like
We need example code and/or end2end tests showing:

an indexing pipeline taking as input: either a folder containing multiple files, or a single file
convert files of various types (PDF, docx, txt)
usage of the preprocessor
creation of embeddings
indexing to a docstore for both sparse and dense retrieval

Timoeller added P1 2.x labels

Timoeller added this to the 2.0-beta milestone

Timoeller mentioned this issue

Create indexing pipeline based on unstructured.io partition function #6015

Closed

masci assigned julian-risch

julian-risch mentioned this issue

docs: Add indexing example #6412

Merged

julian-risch closed this as completed in #6412

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment