Problem/Motivation

When a content type has a media field type containing PDF files, we want to index the text inside the PDF and save it in the Typesense's vector database in order to allow AI embaddings.

Remaining tasks

User interface changes

API changes

Data model changes

Issue fork search_api_typesense-3459544

Command icon Show commands

Start within a Git clone of the project using the version control instructions.

Or, if you do not have SSH keys set up on git.drupalcode.org:

About issue forks

Comments

robertoperuzzo created an issue. See original summary.

robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Issue summary: View changes
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Issue summary: View changes

robertoperuzzo opened merge request !28

robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented

@lussoluca I'm not able to fix the phpstan error

$ php vendor/bin/phpstan analyze $_WEB_ROOT/modules/custom/$CI_PROJECT_NAME $PHPSTAN_CONFIGURATION --no-progress || EXIT_CODE=$?
 ------ --------------------------------------------------------------------- 
  Line   src/Attribute/EmbeddingModel.php                                     
 ------ --------------------------------------------------------------------- 
  32     Drupal\search_api_typesense\Attribute\EmbeddingModel::__construct()  
         does not call parent constructor from                                
         Drupal\Component\Plugin\Attribute\Plugin.                            
 ------ --------------------------------------------------------------------- 
 [ERROR] Found 1 error

Any advice?

lussoluca’s picture

lussoluca
he/him
Primary language Italian
Location Italy
commented

This has been fixed in the latest 1.0.x version

robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Assigned: robertoperuzzo » Unassigned
Status: Active » Needs review
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Assigned: Unassigned » robertoperuzzo
Status: Needs review » Needs work
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Issue tags: +ContributionWeekend2025
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented

I close this issue because we can approach that in two steps:

  1. first, we can use search_api_attachments module to extract the text from PDF (...and not only PDFs see #3519494: Add a plugin for Unstructured.io
  2. then, create the embeddings from the extracted text
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Assigned: robertoperuzzo » Unassigned
Status: Needs work » Closed (outdated)
robertoperuzzo’s picture

robertoperuzzo
Primary language Italian
Location 🇮🇹 Tezze sul Brenta, VI
commented
Related issues: +#3519494: Add a plugin for Unstructured.io