Thanks @ishani patel, it is already working as expected
So, moving to RTBC.
There is a related issue with the other boost plugins which will be fixed here: https://www.drupal.org/project/search_api/issues/3550113 🐛 Undefined array key "boosts" warning in NumberFieldBoost processor on Drupal 11 Active
I would like that someone could take a second look on this after been moved to 2.0.x
Moving this to 2.0.x
because of it is not a bug fix, so it could wait.
Thanks @tmiguelv to do a second test there.
Moving it to RTBC.
So, we have added a new logic with three possible scenarios:
Title NOT in contextual content + exclude_title FALSE (default) -> Title IS auto-added
Title IS in contextual content + exclude_title FALSE -> Title NOT auto-added
Title NOT in contextual content + exclude_title TRUE -> Title NOT auto-added
So, we would add the title automatically when it is not added as contextual content and the option "exclude_title" is FALSE?
I've been reviewing changes introduced on this issue and everything seems to be working as described.
Steps to perform
- Enable raw embedding vector retrieval in the Search API server
- Reindex content and extract a known normalised vector from an indexed entity (drupal_entity_id
)
- Execute a search with $query->setOption('vector_input', $extracted_vector)
instead of a text query
Results
- Search has been completed successfully without triggering an extra LLM call
- Top result matched the entity from which the vector was originally retrieved
I've been testing using Ollama and OpenAI and everything works as expected.
I've also added a small change to fix phpcs.
Everything looks good to me @kim.pepper.
I've just created a new issue on SQLite provider where it should be also changed after this change.
See: https://www.drupal.org/project/ai_vdb_provider_sqlite/issues/3549485 📌 Change filter typehint from string to mixed Needs review
Hey Scott!
I've added some changes and tested the solution, now grouping is working as expected on my side.
Maybe we should just create a new release for 2.x
and point this issue to it.
All good for me Scott.
I added some changes to fix phpcs and cspell, the rest is fine.
Hey @herved
The jQuery dependency here is quite minimal, but we'd need to refactor the once()
usage and update all the jQuery calls.
So, if you have the time, feel free to try it :)
Thank you Dieter to keep an eye on this!
It will be included in the next release 1.2.42
gxleano → made their first commit to this issue’s fork.
Thank you @saidatom @dieterholvoet @alorenc for you contribution!
It will be added to the next release 1.2.42
Thanks @herved and @pcambra,
It will be included in next release 1.2.42
Testing on AI and AI Agents 1.1.x with Drupal 10.5.2 the changes make it works.
Setup to be reproduce it
- Drupal 10.5.2
- AI 1.1.x
(AI Assistant API, AI Search and AI Chatbot)
- AI Agents 1.1.x
- Action (Core module, so it just needs to be enabled)
- Key latest_version
- Search API latest_version
- Ollama Provider (ddev addon) latest_version
- Milvus VDB Provider (ddev addon) latest_version
After applying the MR into AI module the error from the next pages is gone:
/admin/config/ai/explorers/tools_explorer
/admin/config/ai/explorers/chat_generator
/admin/structure/ai_agent/add
Moving the issue to RTBC, thanks everyone involved.
Tested with https://www.drupal.org/project/ai/issues/3543112 📌 Make model id required on the OpenAiBasedProviderClientBase Active applied to AI module and everything works as expected.
The code also look good to me Marcus.
Thanks!
It looks good to me Marcus!
Thanks!
Remember that you would need to run drush updb
command once you get the MR before testing the functionality.
Regarding #35 📌 Improve AI Search Module Indexing to Handle Long-Running Chunk Embedding Processes Needs work I would try move forward a working version like it is right now, then open a follow up ticket to improve how the progress bar should looks like.
I am with you that your approach would be more descriptive for the end user, but we would need to expend some time to make this works.
And when everything is working and validated, we could also go with #33
What do you think?
I've just did a push with the fix for #36, thank you very much Scott to point this out.
Tested and everything works as expected.
See: https://www.drupal.org/project/ai/issues/3541470#comment-16239682 📌 Remove canChatStream Active
Tested and everything works as expected.
See: https://www.drupal.org/project/ai/issues/3541470#comment-16239682 📌 Remove canChatStream Active
Tested and everything works as expected.
See: https://www.drupal.org/project/ai/issues/3541470#comment-16239682 📌 Remove canChatStream Active
Tested with:
-
https://www.drupal.org/project/ai/issues/3541471
📌
Add finished reason to stream iterator
Active
-
https://www.drupal.org/project/ai/issues/3541472
🐛
Return streamed message and set tokens on normal message on the OpenAiBasedProviderClientBase
Active
-
https://www.drupal.org/project/ai/issues/3541473
📌
Add token usage to OpenAiProviderClientBase
Active
And everything works as expected.
Steps followed
1. Create a test branch from ai module including mentioned MRs
2. Install AI API Explorer module
3. Go to Chat Generation Explorer
4. Test the output using Streamed option
Evidences
Output
Logging
Thank you very much Dieter and Christian for your effort here.
It will be included in the next release 1.2.42
Thanks to report this issue @damienmckenna
I've been testing it with next configuration:
Drupal 11.2.2
AI Core 1.1.x
AI Search 1.1.x
AI Assistant Api 1.1.x
AI Agents 1.1.x
Huggingface Provider 1.0.x
Sqlite Provider 1.0.x
Search API 1.38
From Huggingface provider I have used the next models:
Chat -> Meta Llama-3-8B
Embeddings -> MxBai Embed Large v1
And I have needed to apply the next patch in Search API in order to can create the view:
https://www.drupal.org/project/search_api/issues/3531256
🐛
Cannot create Search API based views On Drupal 11
Active
I was NOT able to reproduce the error that you are describing. Maybe the problem could be the fields that you are using in Search API Index, and the filter criteria added to the view.
I am using the next fields in Search API Index:
- rendered_item
with type fulltext and main content as indexing option
- url
with type string and Contextual content as indexing option
- title
with type fulltext and contextual content as indexing option
Then in the view I am adding Fulltext search
as filter criteria, then when I perform a search query everything works as expected.
Moving this issue to Postponed until we get more info about the issue in your side.
I will take over of this issue