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.

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

Fix issue when using Fastembed #532

Merged
merged 9 commits into from
Oct 30, 2023

Conversation

valentimarco
Copy link
Collaborator

Description

Fix a issue when using fastembed as embedder for the core which occurs in the initialization of the model, with a 307 http code that didn't follow the redirect of the endpoint

Type of change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist:

  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas

core/Dockerfile Outdated Show resolved Hide resolved
This reverts commit f7a6138, reversing
changes made to 3756f0c.
@pieroit pieroit merged commit 311ba12 into cheshire-cat-ai:develop Oct 30, 2023
1 check passed
pieroit added a commit that referenced this pull request Nov 2, 2023
* Fix plugin settings loading

* Add `settings_model` function to get the plugin settings model

* Validating plugin settings before saving them

* Fix `example` deprecation warning

* Support Ollama

* added user_ids

* Update cheshire_cat.py

* Update websocket.py

* Update websocket.py

* Update websocket.py

* Update websocket.py

* Update websocket.py

* updated tests

* Moved path methods in utils.py and added deprecation warning for plugins

* Removed  get_test_plugin_path

* Plugin folder as MadHatter object attribute

* Mock `cat.utils.get_plugin_path()`

* Get the plugin path with utils

* Removed unnecessary modules

* fix shared working memory overwritten each messages

* Refactoring

* Support Fastembed

* fixed coroutine error

* Update utils.py

* added GET conversation history

* fixed endpoint

* added user_id in header

* Update headers.py

* fixed tests

* update working memory, callback and websocket endpoint to handle notification on multiple users

* Update plugin.py

* Update plugin.py

* Add utility to get the path of the current plugin

* cat as singleton

* issue way

* fixed singleton

* fix tests for iuser ws messages and memory recall

* cat as singleton ready to go

* Update auth_static.py

* Update test_memory_by_user.py

* hotfix plugin loader

* Fix hooks before_cat_recall inverted default

Default configs passed to hooks are inverted, fixed

* FIX: docker build

- Dockerfile: COPY whole cat folder in the resulting image
- github actions for multiplatform build

* Update embedder.py

* changed default embedder for fastembedding

* changed default embedder for sentence-transformers

* Fix issue when using Fastembed  (#532)

* Update Dockerfile

* Fixed bug with 307 http code

* Revert "Merge branch 'cheshire-cat-ai:main' into embedder"

This reverts commit f7a6138, reversing
changes made to 3756f0c.

---------

Co-authored-by: Piero Savastano <[email protected]>

* Bump qdrant container

* version 1.3

---------

Co-authored-by: Nicola Procopio <[email protected]>
Co-authored-by: Emanuele Morrone <[email protected]>
Co-authored-by: valentimarco <[email protected]>
Co-authored-by: Dany <[email protected]>
Co-authored-by: Nicorb <[email protected]>
Co-authored-by: Riccardo Albero <[email protected]>
Co-authored-by: Nicola <[email protected]>
Co-authored-by: Samuele Barzaghi <[email protected]>
Co-authored-by: Adelina G <[email protected]>
@valentimarco valentimarco deleted the embedder branch November 16, 2023 00:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants