# Description
`quivr-core`
- Generate a fixture to simulate a model with function calling
- Monkey patch `QuivrQARAG` stream
- Tests function
`quivr-api`
- Fixes empty API responses
- Fixes non function calling models
---------
Co-authored-by: Stan Girard <girard.stanislas@gmail.com>
This pull request updates the versions of quivr-core and chainlit in the
requirements.txt file. The quivr-core version is changed from 0.0.8 to
0.0.8[base], and the chainlit version is changed from 1.1.306 to
1.1.306.
The commit adds a new Quivr chatbot example to the repository. The
example demonstrates how to create a simple chatbot using Quivr and
Chainlit. Users can upload a text file and ask questions about its
content. The commit includes the necessary files, installation
instructions, and usage guidelines.
# Description
- Defined quivr-core `ChatHistory`
- `ChatHistory` can be iterated over in tuples of
`HumanMessage,AIMessage`
- Brain appends to the chatHistory once response is received
- Brain holds a dict of chats and defines the default chat (TODO: define
a system of selecting the chats)
- Wrote test
- Updated `QuivrQARAG` to use `ChatHistory` as input
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
This commit adds a new GitHub Actions workflow file
`backend-core-tests.yml` to the repository. This workflow is triggered
on push and pull request events, specifically for changes made to the
`backend/core` directory. The workflow runs tests for the backend/core
module using a Tika server as a service. It checks the health of the
Tika server before running the tests. The workflow sets up Python,
installs dependencies using Poetry, and runs the tests using pytest.
This commit is necessary to automate the testing process for the
backend/core module and ensure that the tests are run consistently and
reliably.
Co-authored-by: aminediro <aminedirhoussi@gmail.com>
# Description
- Introduce `LLMEndpoint` class: wrapper around a `BaseChatLLM` to load
OpenAI compatible models
- Add `brain.search(...)` function to retrieve
- Test with test-coverage:
- Added ability to load brain `from langchain.Document`
- Configured mypy and poetry lock in `.pre-commit.yaml`
# Test coverage
![image](https://github.com/QuivrHQ/quivr/assets/14312141/629ede66-146e-400f-b40b-8c22a9258a47)
---------
Co-authored-by: aminediro <aminedirhoussi@gmail.com>
This commit updates the GitHub Actions workflows for the backend services (quivr-com-backend, quivr-com, raise-frontend, raise, theodo-backend, and theodo-frontend) to trigger on tag pushes instead of branch pushes. This change allows for more controlled deployments and ensures that only tagged versions are deployed to the respective environments.
This commit adds the release-please-core workflow and configuration files for the python package in the backend. The release-please workflow is triggered on push to the main branch and on manual workflow dispatch. It sets up Python, installs Poetry, configures Poetry, and runs release-please for the backend/core package. The release-please configuration file specifies the release type, package name, bump patch for minor pre-major, changelog notes type, include v in tag, tag separator, and component.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
* feat(Unplug): Adds new basic headless llm
* feat(Unplug): adds chatting without brain option when no streaming
* feat(Unplug): adds chatting without brain option when streaming