# Description
Major PR which, among other things, introduces the possibility of easily
customizing the retrieval workflows. Workflows are based on LangGraph,
and can be customized using a [yaml configuration
file](core/tests/test_llm_endpoint.py), and adding the implementation of
the nodes logic into
[quivr_rag_langgraph.py](1a0c98437a/backend/core/quivr_core/quivr_rag_langgraph.py)
This is a first, simple implementation that will significantly evolve in
the coming weeks to enable more complex workflows (for instance, with
conditional nodes). We also plan to adopt a similar approach for the
ingestion part, i.e. to enable user to easily customize the ingestion
pipeline.
Closes CORE-195, CORE-203, CORE-204
## Checklist before requesting a review
Please delete options that are not relevant.
- [X] My code follows the style guidelines of this project
- [X] I have performed a self-review of my code
- [X] I have commented hard-to-understand areas
- [X] I have ideally added tests that prove my fix is effective or that
my feature works
- [X] New and existing unit tests pass locally with my changes
- [X] Any dependent changes have been merged
## Screenshots (if appropriate):
# Description
- Save and load brain to disk:
```python
async def main():
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt") as temp_file:
temp_file.write("Gold is a liquid of blue-like colour.")
temp_file.flush()
brain = await Brain.afrom_files(name="test_brain", file_paths=[temp_file.name])
save_path = await brain.save("/home/amine/.local/quivr")
brain_loaded = Brain.load(save_path)
brain_loaded.print_info()
```
# TODO:
- Loading all chat history
- Loading from other vector stores, PG for example can be great ...
# Description
Using LangGraph instead of LangChain LCEL to build and run the RAG
pipeline, as LangGraph enables greater flexibility and an easier
maintainability of complex (agentic) pipelines
Completes CORE-175
## Checklist before requesting a review
Please delete options that are not relevant.
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [x] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged
## Screenshots (if appropriate):
---------
Co-authored-by: Stan Girard <girard.stanislas@gmail.com>
# Description
- Moved `quivr-api` parser to `quivr_core.processor.implementations` by
Dynamically creating classes on the fly that inherit from
`ProcessorBase`
- Defined a priority based based system to automagically register the
"important" processor that we can import at runtime
- Wrote extensive tests for the registry
- Added support file extensions
### Next steps
- Find a way to have correct LSP autocomplete on the dynamically
generated processors
- Test that processor are imported correctly based on the installed
packages in environment ( using tox) ?
# Description
- Created registry processor logic for automagically adding processors
to quivr_core based Entrypoints
- Added a langchain_community free `SimpleTxtParser` for the quivr_core
base package
- Added tests
- Added brain_info
- Enriched parsed documents metadata based on quivr_file metadata
used Rich for `Brain.print_info()` to get a better output:
