# 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
- 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:
# 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>
# 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
- 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
---------
Co-authored-by: aminediro <aminedirhoussi@gmail.com>
