Motivation, it seems that when dealing with a long context and "big"
number of relevant documents we must avoid using out of the box score
ordering from vector stores.
See: https://arxiv.org/pdf/2306.01150.pdf
So, I added an additional parameter that allows you to reorder the
retrieved documents so we can work around this performance degradation.
The relevance respect the original search score but accommodates the
lest relevant document in the middle of the context.
Extract from the paper (one image speaks 1000 tokens):
This seems to be common to all diff arquitectures. SO I think we need a
good generic way to implement this reordering and run some test in our
already running retrievers.
It could be that my approach is not the best one from the architecture
point of view, happy to have a discussion about that.
For me this was the best place to introduce the change and start
retesting diff implementations.
@rlancemartin, @eyurtsev
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Adds a new document transformer that automatically extracts metadata for
a document based on an input schema. I also moved
`document_transformers.py` to `document_transformers/__init__.py` to
group it with this new transformer - it didn't seem to cause issues in
the notebook, but let me know if I've done something wrong there.
Also had a linter issue I couldn't figure out:
```
MacBook-Pro:langchain jacoblee$ make lint
poetry run mypy .
docs/dist/conf.py: error: Duplicate module named "conf" (also at "./docs/api_reference/conf.py")
docs/dist/conf.py: note: See https://mypy.readthedocs.io/en/stable/running_mypy.html#mapping-file-paths-to-modules for more info
docs/dist/conf.py: note: Common resolutions include: a) using `--exclude` to avoid checking one of them, b) adding `__init__.py` somewhere, c) using `--explicit-package-bases` or adjusting MYPYPATH
Found 1 error in 1 file (errors prevented further checking)
make: *** [lint] Error 2
```
@rlancemartin @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Add two new document transformers that translates
documents into different languages and converts documents into q&a
format to improve vector search results. Uses OpenAI function calling
via the [doctran](https://github.com/psychic-api/doctran/tree/main)
library.
- Issue: N/A
- Dependencies: `doctran = "^0.0.5"`
- Tag maintainer: @rlancemartin @eyurtsev @hwchase17
- Twitter handle: @psychicapi or @jfan001
Notes
- Adheres to the `DocumentTransformer` abstraction set by @dev2049 in
#3182
- refactored `EmbeddingsRedundantFilter` to put it in a file under a new
`document_transformers` module
- Added basic docs for `DocumentInterrogator`, `DocumentTransformer` as
well as the existing `EmbeddingsRedundantFilter`
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
German Martin