- 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>
Improve documentation for a central use-case, qa / chat over documents.
This will be merged as an update to `index.mdx`
[here](https://python.langchain.com/docs/use_cases/question_answering/).
Testing w/ local Docusaurus server:
```
From `docs` directory:
mkdir _dist
cp -r {docs_skeleton,snippets} _dist
cp -r extras/* _dist/docs_skeleton/docs
cd _dist/docs_skeleton
yarn install
yarn start
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
updated `tutorials.mdx`:
- added a link to new `Deeplearning AI` course on LangChain
- added links to other tutorial videos
- fixed format
@baskaryan, @hwchase17
added tutorials.mdx; updated youtube.mdx
Rationale: the Tutorials section in the documentation is top-priority.
(for example, https://pytorch.org/docs/stable/index.html) Not every
project has resources to make tutorials. We have such a privilege.
Community experts created several tutorials on YouTube. But the tutorial
links are now hidden on the YouTube page and not easily discovered by
first-time visitors.
- Added new videos and tutorials that were created since the last
update.
- Made some reprioritization between videos on the base of the view
numbers.
#### Who can review?
- @hwchase17
- @dev2049
This PR introduces a new Mendable UI tailored to a better search
experience.
We're more closely integrating our traditional search with our AI
generation.
With this change, you won't have to tab back and forth between the
mendable bot and the keyword search. Both types of search are handled in
the same bar. This should make the docs easier to navigate. while still
letting users get code generations or AI-summarized answers if they so
wish. Also, it should reduce the cost.
Would love to hear your feedback :)
Cc: @dev2049 @hwchase17
**Description**:
The JSON Lines format is used by some services such as OpenAI and
HuggingFace. It's also a convenient alternative to CSV.
This PR adds JSON Lines support to `JSONLoader` and also updates related
tests.
**Tag maintainer**: @rlancemartin, @eyurtsev.
PS I was not able to build docs locally so didn't update related
section.
# Add caching to BaseChatModel
Fixes#1644
(Sidenote: While testing, I noticed we have multiple implementations of
Fake LLMs, used for testing. I consolidated them.)
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
Models
- @hwchase17
- @agola11
Twitter: [@UmerHAdil](https://twitter.com/@UmerHAdil) | Discord:
RicChilligerDude#7589
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
#### Fix
Added the mention of "store" amongst the tasks that the data connection
module can perform aside from the existing 3 (load, transform and
query). Particularly, this implies the generation of embeddings vectors
and the creation of vector stores.
skip building preview of docs for anything branch that doesn't start
with `__docs__`. will eventually update to look at code diff directories
but patching for now
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.
Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.
After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
<!-- Remove if not applicable -->
Fixes #
links to prompt templates and example selectors on the
[Prompts](https://python.langchain.com/docs/modules/model_io/prompts/)
page are invalid.
#### Before submitting
Just a small note that I tried to run `make docs_clean` and other
related commands before PR written
[here](https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md#build-documentation-locally),
it gives me an error:
```bash
langchain % make docs_clean
Traceback (most recent call last):
File "/Users/masafumi/Downloads/langchain/.venv/bin/make", line 5, in <module>
from scripts.proto import main
ModuleNotFoundError: No module named 'scripts'
make: *** [docs_clean] Error 1
# Poetry (version 1.5.1)
# Python 3.9.13
```
I couldn't figure out how to fix this, so I didn't run those command.
But links should work.
#### Who can review?
Tag maintainers/contributors who might be interested:
@hwchase17
Similar issue #6323
Co-authored-by: masafumimori <m.masafumimori@outlook.com>
Jason Fan