<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: a description of the change,
- Issue: the issue # it fixes (if applicable),
- Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
- Adds integration for MLflow AI Gateway (this will be shipped in MLflow
2.5 this week).
Manual testing:
```sh
# Move to mlflow repo
cd /path/to/mlflow
# install langchain
pip install git+https://github.com/harupy/langchain.git@gateway-integration
# launch gateway service
mlflow gateway start --config-path examples/gateway/openai/config.yaml
# Then, run the examples in this PR
```
Fixed missing "content" field in azure.
Added a check for "content" in _dict (missing for azure
api=2023-07-01-preview)
@baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: VectorStoreRetriever->similarity_score_threshold with
search_type of "similarity_score_threshold" not working with the
following two minor issues,
- Issue: 1. In line 237 of `vectorstores/base.py`, "score_threshold" is
passed to `_similarity_search_with_relevance_scores` as in the kwargs,
while score_threshold is not a valid argument of this method. As a fix,
before calling `_similarity_search_with_relevance_scores`,
score_threshold is popped from kwargs. 2. In line 596 to 607 of
`vectorstores/pgvector.py`, it's checking the distance_strategy against
the string in Enum. However, self.distance_strategy will get the
property of distance_strategy from line 316, where the callable function
is passed. To solve this issue, self.distance_strategy is changed to
self._distance_strategy to avoid calling the property method.,
- Dependencies: No,
- Tag maintainer: @rlancemartin, @eyurtsev,
- Twitter handle: No
---------
Co-authored-by: Bin Wang <bin@arcanum.ai>
- Description: exposes the ResultItem DocumentAttributes as document
metadata with key 'document_attributes' and refactors
AmazonKendraRetriever by providing a ResultItem base class in order to
avoid duplicate code;
- Tag maintainer: @3coins @hupe1980 @dev2049 @baskaryan
- Twitter handle: wilsonleao
### Why?
Some use cases depend on specific document attributes returned by the
retriever in order to improve the quality of the overall completion and
adjust what will be displayed to the user. For the sake of consistency,
we need to expose the DocumentAttributes as document metadata so we are
sure that we are using the values returned by the kendra request issued
by langchain.
I would appreciate your review @3coins @hupe1980 @dev2049. Thank you in
advance!
### References
- [Amazon Kendra
DocumentAttribute](https://docs.aws.amazon.com/kendra/latest/APIReference/API_DocumentAttribute.html)
- [Amazon Kendra
DocumentAttributeValue](https://docs.aws.amazon.com/kendra/latest/APIReference/API_DocumentAttributeValue.html)
---------
Co-authored-by: Piyush Jain <piyushjain@duck.com>
- Description: check title and excerpt separately for page_content so
that if title is empty but excerpt is present, the page_content will
only contain the excerpt
- Issue: #7782
- Tag maintainer: @3coins @baskaryan
- Twitter handle: wilsonleao
- Description: It allows to use chat models that do not return token
usage
- Issue: [#7900](https://github.com/hwchase17/langchain/issues/7900)
- Dependencies: None
- Tag maintainer: @agola11 @hwchase17
- Twitter handle: @alonsosilva
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
** This should land Monday the 17th **
Chroma is upgrading from `0.3.29` to `0.4.0`. `0.4.0` is easier to
build, more durable, faster, smaller, and more extensible. This comes
with a few changes:
1. A simplified and improved client setup. Instead of having to remember
weird settings, users can just do `EphemeralClient`, `PersistentClient`
or `HttpClient` (the underlying direct `Client` implementation is also
still accessible)
2. We migrated data stores away from `duckdb` and `clickhouse`. This
changes the api for the `PersistentClient` that used to reference
`chroma_db_impl="duckdb+parquet"`. Now we simply set
`is_persistent=true`. `is_persistent` is set for you to `true` if you
use `PersistentClient`.
3. Because we migrated away from `duckdb` and `clickhouse` - this also
means that users need to migrate their data into the new layout and
schema. Chroma is committed to providing extension notification and
tooling around any schema and data migrations (for example - this PR!).
After upgrading to `0.4.0` - if users try to access their data that was
stored in the previous regime, the system will throw an `Exception` and
instruct them how to use the migration assistant to migrate their data.
The migration assitant is a pip installable CLI: `pip install
chroma_migrate`. And is runnable by calling `chroma_migrate`
-- TODO ADD here is a short video demonstrating how it works.
Please reference the readme at
[chroma-core/chroma-migrate](https://github.com/chroma-core/chroma-migrate)
to see a full write-up of our philosophy on migrations as well as more
details about this particular migration.
Please direct any users facing issues upgrading to our Discord channel
called
[#get-help](https://discord.com/channels/1073293645303795742/1129200523111841883).
We have also created a [email
listserv](https://airtable.com/shrHaErIs1j9F97BE) to notify developers
directly in the future about breaking changes.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: version check to make sure chromadb >=0.4.0 does not
throw an error, and uses the default sqlite persistence engine when the
directory is set,
- Issue: the issue #7887
For attention of
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR
- fixes the `similarity_search_by_vector` example, makes the code run
and adds the example to mirror `similarity_search`
- reverts back to chroma from faiss to remove sharp edges / create a
happy path for new developers. (1) real metadata filtering, (2) expected
functionality like `update`, `delete`, etc to serve beyond the most
trivial use cases
@hwchase17
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Replace this comment with:
- Description: Modified the code to return the document id from the
redis document search as metadata.
- Issue: the issue # it fixes retrieval of id as metadata as string
- Tag maintainer: @rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: This is an update to a previously published notebook.
Sales Agent now has access to tools, and this notebook shows how to use
a Product Knowledge base
to reduce hallucinations and act as a better sales person!
- Issue: N/A
- Dependencies: `chromadb openai tiktoken`
- Tag maintainer: @baskaryan @hinthornw
- Twitter handle: @FilipMichalsky
Moving to the latest non-preview Azure OpenAI API version=2023-05-15.
The previous 2023-03-15-preview doesn't have support, SLA etc. For
instance, OpenAI SDK has moved to this version
https://github.com/openai/openai-python/releases/tag/v0.27.7
@baskaryan
Description:
Currently, Zilliz only support dedicated clusters using a pair of
username and password for connection. Regarding serverless clusters,
they can connect to them by using API keys( [ see official note
detail](https://docs.zilliz.com/docs/manage-cluster-credentials)), so I
add API key(token) description in Zilliz docs to make it more obvious
and convenient for this group of users to better utilize Zilliz. No
changes done to code.
---------
Co-authored-by: Robin.Wang <3Jg$94sbQ@q1>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Azure GPT-4 models can't be accessed via LLM model. It's easy to miss
that and a lot of discussions about that are on the Internet. Therefore
I added a comment in Azure LLM docs that mentions that and points to
Azure Chat OpenAI docs.
@baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: This PR adds the option to retrieve scores and explanations
in the WeaviateHybridSearchRetriever. This feature improves the
usability of the retriever by allowing users to understand the scoring
logic behind the search results and further refine their search queries.
Issue: This PR is a solution to the issue #7855
Dependencies: This PR does not introduce any new dependencies.
Tag maintainer: @rlancemartin, @eyurtsev
I have included a unit test for the added feature, ensuring that it
retrieves scores and explanations correctly. I have also included an
example notebook demonstrating its use.
Here I am adding documentation for the `PromptLayerCallbackHandler`.
When we created the initial PR for the callback handler the docs were
causing issues, so we merged without the docs.
1. Add the metadata filter of documents.
2. Add the text page_content filter of documents
3. fix the bug of similarity_search_with_score
Improvement and fix bug of AwaDB
Fix the conflict https://github.com/hwchase17/langchain/pull/7840
@rlancemartin @eyurtsev Thanks!
---------
Co-authored-by: vincent <awadb.vincent@gmail.com>
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>
Still don't have good "how to's", and the guides / examples section
could be further pruned and improved, but this PR adds a couple examples
for each of the common evaluator interfaces.
- [x] Example docs for each implemented evaluator
- [x] "how to make a custom evalutor" notebook for each low level APIs
(comparison, string, agent)
- [x] Move docs to modules area
- [x] Link to reference docs for more information
- [X] Still need to finish the evaluation index page
- ~[ ] Don't have good data generation section~
- ~[ ] Don't have good how to section for other common scenarios / FAQs
like regression testing, testing over similar inputs to measure
sensitivity, etc.~
Some docstring / small nits to #6003
---------
Co-authored-by: BoazWasserman <49598618+boazwasserman@users.noreply.github.com>
Co-authored-by: HippoTerrific <49598618+HippoTerrific@users.noreply.github.com>
Co-authored-by: Or Raz <orraz1994@gmail.com>
This new version fixes the"Verified Sources" display that got broken.
Instead of displaying the full URL, it shows the title of the page the
source is from.
