- Until now, hybrid search was limited to modules requiring external
services, such as Weaviate/Pinecone Hybrid Search. However, I have
developed a hybrid retriever that can merge a list of retrievers using
the [Reciprocal Rank
Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf)
algorithm. This new approach, similar to Weaviate hybrid search, does
not require the initialization of any external service.
- Dependencies: No - Twitter handle: dayuanjian21687
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Stop sequences are useful if you are doing long-running completions and
need to early-out rather than running for the full max_length... not
only does this save inference cost on Replicate, it is also much faster
if you are going to truncate the output later anyway.
Other LLMs support stop sequences natively (e.g. OpenAI) but I didn't
see this for Replicate so adding this via their prediction cancel
method.
Housekeeping: I ran `make format` and `make lint`, no issues reported in
the files I touched.
I did update the replicate integration test and ran `poetry run pytest
tests/integration_tests/llms/test_replicate.py` successfully.
Finally, I am @tjaffri https://twitter.com/tjaffri for feature
announcement tweets... or if you could please tag @docugami
https://twitter.com/docugami we would really appreciate that :-)
Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
@rlancemartin
The modification includes:
* etherscanLoader
* test_etherscan
* document ipynb
I have run the test, lint, format, and spell check. I do encounter a
linting error on ipynb, I am not sure how to address that.
```
docs/extras/modules/data_connection/document_loaders/integrations/Etherscan.ipynb:55: error: Name "null" is not defined [name-defined]
docs/extras/modules/data_connection/document_loaders/integrations/Etherscan.ipynb:76: error: Name "null" is not defined [name-defined]
Found 2 errors in 1 file (checked 1 source file)
```
- Description: The Etherscan loader uses etherscan api to load
transaction histories under specific accounts on Ethereum Mainnet.
- No dependency is introduced by this PR.
- Twitter handle: glazecl
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
ChatGLM LLM integration will by default accumulate conversation
history(with_history=True) to ChatGLM backend api, which is not expected
in most cases. This PR set with_history=False by default, user should
explicitly set llm.with_history=True to turn this feature on. Related
PR: #8048#7774
---------
Co-authored-by: mlot <limpo2000@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Simple change of the Class that ContentHandler
inherits from. To create an object of type SagemakerEndpointEmbeddings,
the property content_handler must be of type EmbeddingsContentHandler
not ContentHandlerBase anymore,
- **Twitter handle:** @Juanjo_Torres11
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description:
This PR adds embeddings for LocalAI (
https://github.com/go-skynet/LocalAI ), a self-hosted OpenAI drop-in
replacement. As LocalAI can re-use OpenAI clients it is mostly following
the lines of the OpenAI embeddings, however when embedding documents, it
just uses string instead of sending tokens as sending tokens is
best-effort depending on the model being used in LocalAI. Sending tokens
is also tricky as token id's can mismatch with the model - so it's safer
to just send strings in this case.
Partly related to: https://github.com/hwchase17/langchain/issues/5256
Dependencies: No new dependencies
Twitter: @mudler_it
---------
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**PR Description:**
This pull request introduces several enhancements and new features to
the `CubeSemanticLoader`. The changes include the following:
1. Added imports for the `json` and `time` modules.
2. Added new constructor parameters: `load_dimension_values`,
`dimension_values_limit`, `dimension_values_max_retries`, and
`dimension_values_retry_delay`.
3. Updated the class documentation with descriptions for the new
constructor parameters.
4. Added a new private method `_get_dimension_values()` to retrieve
dimension values from Cube's REST API.
5. Modified the `load()` method to load dimension values for string
dimensions if `load_dimension_values` is set to `True`.
6. Updated the API endpoint in the `load()` method from the base URL to
the metadata endpoint.
7. Refactored the code to retrieve metadata from the response JSON.
8. Added the `column_member_type` field to the metadata dictionary to
indicate if a column is a measure or a dimension.
9. Added the `column_values` field to the metadata dictionary to store
the dimension values retrieved from Cube's API.
10. Modified the `page_content` construction to include the column title
and description instead of the table name, column name, data type,
title, and description.
These changes improve the functionality and flexibility of the
`CubeSemanticLoader` class by allowing the loading of dimension values
and providing more detailed metadata for each document.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Hopefully, this doesn't come across as nitpicky! That isn't the
intention. I only noticed it, because I enjoy reading the documentation
and when I hit a mental road bump it is usually due to a missing word or
something =)
@baskaryan
New HTML loader that asynchronously loader a list of urls.
New transformer using [HTML2Text](https://github.com/Alir3z4/html2text/)
for HTML to clean, easy-to-read plain ASCII text (valid Markdown).
In certain 0-shot scenarios, the existing stateful language model can
unintentionally send/accumulate the .history.
This commit adds the "with_history" option to chatglm, allowing users to
control the behavior of .history and prevent unintended accumulation.
Possible reviewers @hwchase17 @baskaryan @mlot
Refer to discussion over this thread:
https://twitter.com/wey_gu/status/1681996149543276545?s=20
I've extended the support of async API to local Qdrant mode. It is faked
but allows prototyping without spinning a container. The tests are
improved to test the in-memory case as well.
@baskaryan @rlancemartin @eyurtsev @agola11
Streaming support is useful if you are doing long-running completions or
need interactivity e.g. for chat... adding it to replicate, using a
similar pattern to other LLMs that support streaming.
Housekeeping: I ran `make format` and `make lint`, no issues reported in
the files I touched.
I did update the replicate integration test but ran into some issues,
specifically:
1. The original test was failing for me due to the model argument not
being specified... perhaps this test is not regularly run? I fixed it by
adding a call to the lightweight hello world model which should not be
burdensome for replicate infra.
2. I couldn't get the `make integration_tests` command to pass... a lot
of failures in other integration tests due to missing dependencies...
however I did make sure the particluar test file I updated does pass, by
running `poetry run pytest
tests/integration_tests/llms/test_replicate.py`
Finally, I am @tjaffri https://twitter.com/tjaffri for feature
announcement tweets... or if you could please tag @docugami
https://twitter.com/docugami we would really appreciate that :-)
Tagging model maintainers @hwchase17 @baskaryan
Thank for all the awesome work you folks are doing.
---------
Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
## Description
This PR adds a graph class and an openCypher QA chain to work with the
Amazon Neptune database.
## Dependencies
`requests` which is included in the LangChain dependencies.
## Maintainers for Review
@krlawrence
@baskaryan
### Twitter handle
pjain7
Integrating Portkey, which adds production features like caching,
tracing, tagging, retries, etc. to langchain apps.
- Dependencies: None
- Twitter handle: https://twitter.com/portkeyai
- test_portkey.py added for tests
- example notebook added in new utilities folder in modules
Also fixed a bug with OpenAIEmbeddings where headers weren't passing.
cc @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
BedrockEmbeddings does not have endpoint_url so that switching to custom
endpoint is not possible. I have access to Bedrock custom endpoint and
cannot use BedrockEmbeddings
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Golden Query is a wrapper on top of the [Golden Query
API](https://docs.golden.com/reference/query-api) which enables
programmatic access to query results on entities across Golden's
Knowledge Base. For more information about Golden API, please see the
[Golden API Getting
Started](https://docs.golden.com/reference/getting-started) page.
**Issue:** None
**Dependencies:** requests(already present in project)
**Tag maintainer:** @hinthornw
Signed-off-by: Constantin Musca <constantin.musca@gmail.com>
## Background
With the addition on email and calendar tools, LangChain is continuing
to complete its functionality to automate business processes.
## Challenge
One of the pieces of business functionality that LangChain currently
doesn't have is the ability to search for flights and travel in order to
book business travel.
## Changes
This PR implements an integration with the
[Amadeus](https://developers.amadeus.com/) travel search API for
LangChain, enabling seamless search for flights with a single
authentication process.
## Who can review?
@hinthornw
## Appendix
@tsolakoua and @minjikarin, I utilized your
[amadeus-python](https://github.com/amadeus4dev/amadeus-python) library
extensively. Given the rising popularity of LangChain and similar AI
frameworks, the convergence of libraries like amadeus-python and tools
like this one is likely. So, I wanted to keep you updated on our
progress.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
## Description
Added a doc about the [Datadog APM integration for
LangChain](https://github.com/DataDog/dd-trace-py/pull/6137).
Note that the integration is on `ddtrace`'s end and so no code is
introduced/required by this integration into the langchain library. For
that reason I've refrained from adding an example notebook (although
I've added setup instructions for enabling the integration in the doc)
as no code is technically required to enable the integration.
Tagging @baskaryan as reviewer on this PR, thank you very much!
## Dependencies
Datadog APM users will need to have `ddtrace` installed, but the
integration is on `ddtrace` end and so does not introduce any external
dependencies to the LangChain project.
Co-authored-by: Bagatur <baskaryan@gmail.com>
Work in Progress.
WIP
Not ready...
Adds Document Loader support for
[Geopandas.GeoDataFrames](https://geopandas.org/)
Example:
- [x] stub out `GeoDataFrameLoader` class
- [x] stub out integration tests
- [ ] Experiment with different geometry text representations
- [ ] Verify CRS is successfully added in metadata
- [ ] Test effectiveness of searches on geometries
- [ ] Test with different geometry types (point, line, polygon with
multi-variants).
- [ ] Add documentation
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Lance Martin <122662504+rlancemartin@users.noreply.github.com>
<!-- 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
```
** 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>
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>
- 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.
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.~
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.
- Description: Add a BM25 Retriever that do not need Elastic search
- Dependencies: rank_bm25(if it is not installed it will be install by
using pip, just like TFIDFRetriever do)
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: DayuanJian21687
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description:
Add LLM for ChatGLM-6B & ChatGLM2-6B API
Related Issue:
Will the langchain support ChatGLM? #4766
Add support for selfhost models like ChatGLM or transformer models #1780
Dependencies:
No extra library install required.
It wraps api call to a ChatGLM(2)-6B server(start with api.py), so api
endpoint is required to run.
Tag maintainer: @mlot
Any comments on this PR would be appreciated.
---------
Co-authored-by: mlot <limpo2000@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
# Support Redis Sentinel database connections
This PR adds the support to connect not only to Redis standalone servers
but High Availability Replication sets too
(https://redis.io/docs/management/sentinel/)
Redis Replica Sets have on Master allowing to write data and 2+ replicas
with read-only access to the data. The additional Redis Sentinel
instances monitor all server and reconfigure the RW-Master on the fly if
it comes unavailable.
Therefore all connections must be made through the Sentinels the query
the current master for a read-write connection. This PR adds basic
support to also allow a redis connection url specifying a Sentinel as
Redis connection.
Redis documentation and Jupyter notebook with Redis examples are updated
to mention how to connect to a redis Replica Set with Sentinels
-
Remark - i did not found test cases for Redis server connections to add
new cases here. Therefor i tests the new utility class locally with
different kind of setups to make sure different connection urls are
working as expected. But no test case here as part of this PR.
- [Xorbits](https://doc.xorbits.io/en/latest/) is an open-source
computing framework that makes it easy to scale data science and machine
learning workloads in parallel. Xorbits can leverage multi cores or GPUs
to accelerate computation on a single machine, or scale out up to
thousands of machines to support processing terabytes of data.
- This PR added support for the Xorbits agent, which allows langchain to
interact with Xorbits Pandas dataframe and Xorbits Numpy array.
- Dependencies: This change requires the Xorbits library to be installed
in order to be used.
`pip install xorbits`
- Request for review: @hinthornw
- Twitter handle: https://twitter.com/Xorbitsio
<!-- 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
-->
<!-- 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
-->
