…tch]: import models from community
ran
```bash
git grep -l 'from langchain\.chat_models' | xargs -L 1 sed -i '' "s/from\ langchain\.chat_models/from\ langchain_community.chat_models/g"
git grep -l 'from langchain\.llms' | xargs -L 1 sed -i '' "s/from\ langchain\.llms/from\ langchain_community.llms/g"
git grep -l 'from langchain\.embeddings' | xargs -L 1 sed -i '' "s/from\ langchain\.embeddings/from\ langchain_community.embeddings/g"
git checkout master libs/langchain/tests/unit_tests/llms
git checkout master libs/langchain/tests/unit_tests/chat_models
git checkout master libs/langchain/tests/unit_tests/embeddings/test_imports.py
make format
cd libs/langchain; make format
cd ../experimental; make format
cd ../core; make format
```
- **Description:** SingleFileFacebookMessengerChatLoader did not handle
the case for when messages had stickers and/or photos so fixed that.
- **Issue:** #15356
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:** updates/enhancements to IBM
[watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider
(prompt tuned models and prompt templates deployments support)
- **Dependencies:**
[ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),
- **Tag maintainer:** : @hwchase17 , @eyurtsev , @baskaryan
- **Twitter handle:** details in comment below.
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally. ✅
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
The fix#14221 has broken default gitlab url which is forcing the users
to specify GITLAB_URL for default one. With this fix if GITLAB_URL is
not set, the default gitlab url will be taken.
- **Description:** Add the GITHUB URL instead of None
- **Issue:** the issue #14221 has broken the default github URL
- **Dependencies:** None
- **Tag maintainer:** @hwchase17
- **Twitter handle:** manjunath_shiva
- **Description:** This PR adds `api_base` to `_client_params` in the
`chat_model` of LiteLLM to ensure it's included in API calls.
Previously, `api_base` was set on the client but was not included in the
parameters passed to the completion function. This change ensures that
`api_base` is correctly passed to all API calls.
- **Issue:** #14338
- **Tag maintainer:** @hwchase17 @agola11
- **Twitter handle:** @LMS_David_RS
<!-- Thank you for contributing to LangChain!
Replace this entire 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!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
This change addresses the issue where DashScopeEmbeddingAPI limits
requests to 25 lines of data, and DashScopeEmbeddings did not handle
cases with more than 25 lines, leading to errors. I have implemented a
fix to manage data exceeding this limit efficiently.
---------
Co-authored-by: xuxiang <xuxiang@aliyun.com>
<!-- Thank you for contributing to LangChain!
Replace this entire 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!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- **Description:** Using PGVector vector store, it was only possible to
filter for values equals, in or not in metadata. Extended this feature
to work with the following keywords : IN, NIN, BETWEEN, GT, LT, NE, EQ,
LIKE, CONTAINS, OR, AND
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:**
- This PR introduces a significant enhancement to the LangChain project
by integrating a new chat model powered by the third-generation base
large model, ChatGLM3, via the zhipuai API.
- This advanced model supports functionalities like function calls, code
interpretation, and intelligent Agent capabilities.
- The additions include the chat model itself, comprehensive
documentation in the form of Python notebook docs, and thorough testing
with both unit and integrated tests.
- **Dependencies:** This update relies on the ZhipuAI package as a key
dependency.
- **Twitter handle:** If this PR receives spotlight attention, we would
be honored to receive a mention for our integration of the advanced
ChatGLM3 model via the ZhipuAI API. Kindly tag us at @kaiwu.
To ensure quality and standards, we have performed extensive linting and
testing. Commands such as make format, make lint, and make test have
been run from the root of the modified package to ensure compliance with
LangChain's coding standards.
TO DO: Continue refining and enhancing both the unit tests and
integrated tests.
---------
Co-authored-by: jing <jingguo92@gmail.com>
Co-authored-by: hyy1987 <779003812@qq.com>
Co-authored-by: jianchuanqi <qijianchuan@hotmail.com>
Co-authored-by: lirq <whuclarence@gmail.com>
Co-authored-by: whucalrence <81530213+whucalrence@users.noreply.github.com>
Co-authored-by: Jing Guo <48378126+JaneCrystall@users.noreply.github.com>
Description: Volcano Ark is an enterprise-grade large-model service
platform for developers, providing a full range of functions and
services such as model training, inference, evaluation, fine-tuning. You
can visit its homepage at https://www.volcengine.com/docs/82379/1099455
for details. This change could help developers use the platform for
embedding.
Issue: None
Dependencies: volcengine
Tag maintainer: @baskaryan
Twitter handle: @hinnnnnnnnnnnns
---------
Co-authored-by: lujingxuansc <lujingxuansc@bytedance.com>
**Description:** the MWDumpLoader implementation currently does not
support the lazy_load method, and the files are usually very large. We
are proposing refactoring the load function, extracting two private
functions with the functionality of loading the dump file and parsing a
single page, to reuse the code in the lazy_load implementation.
**Description:**
This PR adds the `**kwargs` parameter to six calls in the `chroma.py`
package. All functions already were able to receive `kwargs` but they
were discarded before.
**Issue:**
When passing `kwargs` to functions in the `chroma.py` package they are
being ignored.
For example:
```
chroma_instance.similarity_search_with_score(
query,
k=100,
include=["metadatas", "documents", "distances", "embeddings"], # this parameter gets ignored
)
```
The `include` parameter does not get passed on to the next function and
does not have any effect.
**Dependencies:**
None
- **Description:**
- support custom kwargs in object initialization. For instantance, QPS
differs from multiple object(chat/completion/embedding with diverse
models), for which global env is not a good choice for configuration.
- **Issue:** no
- **Dependencies:** no
- **Twitter handle:** no
@baskaryan PTAL
- Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor
needs manual handling of context vars
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **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!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
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. It lives in
`docs/docs/integrations` directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- **Description:** fixes and upgrades for the Tongyi LLM and ChatTongyi
Model
- Fixed typos; it should be `Tongyi`, not `OpenAI`.
- Fixed a bug in `stream_generate_with_retry`; it's a real stream
generator now.
- Fixed a bug in `validate_environment`; the `dashscope_api_key` should
be properly handled when set by environment variables or initialization
parameters.
- Changed the `dashscope` response to incremental output by setting the
parameter `incremental_output`, which eliminates the need for the
prefix-removal trick.
- Removed some unused parameters, like `n`, `prefix_messages`.
- Added `_stream` method.
- Added async methods support, such as `_astream`, `_agenerate`,
`_abatch`.
- **Dependencies:** No new dependencies.
- **Tag maintainer:** @hwchase17
> PS: Some may be confused about the terms `dashscope`, `tongyi`, and
`Qwen`:
> - `dashscope`: A platform to deploy LLMs and provide APIs to invoke
the LLM.
> - `tongyi`: A brand name or overall term about Alibaba Cloud's LLM/AI.
> - `Qwen`: An LLM that is open-sourced and deployed in `dashscope`.
>
> We use the `dashscope` SDK to interact with the `tongyi`-`Qwen` LLM.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
While using `chain.batch`, the default implementation uses a
`ThreadPoolExecutor` and run the chains in separate threads. An issue
with this approach is that that [the token counting
callback](https://python.langchain.com/docs/modules/callbacks/token_counting)
fails to work as a consequence of the context not being propagated
between threads. This PR adds context propagation to the new threads and
adds some thread synchronization in the OpenAI callback. With this
change, the token counting callback works as intended.
Having the context propagation change would be highly beneficial for
those implementing custom callbacks for similar functionalities as well.
---------
Co-authored-by: Nuno Campos <nuno@langchain.dev>
- **Description:** The Github error prompt is confused because of JWT
enctrypt to somebody not familiar with Github connection method. This PR
is to add some useful error prompt to help users troubleshooting.
- **Issue:**
https://github.com/langchain-ai/langchain/issues/14550#issuecomment-1867445049
- **Dependencies:** None,
- **Twitter handle:** None
**Description:**
Adding async methods to booth OllamaLLM and ChatOllama to enable async
streaming and async .on_llm_new_token callbacks.
**Issue:**
ChatOllama is not working in combination with an AsyncCallbackManager
because the .on_llm_new_token method is not awaited.
- Added ensure_ascii property to ElasticsearchChatMessageHistory
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **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!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
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. It lives in
`docs/docs/integrations` directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
---------
Co-authored-by: Ivan Chetverikov <ivan.chetverikov@raftds.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
**Description**: The parameter chunk_type was being hard coded to
"extractive_answers", so that when "snippet" was being passed, it was
being ignored. This change simply doesn't do that.
Added the call function get_summaries_as_docs inside of Arxivloader
- **Description:** Added a function that returns the documents from
get_summaries_as_docs, as the call signature is present in the parent
file but never used from Arxivloader, this can be used from Arxivloader
itself just like .load() as both the signatures are same.
- **Issue:** Reduces time to load papers as no pdf is processed only
metadata is pulled from Arxiv allowing users for faster load times on
bulk loads. Users can then choose one or more paper and use ID directly
with .load() to load pdf thereby loading all the contents of the paper.
- **Description:** `tools.gmail.send_message` implements a
`SendMessageSchema` that is not used anywhere. `GmailSendMessage` also
does not have an `args_schema` attribute (this led to issues when
invoking the tool with an OpenAI functions agent, at least for me). Here
we add the missing attribute and a minimal test for the tool.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** N/A
---------
Co-authored-by: Chester Curme <chestercurme@microsoft.com>
- **Description:** In response to user feedback, this PR refactors the
Baseten integration with updated model endpoints, as well as updates
relevant documentation. This PR has been tested by end users in
production and works as expected.
- **Issue:** N/A
- **Dependencies:** This PR actually removes the dependency on the
`baseten` package!
- **Twitter handle:** https://twitter.com/basetenco
# Description
This PR adds the ability to pass a `botocore.config.Config` instance to
the boto3 client instantiated by the Bedrock LLM.
Currently, the Bedrock LLM doesn't support a way to pass a Config, which
means that some settings (e.g., timeouts and retry configuration)
require instantiating a new boto3 client with a Config and then
replacing the LLM's client:
```python
llm = Bedrock(
region_name='us-west-2',
model_id="anthropic.claude-v2",
model_kwargs={'max_tokens_to_sample': 4096, 'temperature': 0},
)
llm.client = boto_client('bedrock-runtime', region_name='us-west-2', config=Config({'read_timeout': 300}))
```
# Issue
N/A
# Dependencies
N/A
