**Description:** [IPEX-LLM](https://github.com/intel-analytics/ipex-llm)
is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local
PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low
latency. This PR adds Intel GPU support to `ipex-llm` llm integration.
**Dependencies:** `ipex-llm`
**Contribution maintainer**: @ivy-lv11 @Oscilloscope98
**tests and docs**:
- Add: langchain/docs/docs/integrations/llms/ipex_llm_gpu.ipynb
- Update: langchain/docs/docs/integrations/llms/ipex_llm_gpu.ipynb
- Update: langchain/libs/community/tests/llms/test_ipex_llm.py
---------
Co-authored-by: ivy-lv11 <zhicunlv@gmail.com>
- **Description:**
Improve llamacpp embedding class by adding the `device` parameter so it
can be passed to the model and used with `gpu`, `cpu` or Apple metal
(`mps`).
Improve performance by making use of the bulk client api to compute
embeddings in batches.
- **Dependencies:** none
- **Tag maintainer:**
@hwchase17
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:**
Starting from Neo4j 5.23 (22 August 2024), with vector-2.0 indexes,
`vector.dimensions` is not required to be set, which will cause it the
key not exist error in index config if it's not set.
Since the existence of vector.dimensions will only ensure additional
checks, this commit turns embedding dimension check optional, and only
do checks when it exists (not None).
https://neo4j.com/release-notes/database/neo4j-5/
**Twitter handle:** @HollowM186
Signed-off-by: Hollow Man <hollowman@opensuse.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [x] **Add tests and docs**: 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.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
## Description
- Updates the self-query retriever factory to check for the new Qdrant
vector store class. i.e. `langchain_qdrant.QdrantVectorstore`.
- Deprecates `QdrantSparseVectorRetriever`, since the vector store
implementation natively supports it now.
Resolves#25798
- **Description:** When useing LLM integration moonshot,it's occurring
error "'Moonshot' object has no attribute '_client'",it's because of the
"_client" that is private in pydantic v1.0 so that we can't use it.I
turn "_client" into "client" , the error to be resolved!
- **Issue:** the issue #24390
- **Dependencies:** none
- **Twitter handle:** @Rainsubtime
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Co-authored-by: Cyue <Cyue_work2001@163.com>
- [x] **PR title - community: add neo4j query constructor for self
query**
- [x] **PR message**
- **Description:** adding a Neo4jTranslator so that the Neo4j vector
database can use SelfQueryRetriever
- **Issue:** this issue had been raised before in #19748
- **Dependencies:** none.
- **Twitter handle:** @moyi_dang
- p.s. I have not added the query constructor in BUILTIN_TRANSLATORS in
this PR, I want to make changes to only one package at a time.
- [x] **Add tests and docs**: 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.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- [ ] **PR title**: community: add tests for ChatOctoAI
- [ ] **PR message**:
Description: Added unit tests for the ChatOctoAI class in the community
package to ensure proper validation and default values. These tests
verify the correct initialization of fields, the handling of missing
required parameters, and the proper setting of aliases.
Issue: N/A
Dependencies: None
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
Thank you for contributing to LangChain!
community:premai[patch]: standardize init args
- updated `temperature` with Pydantic Field, updated the unit test.
- updated `max_tokens` with Pydantic Field, updated the unit test.
- updated `max_retries` with Pydantic Field, updated the unit test.
Related to #20085
---------
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Description: Moves yield to after callback for _astream for gigachat in
the community package
Issue: #16913
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- [x] **PR title**: "community: Patch enable to use Amazon OpenSearch
Serverless for Semantic Cache store"
- [x] **PR message**:
- **Description:** OpenSearchSemanticCache class support Amazon
OpenSearch Serverless for Semantic Cache store, it's only required to
pass auth(http_auth) parameter to initializer
- **Dependencies:** none
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Jinoos Lee <jinoos@amazon.com>
it fixes two issues:
### YGPTs are broken #25575
```
File ....conda/lib/python3.11/site-packages/langchain_community/embeddings/yandex.py:211, in _make_request(self, texts, **kwargs)
..
--> 211 res = stub.TextEmbedding(request, metadata=self._grpc_metadata) # type: ignore[attr-defined]
AttributeError: 'YandexGPTEmbeddings' object has no attribute '_grpc_metadata'
```
My gut feeling that #23841 is the cause.
I have to drop leading underscore from `_grpc_metadata` for quickfix,
but I just don't know how to do it _pydantic_ enough.
### minor issue:
if we use `api_key`, which is not the best practice the code fails with
```
File ~/git/...../python3.11/site-packages/langchain_community/embeddings/yandex.py:119, in YandexGPTEmbeddings.validate_environment(cls, values)
...
AttributeError: 'tuple' object has no attribute 'append'
```
- Added new integration test. But it requires YGPT env available and
active account. I don't know how int tests dis\enabled in CI.
- added small unit tests with mocks. Should be fine.
---------
Co-authored-by: mikhail-khludnev <mikhail_khludnev@rntgroup.com>
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
Support passing extra params when executing UC functions:
The params should be a dictionary with key EXECUTE_FUNCTION_ARG_NAME,
the assumption is that the function itself doesn't use such variable
name (starting and ending with double underscores), and if it does we
raise Exception.
If invalid params passing to the execute_statement, we raise Exception
as well.
- [x] **Add tests and docs**: 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.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Signed-off-by: Serena Ruan <serena.rxy@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Thank you for contributing to LangChain!
- [ ] **PR title**: "community: optimize xinference llm import"
- [ ] **PR message**:
- **Description:** from xinferece_client import RESTfulClient when there
is no importing xinference.
- **Dependencies:** xinferece_client
- **Why do so:** the total xinference(pip install xinference[all]) is
too heavy for installing, let alone it is useless for langchain user
except RESTfulClient. The modification has maintained consistency with
the xinference embeddings
[embeddings/xinference](../blob/master/libs/community/langchain_community/embeddings/xinference.py#L89).
**Description:**
Adds the 'score' returned by Pinecone to the
`PineconeHybridSearchRetriever` list of returned Documents.
There is currently no way to return the score when using Pinecone hybrid
search, so in this PR I include it by default.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
### Description
adds an init method to ChatDeepInfra to set the model_name attribute
accordings to the argument
### Issue
currently, the model_name specified by the user during initialization of
the ChatDeepInfra class is never set. Therefore, it always chooses the
default model (meta-llama/Llama-2-70b-chat-hf, however probably since
this is deprecated it always uses meta-llama/Llama-3-70b-Instruct). We
stumbled across this issue and fixed it as proposed in this pull
request. Feel free to change the fix according to your coding guidelines
and style, this is just a proposal and we want to draw attention to this
problem.
### Dependencies
no additional dependencies required
Feel free to contact me or @timo282 and @finitearth if you have any
questions.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description:** Make the hyperlink only appear once in the
extract_hyperlinks tool output. (for some websites output contains
meaningless '#' hyperlinks multiple times which will extend the tokens
of context window without any advantage)
**Issue:** None
**Dependencies:** None
Added Azure Search Access Token Authentication instead of API KEY auth.
Fixes Issue: https://github.com/langchain-ai/langchain/issues/24263
Dependencies: None
Twitter: @levalencia
@baskaryan
Could you please review? First time creating a PR that fixes some code.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This addresses the issue mentioned in #25702
I have updated the endpoint used in validating the endpoint API type in
the AzureMLBaseEndpoint class from `/v1/completions` to `/completions`
and `/v1/chat/completions` to `/chat/completions`.
Co-authored-by: = <=>
- **Description:** Added langchain version while calling discover API
during both ingestion and retrieval
- **Issue:** NA
- **Dependencies:** NA
- **Tests:** NA
- **Docs** NA
---------
Co-authored-by: dristy.cd <dristy@clouddefense.io>
- **Description:** Updating source path and file path in Pebblo safe
loader for SharePoint apps during loading
- **Issue:** NA
- **Dependencies:** NA
- **Tests:** NA
- **Docs** NA
---------
Co-authored-by: dristy.cd <dristy@clouddefense.io>
- **PR message**: **Fix URL construction in newer Python versions**
- **Description:**
- Update the URL construction logic to use the .value attribute for
Routes enum members.
- This adjustment resolves an issue where the code worked correctly in
Python 3.9 but failed in Python 3.11.
- Clean up unused routes.
- **Issue:** NA
- **Dependencies:** NA
This PR introduces adjustments to ensure compatibility with the recently
released preview version of [TiDB Serverless Vector
Search](https://tidb.cloud/ai), aiming to prevent user confusion.
- TiDB Vector now supports vector indexing with cosine and l2 distance
strategies, although inner_product remains unsupported.
- Changing the distance strategy is currently not supported, so the test
cased should be adjusted.
Issue: the `service` optional parameter was mentioned but not used.
Fix: added this parameter.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
## Description
There is a bug in the concatenation of embeddings obtained from MLflow
that does not conform to the type hint requested by the function.
``` python
def _query(self, texts: List[str]) -> List[List[float]]:
```
It is logical to expect a **List[List[float]]** for a **List[str]**.
However, the append method encapsulates the response in a global List.
To avoid this, the extend method should be used, which will add the
embeddings of all strings at the same list level.
## Testing
I have tried using OpenAI-ADA to obtain the embeddings, and the result
of executing this snippet is as follows:
``` python
embeds = await MlflowAIGatewayEmbeddings().aembed_documents(texts=["hi", "how are you?"])
print(embeds)
```
``` python
[[[-0.03512698, -0.020624293, -0.015343423, ...], [-0.021260535, -0.011461929, -0.00033121882, ...]]]
```
When in reality, the expected result should be:
``` python
[[-0.03512698, -0.020624293, -0.015343423, ...], [-0.021260535, -0.011461929, -0.00033121882, ...]]
```
The above result complies with the expected type hint:
**List[List[float]]** . As I mentioned, we can achieve that by using the
extend method instead of the append method.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
Description: Simply pass kwargs to allow arguments like "where" to be
propagated
Issue: Previously, db.delete(where={}) wouldn't work for chroma
vectorstores
Dependencies: N/A
Twitter handle: N/A
- [x] **Add tests and docs**: 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.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
Description: Send both the query and query_embedding to the Databricks
index for hybrid search.
Issue: When using hybrid search with non-Databricks managed embedding we
currently don't pass both the embedding and query_text to the index.
Hybrid search requires both of these. This change fixes this issue for
both `similarity_search` and `similarity_search_by_vector`.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
# Issue
As of late July, Perplexity [no longer supports Llama 3
models](https://docs.perplexity.ai/changelog/introducing-new-and-improved-sonar-models).
# Description
This PR updates the default model and doc examples to reflect their
latest supported model. (Mostly updating the same places changed by
#23723.)
# Twitter handle
`@acompa_` on behalf of the team at Not Diamond. Check us out
[here](https://notdiamond.ai).
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
