This is a PR that adds a dangerous load parameter to force users to opt in to use pickle.
This is a PR that's meant to raise user awareness that the pickling module is involved.
- **Description:** Databricks SerDe uses cloudpickle instead of pickle
when serializing a user-defined function transform_input_fn since pickle
does not support functions defined in `__main__`, and cloudpickle
supports this.
- **Dependencies:** cloudpickle>=2.0.0
Added a unit test.
* **Description:** adds `LlamafileEmbeddings` class implementation for
generating embeddings using
[llamafile](https://github.com/Mozilla-Ocho/llamafile)-based models.
Includes related unit tests and notebook showing example usage.
* **Issue:** N/A
* **Dependencies:** N/A
This PR makes `cohere_api_key` in `llms/cohere` a SecretStr, so that the
API Key is not leaked when `Cohere.cohere_api_key` is represented as a
string.
---------
Signed-off-by: Arun <arun@arun.blog>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- **Description**:
[`bigdl-llm`](https://github.com/intel-analytics/BigDL) is a library for
running LLM on Intel XPU (from Laptop to GPU to Cloud) using
INT4/FP4/INT8/FP8 with very low latency (for any PyTorch model). This PR
adds bigdl-llm integrations to langchain.
- **Issue**: NA
- **Dependencies**: `bigdl-llm` library
- **Contribution maintainer**: @shane-huang
Examples added:
- docs/docs/integrations/llms/bigdl.ipynb
**Description:** Llama Guard is deprecated from Anyscale public
endpoint.
**Issue:** Change the default model. and remove the limitation of only
use Llama Guard with Anyscale LLMs
Anyscale LLM can also works with all other Chat model hosted on
Anyscale.
Also added `async_client` for Anyscale LLM
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:** fix SparkLLM error
- **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!
- OpenLLM was using outdated method to get the final text output from
openllm client invocation which was raising the error. Therefore
corrected that.
- OpenLLM `_identifying_params` was getting the openllm's client
configuration using outdated attributes which was raising error.
- Updated the docstring for OpenLLM.
- Added timeout parameter to be passed to underlying openllm client.
1. integrate with
[`Yuan2.0`](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/README-EN.md)
2. update `langchain.llms`
3. add a new doc for [Yuan2.0
integration](docs/docs/integrations/llms/yuan2.ipynb)
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Fixes a type annotation issue in the definition of
BedrockBase. This issue was that the annotation for the `config`
attribute includes a ForwardRef to `botocore.client.Config` which is
only imported when `TYPE_CHECKING`. This can cause pydantic to raise an
error like `pydantic.errors.ConfigError: field "config" not yet prepared
so type is still a ForwardRef, ...`.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** `@__nat_n__`
- **Description:**
[AS-IS] When dealing with a yaml file, the extension must be .yaml.
[TO-BE] In the absence of extension length constraints in the OS, the
extension of the YAML file is yaml, but control over the yml extension
must still be made.
It's as if it's an error because it's a .jpg extension in jpeg support.
- **Issue:** -
- **Dependencies:**
no dependencies required for this change,
**Description:** Invoke callback prior to yielding token in stream
method for watsonx.
**Issue:** [Callback for on_llm_new_token should be invoked before the
token is yielded by the model
#16913](https://github.com/langchain-ai/langchain/issues/16913)
Co-authored-by: Robby <h0rv@users.noreply.github.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:**
1. Modify LLMs/Anyscale to work with OAI v1
2. Get rid of openai_ prefixed variables in Chat_model/ChatAnyscale
3. Modify `anyscale_api_base` to `anyscale_base_url` to follow OAI name
convention (reverted)
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR enables changing the behaviour of huggingface pipeline between
different calls. For example, before this PR there's no way of changing
maximum generation length between different invocations of the chain.
This is desirable in cases, such as when we want to scale the maximum
output size depending on a dynamic prompt size.
Usage example:
```python
from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_id = "gpt2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
hf = HuggingFacePipeline(pipeline=pipe)
hf("Say foo:", pipeline_kwargs={"max_new_tokens": 42})
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Databricks LLM does not support SerDe the
transform_input_fn and transform_output_fn. After saving and loading,
the LLM will be broken. This PR serialize these functions into a hex
string using pickle, and saving the hex string in the yaml file. Using
pickle to serialize a function can be flaky, but this is a simple
workaround that unblocks many use cases. If more sophisticated SerDe is
needed, we can improve it later.
Test:
Added a simple unit test.
I did manual test on Databricks and it works well.
The saved yaml looks like:
```
llm:
_type: databricks
cluster_driver_port: null
cluster_id: null
databricks_uri: databricks
endpoint_name: databricks-mixtral-8x7b-instruct
extra_params: {}
host: e2-dogfood.staging.cloud.databricks.com
max_tokens: null
model_kwargs: null
n: 1
stop: null
task: null
temperature: 0.0
transform_input_fn: 80049520000000000000008c085f5f6d61696e5f5f948c0f7472616e73666f726d5f696e7075749493942e
transform_output_fn: null
```
@baskaryan
```python
from langchain_community.embeddings import DatabricksEmbeddings
from langchain_community.llms import Databricks
from langchain.chains import RetrievalQA
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
import mlflow
embeddings = DatabricksEmbeddings(endpoint="databricks-bge-large-en")
def transform_input(**request):
request["messages"] = [
{
"role": "user",
"content": request["prompt"]
}
]
del request["prompt"]
return request
llm = Databricks(endpoint_name="databricks-mixtral-8x7b-instruct", transform_input_fn=transform_input)
persist_dir = "faiss_databricks_embedding"
# Create the vector db, persist the db to a local fs folder
loader = TextLoader("state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
db = FAISS.from_documents(docs, embeddings)
db.save_local(persist_dir)
def load_retriever(persist_directory):
embeddings = DatabricksEmbeddings(endpoint="databricks-bge-large-en")
vectorstore = FAISS.load_local(persist_directory, embeddings)
return vectorstore.as_retriever()
retriever = load_retriever(persist_dir)
retrievalQA = RetrievalQA.from_llm(llm=llm, retriever=retriever)
with mlflow.start_run() as run:
logged_model = mlflow.langchain.log_model(
retrievalQA,
artifact_path="retrieval_qa",
loader_fn=load_retriever,
persist_dir=persist_dir,
)
# Load the retrievalQA chain
loaded_model = mlflow.pyfunc.load_model(logged_model.model_uri)
print(loaded_model.predict([{"query": "What did the president say about Ketanji Brown Jackson"}]))
```
- **Description:** Ensure the `LlamaGrammar` custom type is always
available when instantiating a `LlamaCpp` LLM
- **Issue:** #16994
- **Dependencies:** None
- **Twitter handle:** @fpaupier
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Adds an additional class variable to `BedrockBase`
called `provider` that allows sending a model provider such as amazon,
cohere, ai21, etc.
Up until now, the model provider is extracted from the `model_id` using
the first part before the `.`, such as `amazon` for
`amazon.titan-text-express-v1` (see [supported list of Bedrock model IDs
here](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids-arns.html)).
But for custom Bedrock models where the ARN of the provisioned
throughput must be supplied, the `model_id` is like
`arn:aws:bedrock:...` so the `model_id` cannot be extracted from this. A
model `provider` is required by the LangChain Bedrock class to perform
model-based processing. To allow the same processing to be performed for
custom-models of a specific base model type, passing this `provider`
argument can help solve the issues.
The alternative considered here was the use of
`provider.arn:aws:bedrock:...` which then requires ARN to be extracted
and passed separately when invoking the model. The proposed solution
here is simpler and also does not cause issues for current models
already using the Bedrock class.
- **Issue:** N/A
- **Dependencies:** N/A
---------
Co-authored-by: Piyush Jain <piyushjain@duck.com>
Previously, if this did not find a mypy cache then it wouldnt run
this makes it always run
adding mypy ignore comments with existing uncaught issues to unblock other prs
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Replace this entire comment with:
- **Description:** Add Baichuan LLM to integration/llm, also updated
related docs.
Co-authored-by: BaiChuanHelper <wintergyc@WinterGYCs-MacBook-Pro.local>
Use the real "history" provided by the original program instead of
putting "None" in the history.
- **Description:** I change one line in the code to make it return the
"history" of the chat model.
- **Issue:** At the moment it returns only the answers of the chat
model. However the chat model himself provides a history more complet
with the questions of the user.
- **Dependencies:** no dependencies required for this change,
This PR includes updates for OctoAI integrations:
- The LLM class was updated to fix a bug that occurs with multiple
sequential calls
- The Embedding class was updated to support the new GTE-Large endpoint
released on OctoAI lately
- The documentation jupyter notebook was updated to reflect using the
new LLM sdk
Thank you!
<!-- 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:** Adding Oracle Cloud Infrastructure Generative AI
integration. Oracle Cloud Infrastructure (OCI) Generative AI is a fully
managed service that provides a set of state-of-the-art, customizable
large language models (LLMs) that cover a wide range of use cases, and
which is available through a single API. Using the OCI Generative AI
service you can access ready-to-use pretrained models, or create and
host your own fine-tuned custom models based on your own data on
dedicated AI clusters.
https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm
- **Issue:** None,
- **Dependencies:** OCI Python SDK,
- **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.
Passed
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.
we provide unit tests. However, we cannot provide integration tests due
to Oracle policies that prohibit public sharing of api keys.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
---------
Co-authored-by: Arthur Cheng <arthur.cheng@oracle.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Added support for optionally supplying 'Guardrails for Amazon Bedrock'
on both types of model invocations (batch/regular and streaming) and for
all models supported by the Amazon Bedrock service.
@baskaryan @hwchase17
```python
llm = Bedrock(model_id="<model_id>", client=bedrock,
model_kwargs={},
guardrails={"id": " <guardrail_id>",
"version": "<guardrail_version>",
"trace": True}, callbacks=[BedrockAsyncCallbackHandler()])
class BedrockAsyncCallbackHandler(AsyncCallbackHandler):
"""Async callback handler that can be used to handle callbacks from langchain."""
async def on_llm_error(
self,
error: BaseException,
**kwargs: Any,
) -> Any:
reason = kwargs.get("reason")
if reason == "GUARDRAIL_INTERVENED":
# kwargs contains additional trace information sent by 'Guardrails for Bedrock' service.
print(f"""Guardrails: {kwargs}""")
# streaming
llm = Bedrock(model_id="<model_id>", client=bedrock,
model_kwargs={},
streaming=True,
guardrails={"id": "<guardrail_id>",
"version": "<guardrail_version>"})
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
