- **Description:** This adds a delete method so that rocksetdb can be
used with `RecordManager`.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** `@_morgan_adams_`
---------
Co-authored-by: Rockset API Bot <admin@rockset.io>
**Description:** Invoke callback prior to yielding token in stream
method for Ollama.
**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>
**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>
**Description:** changed filtering so that failed filter doesn't add
document to results. Currently filtering is entirely broken and all
documents are returned whether or not they pass the filter.
fixes issue introduced in
https://github.com/langchain-ai/langchain/pull/16190
- **Description:** Adds the document loader for [AWS
Athena](https://aws.amazon.com/athena/), a serverless and interactive
analytics service.
- **Dependencies:** Added boto3 as a dependency
- **Description:** This PR adds support for `search_types="mmr"` and
`search_type="similarity_score_threshold"` to retrievers using
`DatabricksVectorSearch`,
- **Issue:**
- **Dependencies:**
- **Twitter handle:**
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Ref: https://openai.com/pricing
<!-- 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**
Make some functions work with Milvus:
1. get_ids: Get primary keys by field in the metadata
2. delete: Delete one or more entities by ids
3. upsert: Update/Insert one or more entities
**Issue**
None
**Dependencies**
None
**Tag maintainer:**
@hwchase17
**Twitter handle:**
None
---------
Co-authored-by: HoaNQ9 <hoanq.1811@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
<!-- 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>
<!-- 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: changes to you.com files**
- general cleanup
- adds community/utilities/you.py, moving bulk of code from retriever ->
utility
- removes `snippet` as endpoint
- adds `news` as endpoint
- adds more tests
<s>**Description: update community MAKE file**
- adds `integration_tests`
- adds `coverage`</s>
- **Issue:** the issue # it fixes if applicable,
- [For New Contributors: Update Integration
Documentation](https://github.com/langchain-ai/langchain/issues/15664#issuecomment-1920099868)
- **Dependencies:** n/a
- **Twitter handle:** @scottnath
- **Mastodon handle:** scottnath@mastodon.social
---------
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:**
Embedding field name was hard-coded named "embedding".
So I suggest that change `res["embedding"]` into
`res[self._embedding_key]`.
- **Issue:** #17177,
- **Twitter handle:**
[@bagcheoljun17](https://twitter.com/bagcheoljun17)
- **Description:** Fixes in the Ontotext GraphDB Graph and QA Chain
related to the error handling in case of invalid SPARQL queries, for
which `prepareQuery` doesn't throw an exception, but the server returns
400 and the query is indeed invalid
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** @OntotextGraphDB
**Description:**
Implemented unique ID validation in the FAISS component to ensure all
document IDs are distinct. This update resolves issues related to
non-unique IDs, such as inconsistent behavior during deletion processes.
* This PR adds async methods to the LLM cache.
* Adds an implementation using Redis called AsyncRedisCache.
* Adds a docker compose file at the /docker to help spin up docker
* Updates redis tests to use a context manager so flushing always happens by default
### Description
support load any github file content based on file extension.
Why not use [git
loader](https://python.langchain.com/docs/integrations/document_loaders/git#load-existing-repository-from-disk)
?
git loader clones the whole repo even only interested part of files,
that's too heavy. This GithubFileLoader only downloads that you are
interested files.
### Twitter handle
my twitter: @shufanhaotop
---------
Co-authored-by: Hao Fan <h_fan@apple.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Please tag this issue with `nvidia_genai`**
- **Description:** Added new Runnables for integration NVIDIA Riva into
LCEL chains for Automatic Speech Recognition (ASR) and Text To Speech
(TTS).
- **Issue:** N/A
- **Dependencies:** To use these runnables, the NVIDIA Riva client
libraries are required. It they are not installed, an error will be
raised instructing how to install them. The Runnables can be safely
imported without the riva client libraries.
- **Twitter handle:** N/A
All of the Riva Runnables are inside a single folder in the Utilities
module. In this folder are four files:
- common.py - Contains all code that is common to both TTS and ASR
- stream.py - Contains a class representing an audio stream that allows
the end user to put data into the stream like a queue.
- asr.py - Contains the RivaASR runnable
- tts.py - Contains the RivaTTS runnable
The following Python function is an example of creating a chain that
makes use of both of these Runnables:
```python
def create(
config: Configuration,
audio_encoding: RivaAudioEncoding,
sample_rate: int,
audio_channels: int = 1,
) -> Runnable[ASRInputType, TTSOutputType]:
"""Create a new instance of the chain."""
_LOGGER.info("Instantiating the chain.")
# create the riva asr client
riva_asr = RivaASR(
url=str(config.riva_asr.service.url),
ssl_cert=config.riva_asr.service.ssl_cert,
encoding=audio_encoding,
audio_channel_count=audio_channels,
sample_rate_hertz=sample_rate,
profanity_filter=config.riva_asr.profanity_filter,
enable_automatic_punctuation=config.riva_asr.enable_automatic_punctuation,
language_code=config.riva_asr.language_code,
)
# create the prompt template
prompt = PromptTemplate.from_template("{user_input}")
# model = ChatOpenAI()
model = ChatNVIDIA(model="mixtral_8x7b") # type: ignore
# create the riva tts client
riva_tts = RivaTTS(
url=str(config.riva_asr.service.url),
ssl_cert=config.riva_asr.service.ssl_cert,
output_directory=config.riva_tts.output_directory,
language_code=config.riva_tts.language_code,
voice_name=config.riva_tts.voice_name,
)
# construct and return the chain
return {"user_input": riva_asr} | prompt | model | riva_tts # type: ignore
```
The following code is an example of creating a new audio stream for
Riva:
```python
input_stream = AudioStream(maxsize=1000)
# Send bytes into the stream
for chunk in audio_chunks:
await input_stream.aput(chunk)
input_stream.close()
```
The following code is an example of how to execute the chain with
RivaASR and RivaTTS
```python
output_stream = asyncio.Queue()
while not input_stream.complete:
async for chunk in chain.astream(input_stream):
output_stream.put(chunk)
```
Everything should be async safe and thread safe. Audio data can be put
into the input stream while the chain is running without interruptions.
---------
Co-authored-by: Hayden Wolff <hwolff@nvidia.com>
Co-authored-by: Hayden Wolff <hwolff@Haydens-Laptop.local>
Co-authored-by: Hayden Wolff <haydenwolff99@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
- **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 a function parameter to HuggingFaceEmbeddings
called `show_progress` that enables a `tqdm` progress bar if enabled.
Does not function if `multi_process = True`.
- **Issue:** n/a
- **Dependencies:** n/a
- **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>
<!-- 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.
-->
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>
## Description
In #16608, the calling `collection_name` was wrong.
I made a fix for it.
Sorry for the inconvenience!
## Issue
https://github.com/langchain-ai/langchain/issues/16962
## Dependencies
N/A
<!-- 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: Kumar Shivendu <kshivendu1@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
The `langchain.prompts.example_selector` [still holds several
artifacts](https://api.python.langchain.com/en/latest/langchain_api_reference.html#module-langchain.prompts)
that belongs to `community`. If they moved to
`langchain_community.example_selectors`, the `langchain.prompts`
namespace would be effectively removed which is great.
- moved a class and afunction to `langchain_community`
Note:
- Previously, the `langchain.prompts.example_selector` artifacts were
moved into the `langchain_core.exampe_selectors`. See the flattened
namespace (`.prompts` was removed)!
Similar flattening was implemented for the `langchain_core` as the
`langchain_core.exampe_selectors`.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
* Adds `AstraDBEnvironment` class and use it in `AstraDBLoader`,
`AstraDBCache`, `AstraDBSemanticCache`, `AstraDBBaseStore` and
`AstraDBChatMessageHistory`
* Create an `AsyncAstraDB` if we only have an `AstraDB` and vice-versa
so:
* we always have an instance of `AstraDB`
* we always have an instance of `AsyncAstraDB` for recent versions of
astrapy
* Create collection if not exists in `AstraDBBaseStore`
* Some typing improvements
Note: `AstraDB` `VectorStore` not using `AstraDBEnvironment` at the
moment. This will be done after the `langchain-astradb` package is out.
Adds:
* methods `aload()` and `alazy_load()` to interface `BaseLoader`
* implementation for class `MergedDataLoader `
* support for class `BaseLoader` in async function `aindex()` with unit
tests
Note: this is compatible with existing `aload()` methods that some
loaders already had.
**Twitter handle:** @cbornet_
---------
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
- **Description:** the existing AssemblyAI API allows to pass a path or
an url to transcribe an audio file and turn in into Langchain Documents,
this PR allows to get existing transcript by their transcript id and
turn them into Documents.
- **Issue:** not related to an existing issue
- **Dependencies:** requests
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
The current implementation leaves it up to the particular file loader
implementation to report the file on which an error was encountered - in
my case pdfminer was simply saying it could not parse a file as a PDF,
but I didn't know which of my hundreds of files it was failing on.
No reason not to log the particular item on which an error was
encountered, and it should be an immense debugging assistant.
<!-- 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: Added the parameter for a possibility to change a language
model in SpacyEmbeddings. The default value is still the same:
"en_core_web_sm", so it shouldn't affect a code which previously did not
specify this parameter, but it is not hard-coded anymore and easy to
change in case you want to use it with other languages or models.
Issue: At Barcelona Supercomputing Center in Aina project
(https://github.com/projecte-aina), a project for Catalan Language
Models and Resources, we would like to use Langchain for one of our
current projects and we would like to comment that Langchain, while
being a very powerful and useful open-source tool, is pretty much
focused on English language. We would like to contribute to make it a
bit more adaptable for using with other languages.
Dependencies: This change requires the Spacy library and a language
model, specified in the model parameter.
Tag maintainer: @dev2049
Twitter handle: @projecte_aina
---------
Co-authored-by: Marina Pliusnina <marina.pliusnina@bsc.es>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description**: fully async versions are available for astrapy 0.7+.
For older astrapy versions or if the user provides a sync client without
an async one, the async methods will call the sync ones wrapped in
`run_in_executor`
- **Twitter handle:** cbornet_
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>
- **Description:**
Filtering in a FAISS vectorstores is very inflexible and doesn't allow
that many use case. I think supporting callable like this enables a lot:
regular expressions, condition on multiple keys etc. **Note** I had to
manually alter a test. I don't understand if it was falty to begin with
or if there is something funky going on.
- **Issue:** None
- **Dependencies:** None
- **Twitter handle:** None
Signed-off-by: thiswillbeyourgithub <26625900+thiswillbeyourgithub@users.noreply.github.com>
## Description
The PR is to return the ID and collection name from qdrant client to
metadata field in `Document` class.
## Issue
The motivation is almost same to
[11592](https://github.com/langchain-ai/langchain/issues/11592)
Returning ID is useful to update existing records in a vector store, but
we cannot know them if we use some retrievers.
In order to avoid any conflicts, breaking changes, the new fields in
metadata have a prefix `_`
## Dependencies
N/A
## Twitter handle
@kill_in_sun
<!-- 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.
-->
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!
## Summary
This PR implements the "Connery Action Tool" and "Connery Toolkit".
Using them, you can integrate Connery actions into your LangChain agents
and chains.
Connery is an open-source plugin infrastructure for AI.
With Connery, you can easily create a custom plugin with a set of
actions and seamlessly integrate them into your LangChain agents and
chains. Connery will handle the rest: runtime, authorization, secret
management, access management, audit logs, and other vital features.
Additionally, Connery and our community offer a wide range of
ready-to-use open-source plugins for your convenience.
Learn more about Connery:
- GitHub: https://github.com/connery-io/connery-platform
- Documentation: https://docs.connery.io
- Twitter: https://twitter.com/connery_io
## TODOs
- [x] API wrapper
- [x] Integration tests
- [x] Connery Action Tool
- [x] Docs
- [x] Example
- [x] Integration tests
- [x] Connery Toolkit
- [x] Docs
- [x] Example
- [x] Formatting (`make format`)
- [x] Linting (`make lint`)
- [x] Testing (`make test`)
- **Description:** To adapt more parameters related to
MemorySearchPayload for the search method of ZepChatMessageHistory,
- **Issue:** None,
- **Dependencies:** None,
- **Twitter handle:** None
Add missing async similarity_distance_threshold handling in
RedisVectorStoreRetriever
- **Description:** added method `_aget_relevant_documents` to
`RedisVectorStoreRetriever` that overrides parent method to add support
of `similarity_distance_threshold` in async mode (as for sync mode)
- **Issue:** #16099
- **Dependencies:** N/A
- **Twitter handle:** N/A
* Description: Fixed schema discrepancy in **from_texts** function for
weaviate vectorstore which created a redundant property "key" inside a
class.
* Issue: Fixed: https://github.com/langchain-ai/langchain/issues/16692
* Twitter handle: @pashvamehta1
- **Description:** Adds Wikidata support to langchain. Can read out
documents from Wikidata.
- **Issue:** N/A
- **Dependencies:** Adds implicit dependencies for
`wikibase-rest-api-client` (for turning items into docs) and
`mediawikiapi` (for hitting the search endpoint)
- **Twitter handle:** @derenrich
You can see an example of this tool used in a chain
[here](https://nbviewer.org/urls/d.erenrich.net/upload/Wikidata_Langchain.ipynb)
or
[here](https://nbviewer.org/urls/d.erenrich.net/upload/Wikidata_Lars_Kai_Hansen.ipynb)
<!-- Thank you for contributing to LangChain!
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:** This update ensures that the user-defined embedding
function specified during vector store creation is applied during
queries. Previously, even if a custom embedding function was defined at
the time of store creation, Bagel DB would default to using the standard
embedding function during query execution. This pull request addresses
this issue by consistently using the user-defined embedding function for
queries if one has been specified earlier.
- **Description:** This change allows the `_fetch` method in the
`WebBaseLoader` class to utilize cookies from an existing
`requests.Session`. It ensures that when the `fetch` method is used, any
cookies in the provided session are included in the request. This
enhancement maintains compatibility with existing functionality while
extending the utility of the `fetch` method for scenarios where cookie
persistence is necessary.
- **Issue:** Not applicable (new feature),
- **Dependencies:** Requires `aiohttp` and `requests` libraries (no new
dependencies introduced),
- **Twitter handle:** N/A
Co-authored-by: Joao Almeida <joao.almeida@mercedes-benz.io>
We can't use `json.dumps` by default as many types returned by the
cassandra driver are not serializable. It's safer to use `str` and let
users define their own custom `page_content_mapper` if needed.
- **Description**: YoutubeLoader right now returns one document that
contains the entire transcript. I think it would be useful to add an
option to return multiple documents, where each document would contain
one line of transcript with the start time and duration in the metadata.
For example,
[AssemblyAIAudioTranscriptLoader](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/document_loaders/assemblyai.py)
is implemented in a similar way, it allows you to choose between the
format to use for the document loader.
- **Description:** Adding Baichuan Text Embedding Model and Baichuan Inc
introduction.
Baichuan Text Embedding ranks #1 in C-MTEB leaderboard:
https://huggingface.co/spaces/mteb/leaderboard
Co-authored-by: BaiChuanHelper <wintergyc@WinterGYCs-MacBook-Pro.local>
- **Description:** This PR adds [EdenAI](https://edenai.co/) for the
chat model (already available in LLM & Embeddings). It supports all
[ChatModel] functionality: generate, async generate, stream, astream and
batch. A detailed notebook was added.
- **Dependencies**: No dependencies are added as we call a rest API.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
… converters
One way to convert anything to an OAI function:
convert_to_openai_function
One way to convert anything to an OAI tool: convert_to_openai_tool
Corresponding bind functions on OAI models: bind_functions, bind_tools
community:
- **Description:**
- Add new ChatLiteLLMRouter class that allows a client to use a LiteLLM
Router as a LangChain chat model.
- Note: The existing ChatLiteLLM integration did not cover the LiteLLM
Router class.
- Add tests and Jupyter notebook.
- **Issue:** None
- **Dependencies:** Relies on existing ChatLiteLLM integration
- **Twitter handle:** @bburgin_0
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
<!-- 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>
- **Description:**
This PR adds a VectorStore integration for SAP HANA Cloud Vector Engine,
which is an upcoming feature in the SAP HANA Cloud database
(https://blogs.sap.com/2023/11/02/sap-hana-clouds-vector-engine-announcement/).
- **Issue:** N/A
- **Dependencies:** [SAP HANA Python
Client](https://pypi.org/project/hdbcli/)
- **Twitter handle:** @sapopensource
Implementation of the integration:
`libs/community/langchain_community/vectorstores/hanavector.py`
Unit tests:
`libs/community/tests/unit_tests/vectorstores/test_hanavector.py`
Integration tests:
`libs/community/tests/integration_tests/vectorstores/test_hanavector.py`
Example notebook:
`docs/docs/integrations/vectorstores/hanavector.ipynb`
Access credentials for execution of the integration tests can be
provided to the maintainers.
---------
Co-authored-by: sascha <sascha.stoll@sap.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:**
Handle unsupported languages in same way as when none is provided
**Issue:**
The following line will throw a KeyError if the language is not
supported.
```python
self.Segmenter = LANGUAGE_SEGMENTERS[language]
```
E.g. when using `Language.CPP` we would get `KeyError: <Language.CPP:
'cpp'>`
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** added the conversational task to hugginFace endpoint
in order to use models designed for chatbot programming.
- **Dependencies:** None
---------
Co-authored-by: Alessio Serra (ext.) <alessio.serra@partner.bmw.de>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Updated `_get_elements()` function of
`UnstructuredFileLoader `class to check if the argument self.file_path
is a file or list of files. If it is a list of files then it iterates
over the list of file paths, calls the partition function for each one,
and appends the results to the elements list. If self.file_path is not a
list, it calls the partition function as before.
- **Issue:** Fixed#15607,
- **Dependencies:** NA
- **Twitter handle:** NA
Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>
- **Description:** This PR enables LangChain to access the iFlyTek's
Spark LLM via the chat_models wrapper.
- **Dependencies:** websocket-client ^1.6.1
- **Tag maintainer:** @baskaryan
### SparkLLM chat model usage
Get SparkLLM's app_id, api_key and api_secret from [iFlyTek SparkLLM API
Console](https://console.xfyun.cn/services/bm3) (for more info, see
[iFlyTek SparkLLM Intro](https://xinghuo.xfyun.cn/sparkapi) ), then set
environment variables `IFLYTEK_SPARK_APP_ID`, `IFLYTEK_SPARK_API_KEY`
and `IFLYTEK_SPARK_API_SECRET` or pass parameters when using it like the
demo below:
```python3
from langchain.chat_models.sparkllm import ChatSparkLLM
client = ChatSparkLLM(
spark_app_id="<app_id>",
spark_api_key="<api_key>",
spark_api_secret="<api_secret>"
)
```
This PR introduces update to Konko Integration with LangChain.
1. **New Endpoint Addition**: Integration of a new endpoint to utilize
completion models hosted on Konko.
2. **Chat Model Updates for Backward Compatibility**: We have updated
the chat models to ensure backward compatibility with previous OpenAI
versions.
4. **Updated Documentation**: Comprehensive documentation has been
updated to reflect these new changes, providing clear guidance on
utilizing the new features and ensuring seamless integration.
Thank you to the LangChain team for their exceptional work and for
considering this PR. Please let me know if any additional information is
needed.
---------
Co-authored-by: Shivani Modi <shivanimodi@Shivanis-MacBook-Pro.local>
Co-authored-by: Shivani Modi <shivanimodi@Shivanis-MBP.lan>
Adds the ability to return similarity scores when using
`RetrievalQA.from_chain_type` with `MongoDBAtlasVectorSearch`. Requires
that `return_source_documents=True` is set.
Example use:
```
vector_search = MongoDBAtlasVectorSearch.from_documents(...)
qa = RetrievalQA.from_chain_type(
llm=OpenAI(),
chain_type="stuff",
retriever=vector_search.as_retriever(search_kwargs={"additional": ["similarity_score"]}),
return_source_documents=True
)
...
docs = qa({"query": "..."})
docs["source_documents"][0].metadata["score"] # score will be here
```
I've tested this feature locally, using a MongoDB Atlas Cluster with a
vector search index.
- **Description:** Allow passing run_id to MLflowCallbackHandler to
resume a run instead of creating a new run. Support recording retriever
relevant metrics. Refactor the code to fix some bugs.
---------
Signed-off-by: Serena Ruan <serena.rxy@gmail.com>
In this PR I added a post-processing function to normalize the
embeddings. This happens only if the new `normalize` flag is `True`.
---------
Co-authored-by: taamedag <Davide.Menini@swisscom.com>
- **Description:** Baichuan Chat (with both Baichuan-Turbo and
Baichuan-Turbo-192K models) has updated their APIs. There are breaking
changes. For example, BAICHUAN_SECRET_KEY is removed in the latest API
but is still required in Langchain. Baichuan's Langchain integration
needs to be updated to the latest version.
- **Issue:** #15206
- **Dependencies:** None,
- **Twitter handle:** None
@hwchase17.
Co-authored-by: BaiChuanHelper <wintergyc@WinterGYCs-MacBook-Pro.local>
**Description:**
- Implement `SQLStrStore` and `SQLDocStore` classes that inherits from
`BaseStore` to allow to persist data remotely on a SQL server.
- SQL is widely used and sometimes we do not want to install a caching
solution like Redis.
- Multiple issues/comments complain that there is no easy remote and
persistent solution that are not in memory (users want to replace
InMemoryStore), e.g.,
https://github.com/langchain-ai/langchain/issues/14267,
https://github.com/langchain-ai/langchain/issues/15633,
https://github.com/langchain-ai/langchain/issues/14643,
https://stackoverflow.com/questions/77385587/persist-parentdocumentretriever-of-langchain
- This is particularly painful when wanting to use
`ParentDocumentRetriever `
- This implementation is particularly useful when:
* it's expensive to construct an InMemoryDocstore/dict
* you want to retrieve documents from remote sources
* you just want to reuse existing objects
- This implementation integrates well with PGVector, indeed, when using
PGVector, you already have a SQL instance running. `SQLDocStore` is a
convenient way of using this instance to store documents associated to
vectors. An integration example with ParentDocumentRetriever and
PGVector is provided in docs/docs/integrations/stores/sql.ipynb or
[here](https://github.com/gcheron/langchain/blob/sql-store/docs/docs/integrations/stores/sql.ipynb).
- It persists `str` and `Document` objects but can be easily extended.
**Issue:**
Provide an easy SQL alternative to `InMemoryStore`.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:** this PR upgrades the `HuggingFaceHub` LLM:
* support more tasks (`translation` and `conversational`)
* replaced the deprecated `InferenceApi` with `InferenceClient`
* adjusted the overall logic to use the "recommended" model for each
task when no model is provided, and vice-versa.
- **Tag mainter(s)**: @baskaryan @hwchase17
**Description** : New documents loader for visio files (with extension
.vsdx)
A [visio file](https://fr.wikipedia.org/wiki/Microsoft_Visio) (with
extension .vsdx) is associated with Microsoft Visio, a diagram creation
software. It stores information about the structure, layout, and
graphical elements of a diagram. This format facilitates the creation
and sharing of visualizations in areas such as business, engineering,
and computer science.
A Visio file can contain multiple pages. Some of them may serve as the
background for others, and this can occur across multiple layers. This
loader extracts the textual content from each page and its associated
pages, enabling the extraction of all visible text from each page,
similar to what an OCR algorithm would do.
**Dependencies** : xmltodict package
I also added LANGCHAIN_COMET_TRACING to enable the CometLLM tracing
integration similar to other tracing integrations. This is easier for
end-users to enable it rather than importing the callback and pass it
manually.
(This is the same content as
https://github.com/langchain-ai/langchain/pull/14650 but rebased and
squashed as something seems to confuse Github Action).
Description: Added support for asynchronous streaming in the Bedrock
class and corresponding tests.
Primarily:
async def aprepare_output_stream
async def _aprepare_input_and_invoke_stream
async def _astream
async def _acall
I've ensured that the code adheres to the project's linting and
formatting standards by running make format, make lint, and make test.
Issue: #12054, #11589
Dependencies: None
Tag maintainer: @baskaryan
Twitter handle: @dominic_lovric
---------
Co-authored-by: Piyush Jain <piyushjain@duck.com>
Replace this entire comment with:
- **Description:** allow user to define tVector length in PGVector when
creating the embedding store, this allows for later indexing
- **Issue:** #16132
- **Dependencies:** None
**Description:** Add support for querying TigerGraph databases through
the InquiryAI service.
**Issue**: N/A
**Dependencies:** N/A
**Twitter handle:** @TigerGraphDB
there is a case where "coords" does not exist in the "sentence"
therefore, the "split(";")" will lead to error.
we can fix that by adding "if sentence.get("coords") is not None:"
the resulting empty "sbboxes" from this scenario will raise error at
"sbboxes[0]["page"]" because sbboxes are empty.
the PDF from https://pubmed.ncbi.nlm.nih.gov/23970373/ can replicate
those errors.
This pull request integrates the TiDB database into LangChain for
storing message history, marking one of several steps towards a
comprehensive integration of TiDB with LangChain.
A simple usage
```python
from datetime import datetime
from langchain_community.chat_message_histories import TiDBChatMessageHistory
history = TiDBChatMessageHistory(
connection_string="mysql+pymysql://<host>:<PASSWORD>@<host>:4000/<db>?ssl_ca=/etc/ssl/cert.pem&ssl_verify_cert=true&ssl_verify_identity=true",
session_id="code_gen",
earliest_time=datetime.utcnow(), # Optional to set earliest_time to load messages after this time point.
)
history.add_user_message("hi! How's feature going?")
history.add_ai_message("It's almot done")
```
- **Description:** add support for kwargs in`MlflowEmbeddings`
`embed_document()` and `embed_query()` so that all the arguments
required by Cohere API (and others?) can be passed down to the server.
- **Issue:** #15234
- **Dependencies:** MLflow with MLflow Deployments (`pip install
mlflow[genai]`)
**Tests**
Now this code [adapted from the
docs](https://python.langchain.com/docs/integrations/providers/mlflow#embeddings-example)
for the Cohere API works locally.
```python
"""
Setup
-----
export COHERE_API_KEY=...
mlflow deployments start-server --config-path examples/deployments/cohere/config.yaml
Run
---
python /path/to/this/file.py
"""
embeddings = MlflowCohereEmbeddings(target_uri="http://127.0.0.1:5000", endpoint="embeddings")
print(embeddings.embed_query("hello")[:3])
print(embeddings.embed_documents(["hello", "world"])[0][:3])
```
Output
```
[0.060455322, 0.028793335, -0.025848389]
[0.031707764, 0.021057129, -0.009361267]
```
Titan Express model was not supported as a chat model because LangChain
messages were not "translated" to a text prompt.
Co-authored-by: Guillem Orellana Trullols <guillem.orellana_trullols@siemens.com>
- **Description:** I removed two queries to the database and left just
one whose results were formatted afterward into other type of schema
(avoided two calls to DB)
- **Issue:** /
- **Dependencies:** /
- **Twitter handle:** @supe_katarina
Enable max inner product for approximate retrieval strategy. For exact
strategy we lack the necessary `maxInnerProduct` function in the
Painless scripting language, this is why we do not add it there.
Similarity docs:
https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Joe McElroy <joseph.mcelroy@elastic.co>
Implement similarity function selector for ElasticsearchStore. The
scores coming back from Elasticsearch are already similarities (not
distances) and they are already normalized (see
[docs](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params)).
Hence we leave the scores untouched and just forward them.
This fixes#11539.
However, in hybrid mode (when keyword search and vector search are
involved) Elasticsearch currently returns no scores. This PR adds an
error message around this fact. We need to think a bit more to come up
with a solution for this case.
This PR also corrects a small error in the Elasticsearch integration
test.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description:**
In this PR, I am adding a `PolygonLastQuote` Tool, which can be used to
get the latest price quote for a given ticker / stock.
Additionally, I've added a Polygon Toolkit, which we can use to
encapsulate future tools that we build for Polygon.
**Twitter handle:** [@virattt](https://twitter.com/virattt)
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
fixed multi-query template for Vectara
added self-query template for Vectara
Also added prompt_name parameter to summarization
CC @efriis
**Twitter handle:** @ofermend
- **Description:** Some text-generation models on huggingface repeat the
prompt in their generated response, but not all do! The tests use "gpt2"
which DOES repeat the prompt and as such, the HuggingFaceHub class is
hardcoded to remove the first few characters of the response (to match
the len(prompt)). However, if you are using a model (such as the very
popular "meta-llama/Llama-2-7b-chat-hf") that DOES NOT repeat the prompt
in it's generated text, then the beginning of the generated text will be
cut off. This code change fixes that bug by first checking whether the
prompt is repeated in the generated response and removing it
conditionally.
- **Issue:** #16232
- **Dependencies:** N/A
- **Twitter handle:** N/A
The timeout function comes in handy when you want to kill longrunning
queries.
The value sanitization removes all lists that are larger than 128
elements. The idea here is to remove embedding properties from results.
- **Description:** As Shell tool is very versatile, while integrating it
into applications as openai functions, developers have no clue about
what command is being executed using the ShellTool. All one can see is:
Summarising my feature request:
1. There's no visibility about what command was executed.
2. There's no mechanism to prevent a command to be executed using
ShellTool, like a y/n human input which can be accepted from user to
proceed with executing the command.,
- **Issue:** the issue #15931 it fixes if applicable,
- **Dependencies:** There isn't any dependancy,
- **Twitter handle:** @krishnashed
- **Description:** Made a small fix for the `SQLDatabase` highlighted in
an issue. The issue pertains to switching schema for different SQL
engines.
- **Issue:** #16023
@baskaryan
- **Description:** This handles the cohere response when documents
aren't included in the response
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** N/A
