# OpenAIWhisperParser
This PR creates a new parser, `OpenAIWhisperParser`, that uses the
[OpenAI Whisper
model](https://platform.openai.com/docs/guides/speech-to-text/quickstart)
to perform transcription of audio files to text (`Documents`). Please
see the notebook for usage.
Zep now supports persisting custom metadata with messages and hybrid
search across both message embeddings and structured metadata. This PR
implements custom metadata and enhancements to the
`ZepChatMessageHistory` and `ZepRetriever` classes to implement this
support.
Tag maintainers/contributors who might be interested:
VectorStores / Retrievers / Memory
- @dev2049
---------
Co-authored-by: Daniel Chalef <daniel.chalef@private.org>
# Check if generated Cypher code is wrapped in backticks
Some LLMs like the VertexAI like to explain how they generated the
Cypher statement and wrap the actual code in three backticks:
I have observed a similar pattern with OpenAI chat models in a
conversational settings, where multiple user and assistant message are
provided to the LLM to generate Cypher statements, where then the LLM
wants to maybe apologize for previous steps or explain its thoughts.
Interestingly, both OpenAI and VertexAI wrap the code in three backticks
if they are doing any explaining or apologizing. Checking if the
generated cypher is wrapped in backticks seems like a low-hanging fruit
to expand the cypher search to other LLMs and conversational settings.
# Token text splitter for sentence transformers
The current TokenTextSplitter only works with OpenAi models via the
`tiktoken` package. This is not clear from the name `TokenTextSplitter`.
In this (first PR) a token based text splitter for sentence transformer
models is added. In the future I think we should work towards injecting
a tokenizer into the TokenTextSplitter to make ti more flexible.
Could perhaps be reviewed by @dev2049
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Raises exception if OutputParsers receive a response with both a valid
action and a final answer
Currently, if an OutputParser receives a response which includes both an
action and a final answer, they return a FinalAnswer object. This allows
the parser to accept responses which propose an action and hallucinate
an answer without the action being parsed or taken by the agent.
This PR changes the logic to:
1. store a variable checking whether a response contains the
`FINAL_ANSWER_ACTION` (this is the easier condition to check).
2. store a variable checking whether the response contains a valid
action
3. if both are present, raise a new exception stating that both are
present
4. if an action is present, return an AgentAction
5. if an answer is present, return an AgentAnswer
6. if neither is present, raise the relevant exception based around the
action format (these have been kept consistent with the prior exception
messages)
Disclaimer:
* Existing mock data included strings which did include an action and an
answer. This might indicate that prioritising returning AgentAnswer was
always correct, and I am patching out desired behaviour? @hwchase17 to
advice. Curious if there are allowed cases where this is not
hallucinating, and we do want the LLM to output an action which isn't
taken.
* I have not passed `send_to_llm` through this new exception
Fixes#5601
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@hwchase17 - project lead
@vowelparrot
# Unstructured Excel Loader
Adds an `UnstructuredExcelLoader` class for `.xlsx` and `.xls` files.
Works with `unstructured>=0.6.7`. A plain text representation of the
Excel file will be available under the `page_content` attribute in the
doc. If you use the loader in `"elements"` mode, an HTML representation
of the Excel file will be available under the `text_as_html` metadata
key. Each sheet in the Excel document is its own document.
### Testing
```python
from langchain.document_loaders import UnstructuredExcelLoader
loader = UnstructuredExcelLoader(
"example_data/stanley-cups.xlsx",
mode="elements"
)
docs = loader.load()
```
## Who can review?
@hwchase17
@eyurtsev
# Chroma update_document full document embeddings bugfix
Chroma update_document takes a single document, but treats the
page_content sting of that document as a list when getting the new
document embedding.
This is a two-fold problem, where the resulting embedding for the
updated document is incorrect (it's only an embedding of the first
character in the new page_content) and it calls the embedding function
for every character in the new page_content string, using many tokens in
the process.
Fixes#5582
Co-authored-by: Caleb Ellington <calebellington@Calebs-MBP.hsd1.ca.comcast.net>
# Fix Qdrant ids creation
There has been a bug in how the ids were created in the Qdrant vector
store. They were previously calculated based on the texts. However,
there are some scenarios in which two documents may have the same piece
of text but different metadata, and that's a valid case. Deduplication
should be done outside of insertion.
It has been fixed and covered with the integration tests.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Fixes SQLAlchemy truncating the result if you have a big/text column
with many chars.
SQLAlchemy truncates columns if you try to convert a Row or Sequence to
a string directly
For comparison:
- Before:
```[('Harrison', 'That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio ... (2 characters truncated) ... hat is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio That is my Bio ')]```
- After:
```[('Harrison', 'That is my Bio That is my Bio That is my Bio That is
my Bio That is my Bio That is my Bio That is my Bio That is my Bio That
is my Bio That is my Bio That is my Bio That is my Bio That is my Bio
That is my Bio That is my Bio That is my Bio That is my Bio That is my
Bio That is my Bio That is my Bio ')]```
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
I'm not sure who to tag for chains, maybe @vowelparrot ?
Similar to #1813 for faiss, this PR is to extend functionality to pass
text and its vector pair to initialize and add embeddings to the
PGVector wrapper.
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
- @dev2049
# Support Qdrant filters
Qdrant has an [extensive filtering
system](https://qdrant.tech/documentation/concepts/filtering/) with rich
type support. This PR makes it possible to use the filters in Langchain
by passing an additional param to both the
`similarity_search_with_score` and `similarity_search` methods.
## Who can review?
@dev2049 @hwchase17
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
when the LLMs output 'yes|no'，BooleanOutputParser can parse it to
'True|False', fix the ValueError in parse().
<!--
when use the BooleanOutputParser in the chain_filter.py, the LLMs output
'yes|no'，the function 'parse' will throw ValueError。
-->
Fixes # (issue)
#5396https://github.com/hwchase17/langchain/issues/5396
---------
Co-authored-by: gaofeng27692 <gaofeng27692@hundsun.com>
# Add maximal relevance search to SKLearnVectorStore
This PR implements the maximum relevance search in SKLearnVectorStore.
Twitter handle: jtolgyesi (I submitted also the original implementation
of SKLearnVectorStore)
## Before submitting
Unit tests are included.
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Add batching to Qdrant
Several people requested a batching mechanism while uploading data to
Qdrant. It is important, as there are some limits for the maximum size
of the request payload, and without batching implemented in Langchain,
users need to implement it on their own. This PR exposes a new optional
`batch_size` parameter, so all the documents/texts are loaded in batches
of the expected size (64, by default).
The integration tests of Qdrant are extended to cover two cases:
1. Documents are sent in separate batches.
2. All the documents are sent in a single request.
# Handles the edge scenario in which the action input is a well formed
SQL query which ends with a quoted column
There may be a cleaner option here (or indeed other edge scenarios) but
this seems to robustly determine if the action input is likely to be a
well formed SQL query in which we don't want to arbitrarily trim off `"`
characters
Fixes#5423
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Agents / Tools / Toolkits
- @vowelparrot
# What does this PR do?
Bring support of `encode_kwargs` for ` HuggingFaceInstructEmbeddings`,
change the docstring example and add a test to illustrate with
`normalize_embeddings`.
Fixes#3605
(Similar to #3914)
Use case:
```python
from langchain.embeddings import HuggingFaceInstructEmbeddings
model_name = "hkunlp/instructor-large"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': True}
hf = HuggingFaceInstructEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
)
```
As the title says, I added more code splitters.
The implementation is trivial, so i don't add separate tests for each
splitter.
Let me know if any concerns.
Fixes # (issue)
https://github.com/hwchase17/langchain/issues/5170
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@eyurtsev @hwchase17
---------
Signed-off-by: byhsu <byhsu@linkedin.com>
Co-authored-by: byhsu <byhsu@linkedin.com>
# Creates GitHubLoader (#5257)
GitHubLoader is a DocumentLoader that loads issues and PRs from GitHub.
Fixes#5257
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Added New Trello loader class and documentation
Simple Loader on top of py-trello wrapper.
With a board name you can pull cards and to do some field parameter
tweaks on load operation.
I included documentation and examples.
Included unit test cases using patch and a fixture for py-trello client
class.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Add ToolException that a tool can throw
This is an optional exception that tool throws when execution error
occurs.
When this exception is thrown, the agent will not stop working,but will
handle the exception according to the handle_tool_error variable of the
tool,and the processing result will be returned to the agent as
observation,and printed in pink on the console.It can be used like this:
```python
from langchain.schema import ToolException
from langchain import LLMMathChain, SerpAPIWrapper, OpenAI
from langchain.agents import AgentType, initialize_agent
from langchain.chat_models import ChatOpenAI
from langchain.tools import BaseTool, StructuredTool, Tool, tool
from langchain.chat_models import ChatOpenAI
llm = ChatOpenAI(temperature=0)
llm_math_chain = LLMMathChain(llm=llm, verbose=True)
class Error_tool:
def run(self, s: str):
raise ToolException('The current search tool is not available.')
def handle_tool_error(error) -> str:
return "The following errors occurred during tool execution:"+str(error)
search_tool1 = Error_tool()
search_tool2 = SerpAPIWrapper()
tools = [
Tool.from_function(
func=search_tool1.run,
name="Search_tool1",
description="useful for when you need to answer questions about current events.You should give priority to using it.",
handle_tool_error=handle_tool_error,
),
Tool.from_function(
func=search_tool2.run,
name="Search_tool2",
description="useful for when you need to answer questions about current events",
return_direct=True,
)
]
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True,
handle_tool_errors=handle_tool_error)
agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
```
## Who can review?
- @vowelparrot
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Implemented appending arbitrary messages to the base chat message
history, the in-memory and cosmos ones.
<!--
Thank you for contributing to LangChain! Your PR will appear in our next
release under the title you set. Please make sure it highlights your
valuable contribution.
Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.
After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.
-->
As discussed this is the alternative way instead of #4480, with a
add_message method added that takes a BaseMessage as input, so that the
user can control what is in the base message like kwargs.
<!-- Remove if not applicable -->
Fixes # (issue)
## Before submitting
<!-- If you're adding a new integration, include an integration test and
an example notebook showing its use! -->
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@hwchase17
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
# Fix for `update_document` Function in Chroma
## Summary
This pull request addresses an issue with the `update_document` function
in the Chroma class, as described in
[#5031](https://github.com/hwchase17/langchain/issues/5031#issuecomment-1562577947).
The issue was identified as an `AttributeError` raised when calling
`update_document` due to a missing corresponding method in the
`Collection` object. This fix refactors the `update_document` method in
`Chroma` to correctly interact with the `Collection` object.
## Changes
1. Fixed the `update_document` method in the `Chroma` class to correctly
call methods on the `Collection` object.
2. Added the corresponding test `test_chroma_update_document` in
`tests/integration_tests/vectorstores/test_chroma.py` to reflect the
updated method call.
3. Added an example and explanation of how to use the `update_document`
function in the Jupyter notebook tutorial for Chroma.
## Test Plan
All existing tests pass after this change. In addition, the
`test_chroma_update_document` test case now correctly checks the
functionality of `update_document`, ensuring that the function works as
expected and updates the content of documents correctly.
## Reviewers
@dev2049
This fix will ensure that users are able to use the `update_document`
function as expected, without encountering the previous
`AttributeError`. This will enhance the usability and reliability of the
Chroma class for all users.
Thank you for considering this pull request. I look forward to your
feedback and suggestions.
# Fix lost mimetype when using Blob.from_data method
The mimetype is lost due to a typo in the class attribue name
Fixes # - (no issue opened but I can open one if needed)
## Changes
* Fixed typo in name
* Added unit-tests to validate the output Blob
## Review
@eyurtsev
# Add path validation to DirectoryLoader
This PR introduces a minor adjustment to the DirectoryLoader by adding
validation for the path argument. Previously, if the provided path
didn't exist or wasn't a directory, DirectoryLoader would return an
empty document list due to the behavior of the `glob` method. This could
potentially cause confusion for users, as they might expect a
file-loading error instead.
So, I've added two validations to the load method of the
DirectoryLoader:
- Raise a FileNotFoundError if the provided path does not exist
- Raise a ValueError if the provided path is not a directory
Due to the relatively small scope of these changes, a new issue was not
created.
## Before submitting
<!-- If you're adding a new integration, please include:
1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use
See contribution guidelines for more information on how to write tests,
lint
etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@eyurtsev
# Add SKLearnVectorStore
This PR adds SKLearnVectorStore, a simply vector store based on
NearestNeighbors implementations in the scikit-learn package. This
provides a simple drop-in vector store implementation with minimal
dependencies (scikit-learn is typically installed in a data scientist /
ml engineer environment). The vector store can be persisted and loaded
from json, bson and parquet format.
SKLearnVectorStore has soft (dynamic) dependency on the scikit-learn,
numpy and pandas packages. Persisting to bson requires the bson package,
persisting to parquet requires the pyarrow package.
## Before submitting
Integration tests are provided under
`tests/integration_tests/vectorstores/test_sklearn.py`
Sample usage notebook is provided under
`docs/modules/indexes/vectorstores/examples/sklear.ipynb`
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Add Momento as a standard cache and chat message history provider
This PR adds Momento as a standard caching provider. Implements the
interface, adds integration tests, and documentation. We also add
Momento as a chat history message provider along with integration tests,
and documentation.
[Momento](https://www.gomomento.com/) is a fully serverless cache.
Similar to S3 or DynamoDB, it requires zero configuration,
infrastructure management, and is instantly available. Users sign up for
free and get 50GB of data in/out for free every month.
## Before submitting
✅ We have added documentation, notebooks, and integration tests
demonstrating usage.
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
Add Multi-CSV/DF support in CSV and DataFrame Toolkits
* CSV and DataFrame toolkits now accept list of CSVs/DFs
* Add default prompts for many dataframes in `pandas_dataframe` toolkit
Fixes#1958
Potentially fixes#4423
## Testing
* Add single and multi-dataframe integration tests for
`pandas_dataframe` toolkit with permutations of `include_df_in_prompt`
* Add single and multi-CSV integration tests for csv toolkit
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
