- **Description:** The HTMLHeaderTextSplitter Class now explicitly
specifies utf-8 encoding in the part of the split_text_from_file method
that calls the HTMLParser.
- **Issue:** Prevent garbled characters due to differences in encoding
of html files (except for English in particular, I noticed that problem
with Japanese).
- **Dependencies:** No dependencies,
- **Twitter handle:** @i_w__a
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
- FIX templates/retrieval-agent/retireval-agent/chain.py to use the new
Syntax for Azure env params
- cr
---------
Co-authored-by: braun-viathan <p.braun@viathan.de>
Co-authored-by: Braun-viathan <121631422+braun-viathan@users.noreply.github.com>
For tracing, if a validation error occurs, currently it is attributed to
the previous step of the chain. It would be nice to have the on_start
and on_error callbacks called for tools when there is a validation error
that occurs to more easily attribute the root-cause
**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
- **Description:** Updated the Chat/Ollama docs notebook with LCEL chain
examples
- **Issue:** #15664 I'm a new contributor 😊
- **Dependencies:** No dependencies
- **Twitter handle:**
Comments:
- How do I truncate the output of the stream in the notebook if and or
when it goes on and on and on for even the basic of prompts?
Edit:
Looking forward to feedback @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
## Problem
Spent several hours trying to figure out how to pass
`RedisChatMessageHistory` as a `GetSessionHistoryCallable` with a
different REDIS hostname. This example kept connecting to
`redis://localhost:6379`, but I wanted to connect to a server not hosted
locally.
## Cause
Assumption the user knows how to implement `BaseChatMessageHistory` and
`GetSessionHistoryCallable`
## Solution
Update documentation to show how to explicitly set the REDIS hostname
using a lambda function much like the MongoDB and SQLite examples.
After merging [PR
#16304](https://github.com/langchain-ai/langchain/pull/16304), I
realized that our notebook example for integrating TiDB with LangChain
was too basic. To make it more useful and user-friendly, I plan to
create a detailed example. This will show how to use TiDB for saving
history messages in LangChain, offering a clearer, more practical guide
for our users
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:** At the moment it's not possible to include in the
same project langchain-google-vertexai and boto3 (e.g. use bedrock and
vertex in the same application) because of the dependency resolutions
conflict. boto3 is still using urllib3 1.x, meanwhile
langchain-google-vertexai -> types-requests depends on urllib3 2.x. [the
last version of types-requests that allows urllib3 1.x is
2.31.0.6](https://pypi.org/project/types-requests/#description).
In this PR I allow the vertexai package to get that version also.
- **Twitter handle:** nicoloboschi
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 milvus multitenancy doc, it is an example for
this [pr](https://github.com/langchain-ai/langchain/pull/15740) .
- **Issue:** No,
- **Dependencies:** No,
- **Twitter handle:** No
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
**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")
```
The callbacks get started demo code was updated , replacing the
chain.run() command ( which is now depricated) ,with the updated
chain.invoke() command.
Solving the following issue : #16379
Twitter/X : @Hazxhx
- **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>
Adjusted `deprecate` decorator to make sure decorated async functions
are still recognized as "coroutinefunction" by `inspect`.
Before change, functions such as `LLMChain.acall` which are decorated as
deprecated are not recognized as coroutine functions. After the change,
they are recognized:
```python
import inspect
from langchain import LLMChain
# Is false before change but true after.
inspect.iscoroutinefunction(LLMChain.acall)
```
- **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
