- [Xorbits
Inference(Xinference)](https://github.com/xorbitsai/inference) is a
powerful and versatile library designed to serve language, speech
recognition, and multimodal models. Xinference supports a variety of
GGML-compatible models including chatglm, whisper, and vicuna, and
utilizes heterogeneous hardware and a distributed architecture for
seamless cross-device and cross-server model deployment.
- This PR integrates Xinference models and Xinference embeddings into
LangChain.
- Dependencies: To install the depenedencies for this integration, run
`pip install "xinference[all]"`
- Example Usage:
To start a local instance of Xinference, run `xinference`.
To deploy Xinference in a distributed cluster, first start an Xinference
supervisor using `xinference-supervisor`:
`xinference-supervisor -H "${supervisor_host}"`
Then, start the Xinference workers using `xinference-worker` on each
server you want to run them on.
`xinference-worker -e "http://${supervisor_host}:9997"`
To use Xinference with LangChain, you also need to launch a model. You
can use command line interface (CLI) to do so. Fo example: `xinference
launch -n vicuna-v1.3 -f ggmlv3 -q q4_0`. This launches a model named
vicuna-v1.3 with `model_format="ggmlv3"` and `quantization="q4_0"`. A
model UID is returned for you to use.
Now you can use Xinference with LangChain:
```python
from langchain.llms import Xinference
llm = Xinference(
server_url="http://0.0.0.0:9997", # suppose the supervisor_host is "0.0.0.0"
model_uid = {model_uid} # model UID returned from launching a model
)
llm(
prompt="Q: where can we visit in the capital of France? A:",
generate_config={"max_tokens": 1024},
)
```
You can also use RESTful client to launch a model:
```python
from xinference.client import RESTfulClient
client = RESTfulClient("http://0.0.0.0:9997")
model_uid = client.launch_model(model_name="vicuna-v1.3", model_size_in_billions=7, quantization="q4_0")
```
The following code block demonstrates how to use Xinference embeddings
with LangChain:
```python
from langchain.embeddings import XinferenceEmbeddings
xinference = XinferenceEmbeddings(
server_url="http://0.0.0.0:9997",
model_uid = model_uid
)
```
```python
query_result = xinference.embed_query("This is a test query")
```
```python
doc_result = xinference.embed_documents(["text A", "text B"])
```
Xinference is still under rapid development. Feel free to [join our
Slack
community](https://xorbitsio.slack.com/join/shared_invite/zt-1z3zsm9ep-87yI9YZ_B79HLB2ccTq4WA)
to get the latest updates!
- Request for review: @hwchase17, @baskaryan
- Twitter handle: https://twitter.com/Xorbitsio
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Added a new tool to the Github toolkit called **Create Pull Request.**
Now we can make our own langchain contributor in langchain 😁
In order to have somewhere to pull from, I also added a new env var,
"GITHUB_BASE_BRANCH." This will allow the existing env var,
"GITHUB_BRANCH," to be a working branch for the bot (so that it doesn't
have to always commit on the main/master). For example, if you want the
bot to work in a branch called `bot_dev` and your repo base is `main`,
you would set up the vars like:
```
GITHUB_BASE_BRANCH = "main"
GITHUB_BRANCH = "bot_dev"
```
Maintainer responsibilities:
- Agents / Tools / Toolkits: @hinthornw
# PromptTemplate
* Update documentation to highlight the classmethod for instantiating a
prompt template.
* Expand kwargs in the classmethod to make parameters easier to discover
In this PR:
- Removed restricted model loading logic for Petals-Bloom
- Removed petals imports (DistributedBloomForCausalLM,
BloomTokenizerFast)
- Instead imported more generalized versions of loader
(AutoDistributedModelForCausalLM, AutoTokenizer)
- Updated the Petals example notebook to allow for a successful
installation of Petals in Apple Silicon Macs
- Tag maintainer: @hwchase17, @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description:
This PR will enable the Open API chain to work with valid Open API
specifications missing `description` and `summary` properties for path
and operation nodes in open api specs.
Since both `description` and `summary` property are declared optional we
cannot be sure they are defined. This PR resolves this problem by
providing an empty (`''`) description as fallback.
The previous behavior of the Open API chain was that the underlying LLM
(OpenAI) throw ed an exception since `None` is not of type string:
```
openai.error.InvalidRequestError: None is not of type 'string' - 'functions.0.description'
```
Using this PR the Open API chain will succeed also using Open API specs
lacking `description` and `summary` properties for path and operation
nodes.
Thanks for your amazing work !
Tag maintainer: @baskaryan
---------
Co-authored-by: Lars Gersmann <lars.gersmann@cm4all.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
1. Upgrade the AwaDB from v0.3.7 to v0.3.9
2. Change the default embedding to AwaEmbedding
---------
Co-authored-by: ljeagle <awadb.vincent@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- Description: Adds AwaEmbeddings class for embeddings, which provides
users with a convenient way to do fine-tuning, as well as the potential
need for multimodality
- Tag maintainer: @baskaryan
Create `Awa.ipynb`: an example notebook for AwaEmbeddings class
Modify `embeddings/__init__.py`: Import the class
Create `embeddings/awa.py`: The embedding class
Create `embeddings/test_awa.py`: The test file.
---------
Co-authored-by: taozhiwang <taozhiwa@gmail.com>
Full set of params are missing from Vertex* LLMs when `dict()` method is
called.
```
>>> from langchain.chat_models.vertexai import ChatVertexAI
>>> from langchain.llms.vertexai import VertexAI
>>> chat_llm = ChatVertexAI()
l>>> llm = VertexAI()
>>> chat_llm.dict()
{'_type': 'vertexai'}
>>> llm.dict()
{'_type': 'vertexai'}
```
This PR just uses the same mechanism used elsewhere to expose the full
params.
Since `_identifying_params()` is on the `_VertexAICommon` class, it
should cover the chat and non-chat cases.
<!-- Thank you for contributing to LangChain!
Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
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.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
Spelling error fix
<!-- Thank you for contributing to LangChain!
Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
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.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
<!-- Thank you for contributing to LangChain!
Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
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.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
<!-- Thank you for contributing to LangChain!
Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
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.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
## Description
This commit introduces the `DropboxLoader` class, a new document loader
that allows loading files from Dropbox into the application. The loader
relies on a Dropbox app, which requires creating an app on Dropbox,
obtaining the necessary scope permissions, and generating an access
token. Additionally, the dropbox Python package is required.
The `DropboxLoader` class is designed to be used as a document loader
for processing various file types, including text files, PDFs, and
Dropbox Paper files.
## Dependencies
`pip install dropbox` and `pip install unstructured` for PDF reading.
## Tag maintainer
@rlancemartin, @eyurtsev (from Data Loaders). I'd appreciate some
feedback here 🙏 .
## Social Networks
https://github.com/rubenbarraganhttps://www.linkedin.com/in/rgbarragan/https://twitter.com/RubenBarraganP
---------
Co-authored-by: Ruben Barragan <rbarragan@Rubens-MacBook-Air.local>
Since the refactoring into sub-projects `libs/langchain` and
`libs/experimental`, the `make` targets `format_diff` and `lint_diff` do
not work anymore when running `make` from these subdirectories. Reason
is that
```
PYTHON_FILES=$(shell git diff --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
```
generates paths from the project's root directory instead of the
corresponding subdirectories. This PR fixes this by adding a
`--relative` command line option.
- Tag maintainer: @baskaryan
# [WIP] Tree of Thought introducing a new ToTChain.
This PR adds a new chain called ToTChain that implements the ["Large
Language Model Guided
Tree-of-Though"](https://arxiv.org/pdf/2305.08291.pdf) paper.
There's a notebook example `docs/modules/chains/examples/tot.ipynb` that
shows how to use it.
Implements #4975
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
- @hwchase17
- @vowelparrot
---------
Co-authored-by: Vadim Gubergrits <vgubergrits@outbox.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Optimizing important numerical code and making it run faster.
Performance went up by 1.48x (148%). Runtime went down from 138715us to
56020us
Optimization explanation:
The `cosine_similarity_top_k` function is where we made the most
significant optimizations.
Instead of sorting the entire score_array which needs considering all
elements, `np.argpartition` is utilized to find the top_k largest scores
indices, this operation has a time complexity of O(n), higher
performance than sorting. Remember, `np.argpartition` doesn't guarantee
the order of the values. So we need to use argsort() to get the indices
that would sort our top-k values after partitioning, which is much more
efficient because it only sorts the top-K elements, not the entire
array. Then to get the row and column indices of sorted top_k scores in
the original score array, we use `np.unravel_index`. This operation is
more efficient and cleaner than a list comprehension.
The code has been tested for correctness by running the following
snippet on both the original function and the optimized function and
averaged over 5 times.
```
def test_cosine_similarity_top_k_large_matrices():
X = np.random.rand(1000, 1000)
Y = np.random.rand(1000, 1000)
top_k = 100
score_threshold = 0.5
gc.disable()
counter = time.perf_counter_ns()
return_value = cosine_similarity_top_k(X, Y, top_k, score_threshold)
duration = time.perf_counter_ns() - counter
gc.enable()
```
@hwaking @hwchase17 @jerwelborn
Unit tests pass, I also generated more regression tests which all
passed.
Description: Adding support for custom index and scoring profile support
in Azure Cognitive Search
@hwchase17
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This change compacts the left-side Navbar (ToC) of the [API
Reference](https://api.python.langchain.com/en/latest/api_reference.html).
Now almost each namespace item is split into two lines. For example
`langchain.chat_models: Chat Models`
We remove the `Chat Models` and leave one the `langchain.chat_models`.
This effectively compacts the navbar and increases the main page's
usability. On my screen, it reduces # of lines in Toc from 28 t to 18,
which is huge.
Removing the namespace "title" (like `Chat Models`) does not remove any
information because the title is composed directly from the namespace.
API Reference users are developers. Usability for them is very
important. We see less text => we find faster.
This PR introduces async API support for Cohere, both LLM and
embeddings. It requires updating `cohere` package to `^4`.
Tagging @hwchase17, @baskaryan, @agola11
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
# Description:
**Add the possibility to keep text as Markdown in the ConfluenceLoader**
Add a bool variable that allows to keep the Markdown format of the
Confluence pages.
It is useful because it allows to use MarkdownHeaderTextSplitter as a
DataSplitter.
If this variable in set to True in the load() method, the pages are
extracted using the markdownify library.
# Issue:
[4407](https://github.com/langchain-ai/langchain/issues/4407)
# Dependencies:
Add the markdownify library
# Tag maintainer:
@rlancemartin, @eyurtsev
# Twitter handle:
FloBastinHeyI - https://twitter.com/FloBastinHeyI
---------
Co-authored-by: Florian Bastin <florian.bastin@octo.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Objects implementing Runnable: BasePromptTemplate, LLM, ChatModel,
Chain, Retriever, OutputParser
- [x] Implement Runnable in base Retriever
- [x] Raise TypeError in operator methods for unsupported things
- [x] Implement dict which calls values in parallel and outputs dict
with results
- [x] Merge in `+` for prompts
- [x] Confirm precedence order for operators, ideal would be `+` `|`,
https://docs.python.org/3/reference/expressions.html#operator-precedence
- [x] Add support for openai functions, ie. Chat Models must return
messages
- [x] Implement BaseMessageChunk return type for BaseChatModel, a
subclass of BaseMessage which implements __add__ to return
BaseMessageChunk, concatenating all str args
- [x] Update implementation of stream/astream for llm and chat models to
use new `_stream`, `_astream` optional methods, with default
implementation in base class `raise NotImplementedError` use
https://stackoverflow.com/a/59762827 to see if it is implemented in base
class
- [x] Delete the IteratorCallbackHandler (leave the async one because
people using)
- [x] Make BaseLLMOutputParser implement Runnable, accepting either str
or BaseMessage
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
