This PR adds a Baseten integration. I've done my best to follow the
contributor's guidelines and add docs, an example notebook, and an
integration test modeled after similar integrations' test.
Please let me know if there is anything I can do to improve the PR. When
it is merged, please tag https://twitter.com/basetenco and
https://twitter.com/philip_kiely as contributors (the note on the PR
template said to include Twitter accounts)
# Your PR Title (What it does)
<!--
Thank you for contributing to LangChain! Your PR will appear in our
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.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
<!-- Remove if not applicable -->
Fixes # (issue)
## 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:
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @vowelparrot
VectorStores / Retrievers / Memory
- @dev2049
-->
#### Who can review?
Tag maintainers/contributors who might be interested:
@hwchase17 - project lead
- @agola11
---------
Co-authored-by: Yessen Kanapin <yessen@deepinfra.com>
<!--
Thank you for contributing to LangChain! Your PR will appear in our
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.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
In the [Databricks
integration](https://python.langchain.com/en/latest/integrations/databricks.html)
and [Databricks
LLM](https://python.langchain.com/en/latest/modules/models/llms/integrations/databricks.html),
we suggestted users to set the ENV variable `DATABRICKS_API_TOKEN`.
However, this is inconsistent with the other Databricks library. To make
it consistent, this PR changes the variable from `DATABRICKS_API_TOKEN`
to `DATABRICKS_TOKEN`
After changes, there is no more `DATABRICKS_API_TOKEN` in the doc
```
$ git grep DATABRICKS_API_TOKEN|wc -l
0
$ git grep DATABRICKS_TOKEN|wc -l
8
```
cc @hwchase17 @dev2049 @mengxr since you have reviewed the previous PRs.
Aviary is an open source toolkit for evaluating and deploying open
source LLMs. You can find out more about it on
[http://github.com/ray-project/aviary). You can try it out at
[http://aviary.anyscale.com](aviary.anyscale.com).
This code adds support for Aviary in LangChain. To minimize
dependencies, it connects directly to the HTTP endpoint.
The current implementation is not accelerated and uses the default
implementation of `predict` and `generate`.
It includes a test and a simple example.
@hwchase17 and @agola11 could you have a look at this?
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
<!--
Thank you for contributing to LangChain! Your PR will appear in our
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.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
<!-- Remove if not applicable -->
Fixes#5638. Retitles "Amazon Bedrock" page to "Bedrock" so that the
Integrations section of the left nav is properly sorted in alphabetical
order.
#### Who can review?
Tag maintainers/contributors who might be interested:
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @vowelparrot
VectorStores / Retrievers / Memory
- @dev2049
-->
# Bedrock LLM and Embeddings
This PR adds a new LLM and an Embeddings class for the
[Bedrock](https://aws.amazon.com/bedrock) service. The PR also includes
example notebooks for using the LLM class in a conversation chain and
embeddings usage in creating an embedding for a query and document.
**Note**: AWS is doing a private release of the Bedrock service on
05/31/2023; users need to request access and added to an allowlist in
order to start using the Bedrock models and embeddings. Please use the
[Bedrock Home Page](https://aws.amazon.com/bedrock) to request access
and to learn more about the models available in Bedrock.
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @vowelparrot
VectorStores / Retrievers / Memory
- @dev2049
-->
This PR adds a new method `from_es_connection` to the
`ElasticsearchEmbeddings` class allowing users to use Elasticsearch
clusters outside of Elastic Cloud.
Users can create an Elasticsearch Client object and pass that to the new
function.
The returned object is identical to the one returned by calling
`from_credentials`
```
# Create Elasticsearch connection
es_connection = Elasticsearch(
hosts=['https://es_cluster_url:port'],
basic_auth=('user', 'password')
)
# Instantiate ElasticsearchEmbeddings using es_connection
embeddings = ElasticsearchEmbeddings.from_es_connection(
model_id,
es_connection,
)
```
I also added examples to the elasticsearch jupyter notebook
Fixes # https://github.com/hwchase17/langchain/issues/5239
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Update llamacpp demonstration notebook
Add instructions to install with BLAS backend, and update the example of
model usage.
Fixes#5071. However, it is more like a prevention of similar issues in
the future, not a fix, since there was no problem in the framework
functionality
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
- @hwchase17
- @agola11
# docs: improve flow of llm caching notebook
The notebook `llm_caching` demos various caching providers. In the
previous version, there was setup common to all examples but under the
`In Memory Caching` heading.
If a user comes and only wants to try a particular example, they will
run the common setup, then the cells for the specific provider they are
interested in. Then they will get import and variable reference errors.
This commit moves the common setup to the top to avoid this.
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@dev2049
This PR adds LLM wrapper for Databricks. It supports two endpoint types:
* serving endpoint
* cluster driver proxy app
An integration notebook is included to show how it works.
Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com>
Co-authored-by: Gengliang Wang <gengliang@apache.org>
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 C Transformers for GGML Models
I created Python bindings for the GGML models:
https://github.com/marella/ctransformers
Currently it supports GPT-2, GPT-J, GPT-NeoX, LLaMA, MPT, etc. See
[Supported
Models](https://github.com/marella/ctransformers#supported-models).
It provides a unified interface for all models:
```python
from langchain.llms import CTransformers
llm = CTransformers(model='/path/to/ggml-gpt-2.bin', model_type='gpt2')
print(llm('AI is going to'))
```
It can be used with models hosted on the Hugging Face Hub:
```py
llm = CTransformers(model='marella/gpt-2-ggml')
```
It supports streaming:
```py
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
llm = CTransformers(model='marella/gpt-2-ggml', callbacks=[StreamingStdOutCallbackHandler()])
```
Please see [README](https://github.com/marella/ctransformers#readme) for
more details.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Beam
Calls the Beam API wrapper to deploy and make subsequent calls to an
instance of the gpt2 LLM in a cloud deployment. Requires installation of
the Beam library and registration of Beam Client ID and Client Secret.
Additional calls can then be made through the instance of the large
language model in your code or by calling the Beam API.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Add MosaicML inference endpoints
This PR adds support in langchain for MosaicML inference endpoints. We
both serve a select few open source models, and allow customers to
deploy their own models using our inference service. Docs are here
(https://docs.mosaicml.com/en/latest/inference.html), and sign up form
is here (https://forms.mosaicml.com/demo?utm_source=langchain). I'm not
intimately familiar with the details of langchain, or the contribution
process, so please let me know if there is anything that needs fixing or
this is the wrong way to submit a new integration, thanks!
I'm also not sure what the procedure is for integration tests. I have
tested locally with my api key.
## Who can review?
@hwchase17
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This PR introduces a new module, `elasticsearch_embeddings.py`, which
provides a wrapper around Elasticsearch embedding models. The new
ElasticsearchEmbeddings class allows users to generate embeddings for
documents and query texts using a [model deployed in an Elasticsearch
cluster](https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-model-ref.html#ml-nlp-model-ref-text-embedding).
### Main features:
1. The ElasticsearchEmbeddings class initializes with an Elasticsearch
connection object and a model_id, providing an interface to interact
with the Elasticsearch ML client through
[infer_trained_model](https://elasticsearch-py.readthedocs.io/en/v8.7.0/api.html?highlight=trained%20model%20infer#elasticsearch.client.MlClient.infer_trained_model)
.
2. The `embed_documents()` method generates embeddings for a list of
documents, and the `embed_query()` method generates an embedding for a
single query text.
3. The class supports custom input text field names in case the deployed
model expects a different field name than the default `text_field`.
4. The implementation is compatible with any model deployed in
Elasticsearch that generates embeddings as output.
### Benefits:
1. Simplifies the process of generating embeddings using Elasticsearch
models.
2. Provides a clean and intuitive interface to interact with the
Elasticsearch ML client.
3. Allows users to easily integrate Elasticsearch-generated embeddings.
Related issue https://github.com/hwchase17/langchain/issues/3400
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Fix typo + add wikipedia package installation part in
human_input_llm.ipynb
This PR
1. Fixes typo ("the the human input LLM"),
2. Addes wikipedia package installation part (in accordance with
`WikipediaQueryRun`
[documentation](https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html))
in `human_input_llm.ipynb`
(`docs/modules/models/llms/examples/human_input_llm.ipynb`)
OpenLM is a zero-dependency OpenAI-compatible LLM provider that can call
different inference endpoints directly via HTTP. It implements the
OpenAI Completion class so that it can be used as a drop-in replacement
for the OpenAI API. This changeset utilizes BaseOpenAI for minimal added
code.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Update GPT4ALL integration
GPT4ALL have completely changed their bindings. They use a bit odd
implementation that doesn't fit well into base.py and it will probably
be changed again, so it's a temporary solution.
Fixes#3839, #4628
# Documentation for Azure OpenAI embeddings model
- OPENAI_API_VERSION environment variable is needed for the endpoint
- The constructor does not work with model, it works with deployment.
I fixed it in the notebook.
(This is my first contribution)
## Who can review?
@hwchase17
@agola
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
# Docs: improvements in the `retrievers/examples/` notebooks
Its primary purpose is to make the Jupyter notebook examples
**consistent** and more suitable for first-time viewers.
- add links to the integration source (if applicable) with a short
description of this source;
- removed `_retriever` suffix from the file names (where it existed) for
consistency;
- removed ` retriever` from the notebook title (where it existed) for
consistency;
- added code to install necessary Python package(s);
- added code to set up the necessary API Key.
- very small fixes in notebooks from other folders (for consistency):
- docs/modules/indexes/vectorstores/examples/elasticsearch.ipynb
- docs/modules/indexes/vectorstores/examples/pinecone.ipynb
- docs/modules/models/llms/integrations/cohere.ipynb
- fixed misspelling in langchain/retrievers/time_weighted_retriever.py
comment (sorry, about this change in a .py file )
## Who can review
@dev2049
[RELLM](https://github.com/r2d4/rellm) is a library that wraps local
HuggingFace pipeline models for structured decoding.
RELLM works by generating tokens one at a time. At each step, it masks
tokens that don't conform to the provided partial regular expression.
[JSONFormer](https://github.com/1rgs/jsonformer) is a bit different, where it sequentially adds the keys then decodes each value directly
[Text Generation
Inference](https://github.com/huggingface/text-generation-inference) is
a Rust, Python and gRPC server for generating text using LLMs.
This pull request add support for self hosted Text Generation Inference
servers.
feature: #4280
---------
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
Related: #4028, I opened a new PR because (1) I was unable to unstage
mistakenly committed files (I'm not familiar with git enough to resolve
this issue), (2) I felt closing the original PR and opening a new PR
would be more appropriate if I changed the class name.
This PR creates HumanInputLLM(HumanLLM in #4028), a simple LLM wrapper
class that returns user input as the response. I also added a simple
Jupyter notebook regarding how and why to use this LLM wrapper. In the
notebook, I went over how to use this LLM wrapper and showed example of
testing `WikipediaQueryRun` using HumanInputLLM.
I believe this LLM wrapper will be useful especially for debugging,
educational or testing purpose.
In the section `Get Message Completions from a Chat Model` of the quick
start guide, the HumanMessage doesn't need to include `Translate this
sentence from English to French.` when there is a system message.
Simplify HumanMessages in these examples can further demonstrate the
power of LLM.
