# Make BaseEntityStore inherit from BaseModel
This enables initializing InMemoryEntityStore by optionally passing in a
value for the store field.
## Who can review?
It's a small change so I think any of the reviewers can review, but
tagging @dev2049 who seems most relevant since the change relates to
Memory.
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
# Fix wrong class instantiation in docs MMR example
<!--
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!
-->
When looking at the Maximal Marginal Relevance ExampleSelector example
at
https://python.langchain.com/en/latest/modules/prompts/example_selectors/examples/mmr.html,
I noticed that there seems to be an error. Initially, the
`MaxMarginalRelevanceExampleSelector` class is used as an
`example_selector` argument to the `FewShotPromptTemplate` class. Then,
according to the text, a comparison is made to regular similarity
search. However, the `FewShotPromptTemplate` still uses the
`MaxMarginalRelevanceExampleSelector` class, so the output is the same.
To fix it, I added an instantiation of the
`SemanticSimilarityExampleSelector` class, because this seems to be what
is intended.
## Who can review?
@hwchase17
# Replace loop appends with list comprehension.
It's significantly faster because it avoids repeated method lookup. It's
also more idiomatic and readable.
# Replace list comprehension with generator.
Since these strings can be fairly long, it's best to not construct
unnecessary temporary list just to pass it to `join`. Generators produce
items one-by-one and even though they are slightly more expensive than
lists in terms of CPU they are much more memory-friendly and slightly
more readable.
# Update Unstructured docs to remove the `detectron2` install
instructions
Removes `detectron2` installation instructions from the Unstructured
docs because installing `detectron2` is no longer required for
`unstructured>=0.7.0`. The `detectron2` model now runs using the ONNX
runtime.
## Who can review?
@hwchase17
@eyurtsev
# Add Managed Motorhead
This change enabled MotorheadMemory to utilize Metal's managed version
of Motorhead. We can easily enable this by passing in a `api_key` and
`client_id` in order to hit the managed url and access the memory api on
Metal.
Twitter: [@softboyjimbo](https://twitter.com/softboyjimbo)
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@dev2049 @hwchase17
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Skips creating boto client if passed in constructor
Current LLM and Embeddings class always creates a new boto client, even
if one is passed in a constructor. This blocks certain users from
passing in externally created boto clients, for example in SSO
authentication.
## Who can review?
@hwchase17
@jasondotparse
@rsgrewal-aws
<!-- 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
-->
# added DeepLearing.AI course link
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
not @hwchase17 - hehe
# Added support for download GPT4All model if does not exist
I've include the class attribute `allow_download` to the GPT4All class.
By default, `allow_download` is set to False.
## Changes Made
- Added a new attribute `allow_download` to the GPT4All class.
- Updated the `validate_environment` method to pass the `allow_download`
parameter to the GPT4All model constructor.
## Context
This change provides more control over model downloading in the GPT4All
class. Previously, if the model file was not found in the cache
directory `~/.cache/gpt4all/`, the package returned error "Failed to
retrieve model (type=value_error)". Now, if `allow_download` is set as
True then it will use GPT4All package to download it . With the addition
of the `allow_download` attribute, users can now choose whether the
wrapper is allowed to download the model or not.
## Dependencies
There are no new dependencies introduced by this change. It only
utilizes existing functionality provided by the GPT4All package.
## Testing
Since this is a minor change to the existing behavior, the existing test
suite for the GPT4All package should cover this scenario
Co-authored-by: Vokturz <victornavarrrokp47@gmail.com>
# 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
-->
# 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>
# SQLite-backed Entity Memory
Following the initiative of
https://github.com/hwchase17/langchain/pull/2397 I think it would be
helpful to be able to persist Entity Memory on disk by default
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
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>
# Added support for modifying the number of threads in the GPT4All model
I have added the capability to modify the number of threads used by the
GPT4All model. This allows users to adjust the model's parallel
processing capabilities based on their specific requirements.
## Changes Made
- Updated the `validate_environment` method to set the number of threads
for the GPT4All model using the `values["n_threads"]` parameter from the
`GPT4All` class constructor.
## Context
Useful in scenarios where users want to optimize the model's performance
by leveraging multi-threading capabilities.
Please note that the `n_threads` parameter was included in the `GPT4All`
class constructor but was previously unused. This change ensures that
the specified number of threads is utilized by the model .
## Dependencies
There are no new dependencies introduced by this change. It only
utilizes existing functionality provided by the GPT4All package.
## Testing
Since this is a minor change testing is not required.
---------
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>
# Adds ability to specify credentials when using Google BigQuery as a
data loader
Fixes#5465 . Adds ability to set credentials which must be of the
`google.auth.credentials.Credentials` type. This argument is optional
and will default to `None.
Co-authored-by: Dev 2049 <dev.dev2049@gmail.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>
Update [psychicapi](https://pypi.org/project/psychicapi/) python package
dependency to the latest version 0.5. The newest python package version
addresses breaking changes in the Psychic http api.
# 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.
# Added Async _acall to FakeListLLM
FakeListLLM is handy when unit testing apps built with langchain. This
allows the use of FakeListLLM inside concurrent code with
[asyncio](https://docs.python.org/3/library/asyncio.html).
I also changed the pydocstring which was out of date.
## Who can review?
@hwchase17 - project lead
@agola11 - async
# 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
)
```
This removes duplicate code presumably introduced by a cut-and-paste
error, spotted while reviewing the code in
```langchain/client/langchain.py```. The original code had back to back
occurrences of the following code block:
```
response = self._get(
path,
params=params,
)
raise_for_status_with_text(response)
```
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>
