Commit Graph

644 Commits

Author SHA1 Message Date
Pierre Alexandre SCHEMBRI
4a7ebb7184
Fix issue #7616 (#7617)
Fix Issue #7616 with a simpler approach to extract function names (use
`__name__` attribute)

@hwchase17

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-06 15:12:03 -07:00
Ankur Agarwal
797c9e92c8
#8786 Fixed: Callback handler disconnect in between (#8787)
Fixes for  #8786 @agola11 

- Description: The flow of callback is breaking till the last chain, as
callbacks are missed in between chain along nested path. This will help
get full trace and correlate parent child relationship in all nested
chains.

  - Issue: the issue #8786 
  - Dependencies: NA
  - Tag maintainer: @agola11 
  - Twitter handle: Agarwal_Ankur
2023-08-06 15:11:45 -07:00
William FH
983678dedc
Add Dist Metrics for String Distance Evaluation (#8837)
Co-authored-by: shibuiwilliam <shibuiyusuke@gmail.com>
2023-08-06 14:05:00 -07:00
William FH
f76d50d8dc
fix exception inconsistencies (#8812) (#8839)
Merge #8812 with main to fix unrelated test failure

Co-authored-by: shibuiwilliam <shibuiyusuke@gmail.com>
2023-08-06 14:04:49 -07:00
Bagatur
15c271e7b3
bump 254 (#8834) 2023-08-06 11:34:54 -07:00
Bagatur
d7b613a293
Bagatur/revert revert nuclia (#8833) 2023-08-06 11:24:36 -07:00
Bagatur
2f309a4ce6
Revert "Bagatur/nuclia (#8404)" (#8832) 2023-08-06 11:14:01 -07:00
Paul Hager
2111ed3c75
Improving the text of the invalid tool to list the available tools. (#8767)
Description: When using a ReAct Agent with tools and no tool is found,
the InvalidTool gets called. Previously it just asked for a different
action, but I've found that if you list the available actions it
improves the chances of getting a valid action in the next round. I've
added a UnitTest for it also.

@hinthornw
2023-08-05 18:09:32 -07:00
shibuiwilliam
d9bc46186d
Add missing test for retrievers self_query (#8783)
# What
- Add missing test for retrievers self_query
- Add missing import validation

<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: Add missing test for retrievers self_query
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @MlopsJ
  
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
 -->
2023-08-05 17:31:41 -07:00
Wilson Leao Neto
b0d0338f21
feat: expose Kendra result item id and document id as document metadata (#8796)
- Description: we expose Kendra result item id and document id as
document metadata.
  - Tag maintainer: @3coins @baskaryan 
  - Twitter handle: wilsonleao

**Why**
The result item id and document id might be used to keep track of the
retrieved resources.
2023-08-05 17:21:24 -07:00
Bagatur
9b86235a56
bump 253 (#8798) 2023-08-05 10:57:22 -07:00
Bagatur
9fc9018951
Bagatur/nuclia (#8404)
Co-authored-by: Eric BREHAULT <ebrehault@gmail.com>
2023-08-05 10:44:43 -07:00
William FH
1d68470bac
Same Project for Eval Runs (#8781) 2023-08-04 17:51:49 -07:00
William FH
c8f3615aa6
Support evaluating runnables and arbitrary functions (#8698)
Added a couple of "integration tests" for these that I ran.

Main design point of feedback: at this point, would it just be better to
have separate arguments for each type? Little confusing what is or isn't
supported and what is the intended usage at this point since I try to
wrap the function as runnable or pack or unpack chains/llms.

```
run_on_dataset(
...
llm_or_chain_factory = None,
llm = None,
chain = NOne,
runnable=None,
function=None
):
# raise error if none set
```

Downside with runnables and arbitrary function support is that you get
much less helpful validation and error messages, but I don't think we
should block you from this, at least.
2023-08-04 16:39:04 -07:00
liguoqinjim
d00a247da7
fix:get bilibili subtitles (#8165)
- Description: fix the Loader 'BiliBiliLoader'
  - Issue: the API response was changed

![image](https://github.com/langchain-ai/langchain/assets/2113954/91216793-82f8-4c82-a018-d49f36f5f6aa)
The previously used API no longer returns the "subtitle_url" property.

![image](https://github.com/langchain-ai/langchain/assets/2113954/a8ec2a7a-f40d-4c2a-b7d0-0ccdf2b327cc)
We should use another API to get `subtitle_url` property. 
The `subtitle_url` returned by this API does not include the http schema
and needs to be added.

  - Dependencies: Nope
  - Tag maintainer: @rlancemartin
2023-08-04 14:30:41 -07:00
Bagatur
f437311eef
Bagatur/runnable with fallbacks (#8543) 2023-08-04 14:06:05 -07:00
Piyush Jain
8374367de2
Amazon Textract as document loader (#8661)
Description: Adding support for [Amazon
Textract](https://aws.amazon.com/textract/) as a PDF document loader

---------

Co-authored-by: schadem <45048633+schadem@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-04 15:55:06 -04:00
Leonid Ganeline
82ef1f587d
fix makefile help (#8723)
Fixed the `makefile` help. It was not up-to-date.
 @baskaryan
2023-08-04 15:37:00 -04:00
Neil Murphy
b0d0399d34
(issue #5163) Append reminder to nest multi-prompt router prompt output in JSON markdown code block, resolving JSON parsing error. (#8709)
Resolves occasional JSON parsing error when some predictions are passed
through a `MultiPromptChain`.

Makes [this
modification](https://github.com/langchain-ai/langchain/issues/5163#issuecomment-1652220401)
to `multi_prompt_prompt.py`, which is much cleaner than appending an
entire example object, which is another community-reported solution.

@hwchase17, @baskaryan

cc: @SimasJan
2023-08-04 15:36:34 -04:00
rjanardhan3
affaaea87b
Updates fireworks (#8765)
<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: Updates to Fireworks Documentation, 
  - Issue: N/A,
  - Dependencies: N/A,
  - Tag maintainer: @rlancemartin,

---------

Co-authored-by: Raj Janardhan <rajjanardhan@Rajs-Laptop.attlocal.net>
2023-08-04 10:32:22 -07:00
Bagatur
e45be8b3f6
bump 252 (#8759) 2023-08-04 08:22:16 -07:00
Bagatur
0d5a90f30a
Revert "add filter to sklearn vector store functions (#8113)" (#8760) 2023-08-04 08:13:32 -07:00
Bagatur
115a77142a
support for arbitrary kwargs for llamacpp (#8727)
llamacpp params (per their own code) are unstable, so instead of
adding/deleting them constantly adding a model_kwargs parameter that
allows for arbitrary additional kwargs

cc @jsjolund and @zacps re #8599 and #8704
2023-08-04 06:52:02 -07:00
Alec Flett
f0b0c72d98
add load() deserializer function that bypasses need for json serialization (#7626)
There is already a `loads()` function which takes a JSON string and
loads it using the Reviver

But in the callbacks system, there is a `serialized` object that is
passed in and that object is already a deserialized JSON-compatible
object. This allows you to call `load(serialized)` and bypass
intermediate JSON encoding.

I found one other place in the code that benefited from this
short-circuiting (string_run_evaluator.py) so I fixed that too.

Tagging @baskaryan for general/utility stuff.

<!-- 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!

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
 -->

---------

Co-authored-by: Nuno Campos <nuno@boringbits.io>
2023-08-04 09:49:41 +01:00
Ruiqi Guo
6aee589eec
Add ScaNN support in vectorstore. (#8251)
Description: Add ScaNN vectorstore to langchain.
ScaNN is a Open Source, high performance vector similarity library
optimized for AVX2-enabled CPUs.
https://github.com/google-research/google-research/tree/master/scann

- Dependencies: scann

Python notebook to illustrate the usage:
docs/extras/integrations/vectorstores/scann.ipynb
Integration test:
libs/langchain/tests/integration_tests/vectorstores/test_scann.py

@rlancemartin, @eyurtsev for review.

Thanks!
2023-08-03 23:41:30 -07:00
Moonsik Kang
5b7ff215e8
Fix load map reduce documents chain (#7915)
This PR updates _load_reduce_documents_chain to handle
`reduce_documents_chain` and `combine_documents_chain` config

Please review @hwchase17, @baskaryan

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 23:27:38 -07:00
shibuiwilliam
0f0ccfe7f6
add filter to sklearn vector store functions (#8113)
# What
- This is to add filter option to sklearn vectore store functions

<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: Add filter to sklearn vectore store functions.
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @MlopsJ

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
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 23:06:41 -07:00
shibuiwilliam
2759e2d857
add save and load tfidf vectorizer and docs for TFIDFRetriever (#8112)
This is to add save_local and load_local to tfidf_vectorizer and docs in
tfidf_retriever to make the vectorizer reusable.

<!-- Thank you for contributing to LangChain!

Replace this comment with:
- Description: add save_local and load_local to tfidf_vectorizer and
docs in tfidf_retriever
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @MlopsJ

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
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 23:06:27 -07:00
aerickson-clt
0f68054401
Issue #8089 Improve painless script scoring with params.query_value. (#8086)
This is a minor improvement that replaces the full query_vector with the
reference string `params.query_value` used in the painless scripting
docs. I have tested it manually and it works on an example. This makes
the query about half the size and much easier to read.


https://opensearch.org/docs/latest/search-plugins/knn/painless-functions/#get-started-with-k-nns-painless-scripting-functions

@babbldev 
#8089

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 23:06:17 -07:00
linpan
0ead8ea708
typo: ignored to ignore (#8740)
<!-- 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
 -->
2023-08-03 23:05:59 -07:00
aerickson-clt
c7ea6e9ff8
Issue 8081 Fix query results size bug. Other bug: pass vector_field param. (#8085)
@baskaryan
#8081 

Likely the reason why the issue occurred is that OpenSearch's default k
is 10, so it needs to be specified.

Here's a similar question about its cousin ElasticSearch

https://discuss.elastic.co/t/elasticsearch-returns-only-10-records-but-the-hit-is-507/136605

I tested this manually and also fixed the same issue in
`_default_painless_scripting_query`. In addition,
`_default_painless_scripting_query` was not passing the `vector_field`
name to a sub call, so I fixed that too.


![image](https://github.com/hwchase17/langchain/assets/32244272/cfb7aad1-f701-49d9-9beb-a723aa276817)

I also tested this in the aws opensearch developer tools.


![image](https://github.com/hwchase17/langchain/assets/32244272/24544682-1578-4bbb-9eb5-980463c5b41b)

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 22:41:11 -07:00
Sidchat95
812419d946
Removing score threshold parameter of faiss _similarity_search_with_r… (#8093)
Removing score threshold parameter of faiss
_similarity_search_with_relevance_scores as the thresholding part is
implemented in similarity_search_with_relevance_scores method which
calls this method.

As this method is supposed to be a private method of faiss.py this will
never receive the score threshold parameter as it is popped in the super
method similarity_search_with_relevance_scores.

@baskaryan @hwchase17
2023-08-03 21:31:43 -07:00
Mathias Panzenböck
873a80e496
Reduce generation of temporary objects (#7950)
Just a tiny change to use `list.append(...)` and `list.extend(...)`
instead of `list += [...]` so that no unnecessary temporary lists are
created.

Since its a tiny miscellaneous thing I guess @baskaryan is the
maintainer to tag?

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 21:24:08 -07:00
Lance Martin
d1b95db874
Retriever that can re-phase user inputs (#8026)
Simple retriever that applies an LLM between the user input and the
query pass the to retriever.

It can be used to pre-process the user input in any way.

The default prompt:

```
DEFAULT_QUERY_PROMPT = PromptTemplate(
    input_variables=["question"],
    template="""You are an assistant tasked with taking a natural languge query from a user
    and converting it into a query for a vectorstore. In this process, you strip out
    information that is not relevant for the retrieval task. Here is the user query: {question} """
)
```

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 21:23:59 -07:00
Harrison Chase
6c3573e7f6
Harrison/aleph alpha (#8735)
Co-authored-by: PiotrMazurek <piotr.mazurek@aleph-alpha.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-03 21:21:15 -07:00
Wilson Leao Neto
179a39954d
Provides access to a Document page_content formatter in the AmazonKendraRetriever (#8034)
- Description: 
- Provides a new attribute in the AmazonKendraRetriever which processes
a ResultItem and returns a string that will be used as page_content;
- The excerpt metadata should not be changed, it will be kept as was
retrieved. But it is cleaned when composing the page_content;
    - Refactors the AmazonKendraRetriever to improve code reusability;
- Issue: #7787 
- Tag maintainer: @3coins @baskaryan
- Twitter handle: wilsonleao

**Why?**

Some use cases need to adjust the page_content by dynamically combining
the ResultItem attributes depending on the context of the item.
2023-08-03 20:54:49 -07:00
Ilya
6f0bccfeb5
Add regex control over separators in character text splitter (#7933)
<!-- 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
 -->
#7854

Added the ability to use the `separator` ase a regex or a simple
character.
Fixed a bug where `start_index` was incorrectly counting from -1.

Who can review?
@eyurtsev
@hwchase17 
@mmz-001
2023-08-03 20:25:23 -07:00
Vasileios Mansolas
e68a1d73d0
Fix Issue #6650: Enable Azure Active Directory token-based auth access for AzureChatOpenAI (#8622)
When using AzureChatOpenAI the openai_api_type defaults to "azure". The
utils' get_from_dict_or_env() function triggered by the root validator
does not look for user provided values from environment variables
OPENAI_API_TYPE, so other values like "azure_ad" are replaced with
"azure". This does not allow the use of token-based auth.

By removing the "default" value, this allows environment variables to be
pulled at runtime for the openai_api_type and thus enables the other
api_types which are expected to work.

This fixes #6650

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-03 20:21:41 -07:00
Alec Flett
5d765408ce
propagate callbacks through load_summarize_chain (#7565)
This lets you pass callbacks when you create the summarize chain:

```
summarize = load_summarize_chain(llm, chain_type="map_reduce", callbacks=[my_callbacks])
summary = summarize(documents)
```
See #5572 for a similar surgical fix.

tagging @hwchase17 for callbacks work

<!-- 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!

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
 -->
2023-08-03 20:12:34 -07:00
Alec Flett
404d103c41
propagate RetrievalQA chain callbacks through its own LLMChain and StuffDocumentsChain (#7853)
This is another case, similar to #5572 and #7565 where the callbacks are
getting dropped during construction of the chains.

tagging @hwchase17 and @agola11 for callbacks propagation

<!-- 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!

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
 -->
2023-08-03 20:11:58 -07:00
Bal Narendra Sapa
47eea32f6a
add serializer methods (#7914)
Description: I have added two methods serializer and deserializer
methods. There was method called save local but it saves the to the
local disk. I wanted the vectorstore in the format using which i can
push it to the sql database's blob field. I have used this while i was
working on something

@rlancemartin, @eyurtsev

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-08-03 20:10:35 -07:00
Ryan Sloan
b786335dd1
fix RecursiveUrlLoader (#8582)
Description: the recursive url loader does not fully crawl for all urls
under base url
Maintainer: @baskaryan
2023-08-03 16:51:57 -07:00
William FH
f81e613086
Fix Async Retry Event Handling (#8659)
It fails currently because the event loop is already running.

The `retry` decorator alraedy infers an `AsyncRetrying` handler for
coroutines (see [tenacity
line](aa6f8f0a24/tenacity/__init__.py (L535)))
However before_sleep always gets called synchronously (see [tenacity
line](aa6f8f0a24/tenacity/__init__.py (L338))).


Instead, check for a running loop and use that it exists. Of course,
it's running an async method synchronously which is not _nice_. Given
how important LLMs are, it may make sense to have a task list or
something but I'd want to chat with @nfcampos on where that would live.

This PR also fixes the unit tests to check the handler is called and to
make sure the async test is run (it looks like it's just been being
skipped). It would have failed prior to the proposed fixes but passes
now.
2023-08-03 15:02:16 -07:00
ruze
8ef7e14a85
RSS Feed / OPML loader (#8694)
Replace this comment with:
- Description: added a document loader for a list of RSS feeds or OPML.
It iterates through the list and uses NewsURLLoader to load each
article.
  - Issue: N/A
  - Dependencies: feedparser, listparser
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @ruze

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-03 14:58:06 -07:00
sumandeng
53e4148a1b
add model_revison parameter to ModelScopeEmbeddings (#8669)
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-03 14:17:48 -07:00
Yoshi
4e8f11b36a
Deterministic Fake Embedding Model (#8706)
Solves #8644 
This embedding models output identical random embedding vectors, given
the input texts are identical.
Useful when used in unittest.
@baskaryan
2023-08-03 13:36:45 -07:00
Leonid Kuligin
2928a1a3c9
added minimum expected version of SDK to the error description (#8712)
#7932

Co-authored-by: Leonid Kuligin <kuligin@google.com>
2023-08-03 13:28:42 -07:00
Harrison Chase
814faa9de5
relax deps for yaml (#8713)
context: https://github.com/yaml/pyyaml/issues/724

I think this is fine? I don't think we use yaml too heavily
2023-08-03 13:22:17 -07:00
Holt Skinner
8a8917e0d9
feat: Add Spell Correction Spec to Google Cloud Enterprise Search connector (#8705) 2023-08-03 13:38:45 -04:00
Bagatur
b2b71b0d35
Bagatur/eden llm (#8670)
Co-authored-by: RedhaWassim <rwasssim@gmail.com>
Co-authored-by: KyrianC <ckyrian@protonmail.com>
Co-authored-by: sam <melaine.samy@gmail.com>
2023-08-03 10:24:51 -07:00
William FH
8022293124
lint (#8702) 2023-08-03 09:33:28 -07:00
William FH
a137492b53
Permit none key in chain mapper (#8696) 2023-08-03 08:50:36 -07:00
Bagatur
e283dc8d50
bump 251 (#8690) 2023-08-03 06:28:36 -07:00
Eugene Yurtsev
81e0cbf2d5
Minor typo fix (#8657)
Fix typo in doc-string.
2023-08-02 23:20:25 -07:00
Harrison Chase
43dffe39fb
Harrison/conversational retrieval agent (#8639)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-02 18:05:15 -07:00
ruze
71f98db2fe
Newspaper (#8647)
- Description: Added newspaper3k based news article loader. Provide a
list of urls.
  - Issue: N/A
  - Dependencies: newspaper3k,
  - Tag maintainer: @rlancemartin , @eyurtsev 
  - Twitter handle: @ruze

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-02 17:56:08 -07:00
shibuiwilliam
f68f3b23d7
add missing RemoteLangChainRetriever _get_relevant_documents test (#8628)
# What
- Add missing RemoteLangChainRetriever _get_relevant_documents test

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-02 17:20:40 -07:00
William FH
206901fa01
Use salt instead of datetime (#8653)
If you want to kick off two runs at the same time it'll cause errors.
Use a uuid instead
2023-08-02 17:15:50 -07:00
William FH
7ea2b08d1f
Use call directly for chain (#8655)
for run_on_dataset since the `run()` method requires a single output
2023-08-02 17:11:39 -07:00
William FH
368aa4ede7
fix enum error message (#8652)
could be a string so don't directly call value
2023-08-02 17:11:27 -07:00
Erick Friis
96b0ff182e
Enterprise support form wording (#8641) 2023-08-02 15:18:20 -07:00
Will Thompson
ee1d13678e
🐛 Docs Fixes [2 one-liners, examples broken] (#8519)
## Description: 
   
1)Map reduce example in docs is missing an important import statement.
Figured other people would benefit from being able to copy 🍝 the code.

2)RefineDocumentsChain example also broken.

## Issue: 

None

## Dependencies:

None. One liner.

## Tag maintainer:

@baskaryan

## Twitter handle: 

I mean, it's a one line fix lol. But @will_thompson_k is my twitter
handle.
2023-08-02 13:39:41 -07:00
Kacper Łukawski
16551536e3
Refactor Qdrant integration (#8634)
This small PR introduces new parameters into Qdrant (`on_disk`), fixes
some tests and changes the error message to be more clear.

Tagging: @baskaryan, @rlancemartin, @eyurtsev
2023-08-02 10:30:18 -07:00
Erick Friis
c5fb3b6069
Enterprise support form in airtable (#8607) 2023-08-02 09:49:59 -07:00
Eugene Yurtsev
1ec0b18379
Re-add __add__ functionality for messages (revert #8245) (#8489)
This PR reverts #8245, so `__add__` is defined on base messages.

Resolves issue: https://github.com/langchain-ai/langchain/issues/8472
2023-08-02 10:51:44 -04:00
Bagatur
f31047a394
bump 250 (#8632) 2023-08-02 07:47:36 -07:00
Comendeiro
5c516945d0
Add local support for audio models (PR #7329) (#7591)
- Description: run the poetry dependencies
  - Issue: #7329 
  - Dependencies: any dependencies required for this change,
  - Tag maintainer: @rlancemartin

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-02 01:24:53 -07:00
Naveen Tatikonda
d2adec3818
[Opensearch] : Fix the service validation in http_auth (#8609)
### Description
OpenSearch supports validation using both Master Credentials (Username
and password) and IAM. For Master Credentials users will not pass the
argument `service` in `http_auth` and the existing code will break. To
fix this, I have updated the condition to check if service attribute is
present in http_auth before accessing it.

### Maintainers
@baskaryan @navneet1v

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-08-02 01:16:38 -07:00
Harrison Chase
7c5c0557cb
cast to string when measuring token length (#8617) 2023-08-02 00:12:59 -07:00
rjanardhan3
68113348cc
Fireworks integration (#8322)
Description - Integrates Fireworks within Langchain LLMs to allow users
to use Fireworks models with Langchain, mainly for summarization.

Issue - Not applicable
Dependencies - None
Tag maintainer - @rlancemartin

---------

Co-authored-by: Raj Janardhan <rajjanardhan@Rajs-Laptop.attlocal.net>
2023-08-01 21:17:26 -07:00
Bagatur
b574507c51
normalized openai embeddings embed_query (#8604)
we weren't normalizing when embedding queries
2023-08-01 17:12:10 -07:00
Taqi Jaffri
4806504ebc Fixed one last key name 2023-08-01 15:43:26 -07:00
Neil Murphy
31820a31e4
Add firestore_client param to FirestoreChatMessageHistory if caller already has one; also lets them specify GCP project, etc. (#8601)
Existing implementation requires that you install `firebase-admin`
package, and prevents you from using an existing Firestore client
instance if available.

This adds optional `firestore_client` param to
`FirestoreChatMessageHistory`, so users can just use their existing
client/settings. If not passed, existing logic executes to initialize a
`firestore_client`.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-01 15:42:13 -07:00
Naveen Tatikonda
13ccf202de
[OpenSearch] : Fix AOSS Initialization (#8600)
### Description
This PR fixes the AOSS Initialization in Opensearch.

### Maintainers
@rlancemartin, @eyurtsev, @navneet1v

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-08-01 15:33:51 -07:00
Joshua Carroll
6705928b9d
Add StreamlitChatMessageHistory (#8497)
Add a StreamlitChatMessageHistory class that stores chat messages in
[Streamlit's Session
State](https://docs.streamlit.io/library/api-reference/session-state).

Note: The integration test uses a currently-experimental Streamlit
testing framework to simulate the execution of a Streamlit app. Marking
this PR as draft until I confirm with the Streamlit team that we're
comfortable supporting it.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-01 14:28:15 -07:00
brettdbrewer
2de028834f
updated to use new llm_util query (#8591)
- Description: added memgraph_graph.py which defines the MemgraphGraph
class, subclassing off the existing Neo4jGraph class. This lets you
query the Memgraph graph database using natural language. It leverages
the Neo4j drivers and the bolt protocol.
- Dependencies: since it is a subclass off of Neo4jGraph, it is
dependent on it and the GraphCypherQA Chain implementations. It is
dependent on the Neo4j drivers being present. It is dependent on having
a running Memgraph instance to connect to.
  - Tag maintainer: @baskaryan
  - Twitter handle: @villageideate
- example usage can be seen in this repo
https://github.com/brettdbrewer/MemgraphGraph/

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-01 14:16:15 -07:00
Tesfagabir Meharizghi
a7000ee89e
Callback handler for Amazon SageMaker Experiments (#8587)
## Description

This PR implements a callback handler for SageMaker Experiments which is
similar to that of mlflow.
* When creating the callback handler, it takes the experiment's run
object as an argument. All the callback outputs are then logged to the
run object.
* The output of each callback action (e.g., `on_llm_start`) is saved to
S3 bucket as json file.
* Optionally, you can also log additional information such as the LLM
hyper-parameters to the same run object.
* Once the callback object is no more needed, you will need to call the
`flush_tracker()` method. This makes sure that any intermediate files
are deleted.
* A separate notebook example is provided to show how the callback is
used.

@3coins  @agola11

---------

Co-authored-by: Tesfagabir Meharizghi <mehariz@amazon.com>
2023-08-01 13:47:08 -07:00
Harrison Chase
9c2b29a1cb
Harrison/loader bug (#8559)
Co-authored-by: ddroghini <d.droghini@mflgroup.com>
Co-authored-by: Buckler89 <Droghini.diego@gmail.com>
2023-08-01 13:31:49 -07:00
Kristelle Widjaja
f190bc3e83
Bug fix: feature/issue-7804-chroma-client_settings-bug (#8267)
Description: Made Chroma constructor more robust when client_settings is
provided. Otherwise, existing embeddings will not be loaded correctly
from Chroma.
Issue: #7804
Dependencies: None
Tag maintainer: @rlancemartin, @eyurtsev

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-01 13:31:35 -07:00
Taqi Jaffri
96843f3bd4 Fixed source key name for docugami loader 2023-08-01 12:54:26 -07:00
mpb159753
7df2dfc4c2
Add Support for Loading Documents from Huawei OBS (#8573)
Description:
This PR adds support for loading documents from Huawei OBS (Object
Storage Service) in Langchain. OBS is a cloud-based object storage
service provided by Huawei Cloud. With this enhancement, Langchain users
can now easily access and load documents stored in Huawei OBS directly
into the system.

Key Changes:
- Added a new document loader module specifically for Huawei OBS
integration.
- Implemented the necessary logic to authenticate and connect to Huawei
OBS using access credentials.
- Enabled the loading of individual documents from a specified bucket
and object key in Huawei OBS.
- Provided the option to specify custom authentication information or
obtain security tokens from Huawei Cloud ECS for easy access.

How to Test:
1. Ensure the required package "esdk-obs-python" is installed.
2. Configure the endpoint, access key, secret key, and bucket details
for Huawei OBS in the Langchain settings.
3. Load documents from Huawei OBS using the updated document loader
module.
4. Verify that documents are successfully retrieved and loaded into
Langchain for further processing.

Please review this PR and let us know if any further improvements are
needed. Your feedback is highly appreciated!

@rlancemartin, @eyurtsev

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-01 09:30:30 -07:00
Leonid Ganeline
ed9a0f8185
Docstrings: Module descriptions (#8262)
Added/changed the module descriptions (the firs-line docstrings in the
`__init__` files).
Added class hierarchy info.
 @baskaryan
2023-08-01 09:12:32 -07:00
shibuiwilliam
465faab935
fix apparent spelling inconsistencies (#8574)
Use ImportErrors where appropriate
2023-08-01 09:09:09 -07:00
Nuno Campos
0ec020698f
Add new run types for Runnables (#8488)
- allow overriding run_type in on_chain_start

<!-- 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
 -->
2023-08-01 12:56:40 +01:00
Bagatur
bd2e298468
bump 249 (#8571) 2023-08-01 01:20:16 -07:00
William FH
e83250cc5f
Rm RunTypeEnum (#8553)
We already support raw strings in the SDK but would like to deprecate
client-side validation of run types. This removes its usage
2023-08-01 07:32:07 +01:00
Jacob Lee
2a26cc6d2b
Fix combining runnable sequences (#8557)
Combining runnable sequences was dropping a step in the middle.

@nfcampos @baskaryan
2023-07-31 18:17:46 -07:00
Mohamad Zamini
3fbb737bb3
Update combined.py (#7541)
from my understanding, the `check_repeated_memory_variable` validator
will raise an error if any of the variables in the `memories` list are
repeated. However, the `load_memory_variables` method does not check for
repeated variables. This means that it is possible for the
`CombinedMemory` instance to return a dictionary of memory variables
that contains duplicate values. This code will check for repeated
variables in the `data` dictionary returned by the
`load_memory_variables` method of each sub-memory. If a repeated
variable is found, an error will be raised.

<!-- 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!

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
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-31 18:15:00 -07:00
yangdihang
ff5024634e
fix: openapi controller prompt, when bot is unable to resolve an api … (#7525)
…call, it needs retry

<!-- 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!

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
 -->

Co-authored-by: yangdihang <yangdihang@bytedance.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-31 17:56:43 -07:00
Kenny
1e8fca5518
Add ConcurrentLoader (#7512)
Works just like the GenericLoader but concurrently for those who choose
to optimize their workflow.

@rlancemartin @eyurtsev

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-31 17:56:31 -07:00
Kevin Buckley
8061994c61
AzureSearch Vector Store: Moving the usage of additional_fields into context of it's definition (bug fix from python error) (#8551)
Description: Using Azure Cognitive Search as a VectorStore. Calling the
`add_texts` method throws an error if there is no metadata property
specified. The `additional_fields` field is set in an `if` statement and
then is used later outside the if statement. This PR just moves the
declaration of `additional_fields` below and puts the usage of it in
context.

Issue: https://github.com/langchain-ai/langchain/issues/8544

Tagging @rlancemartin, @eyurtsev as this is related to Vector stores.

`make format`, `make lint`, `make spellcheck`, and `make test` have been
run
2023-07-31 17:25:57 -07:00
Pranay Chandekar
7e70cd2a28
Bug Fix - #8415 (#8417)
- Issue: #8415

Signed-off-by: Pranay Chandekar <pranayc6@gmail.com>
2023-07-31 17:08:46 -07:00
shibuiwilliam
de61ebd9e0
add tests to redis vectorstore (#8116)
# What
- Add function to get similarity with score with threshold in Redis
vector store.
- Add tests to Redis vector store.
2023-07-31 17:07:09 -07:00
Bruno Bornsztein
5a490a79f4
fix issue #8357 by making json backtick regex greedy (#8528)
- Description: Markdown code blocks in json response should not break
the parser
  - Issue: #8357

@baskaryan @hinthornw
2023-07-31 16:36:57 -07:00
Gordon Clark
64d0a0fcc0
Updating docstings in utilities (#8411)
Updating docstrings on utility packages
 @baskaryan
2023-07-31 16:34:53 -07:00
Mohammad Mohtashim
144b4c0c78
SQL Query Prompt update + added _execute method for SQLDatabase (#8100)
- Description: This pull request (PR) includes two minor changes:

1. Updated the default prompt for SQL Query Checker: The current prompt
does not clearly specify the final response that the LLM (Language
Model) should provide when checking for the query if `use_query_checker`
is enabled in SQLDatabase Chain. As a result, the LLM adds extra words
like "Here is your updated query" to the response. However, this causes
a syntax error when executing the SQL command in SQLDatabaseChain, as
these additional words are also included in the SQL query.

2. Moved the query's execution part into a separate method for
SQLDatabase: The purpose of this change is to provide users with more
flexibility when obtaining the result of an SQL query in the original
form returned by sqlalchemy. In the previous implementation, the run
method returned the results as a string. By creating a distinct method
for execution, users can now receive the results in original format,
which proves helpful in various scenarios. For example, during the
development of a tool, I found it advantageous to obtain results in
original format rather than a string, as currently done by the run
method.

- Tag maintainer: @hinthornw

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-31 16:28:08 -07:00
Matthew DeGuzman
844eca98d5
Add LLaMa Formatter and AzureML Chat Endpoint (#8382)
## Description

Microsoft and Meta recently [announced their
collaboration](https://blogs.microsoft.com/blog/2023/07/18/microsoft-and-meta-expand-their-ai-partnership-with-llama-2-on-azure-and-windows/)
on LLaMa2. This PR extends the current LLM wrapper and introduces a new
Chat Model wrapper for AzureML to support LLaMa2.

## Dependencies

No dependencies added :)

## Twitter Handles

[@matthew_d13](https://twitter.com/matthew_d13)
[@prakhar_in](https://twitter.com/prakhar_in)

maintainers - @hwchase17, @baskaryan
2023-07-31 16:26:25 -07:00
Harrison Chase
15de57b848
fix web loader (#8538) 2023-07-31 12:47:33 -07:00
Nuno Campos
4780156955
Rely less on positional arg order in subclasses of vector store when calling async methods (#8534) 2023-07-31 20:13:11 +01:00
Harrison Chase
5e3b968078
router runnable (#8496)
Co-authored-by: Nuno Campos <nuno@boringbits.io>
2023-07-31 11:07:10 -07:00
Anubhav Bindlish
913a156cff
Minor improvements to rockset vectorstore (#8416)
This PR makes minor improvements to our python notebook, and adds
support for `Rockset` workspaces in our vectorstore client.

@rlancemartin, @eyurtsev

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-31 09:54:59 -07:00
Bagatur
a8be207ea3
bump 248 (#8518) 2023-07-31 07:14:45 -07:00
Harrison Chase
6556a8fcfd
add initial anthropic agent (#8468)
Co-authored-by: Nuno Campos <nuno@boringbits.io>
2023-07-30 21:30:49 -07:00
os1ma
a795c3d860
Fix GitLoader to handle repeated load calls (#8412)
**Description: a description of the change**

In this pull request, GitLoader has been updated to handle multiple load
calls, provided the same repository is being cloned. Previously, calling
`load` multiple times would raise an error if a clone URL was provided.

Additionally, a check has been added to raise a ValueError when
attempting to clone a different repository into an existing path.

New tests have also been introduced to verify the correct behavior of
the GitLoader class when `load` is called multiple times.

Lastly, the GitPython package, a dependency for the GitLoader class, has
been added to the project dependencies (pyproject.toml and poetry.lock).

**Issue: the issue # it fixes (if applicable)**

None

**Dependencies: any dependencies required for this change**

GitPython

**Tag maintainer: for a quicker response, tag the relevant maintainer
(see below)**

- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
2023-07-30 21:27:20 -07:00
Piyush Jain
b2f8a5bae9
Fixed exports for NeptuneOpenCypherQAChain (#8439)
## Description
The imports for `NeptuneOpenCypherQAChain` are failing. This PR adds the
chain class to the `__init__.py` file to fix this issue.

## Maintainers
@dev2049 
@krlawrence
2023-07-30 20:36:22 -07:00
Eugene Yurtsev
e98e2b2b81
ChatPromptTemplate: clean up doc-string (#8473)
Minor doc-string clean up

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-30 20:11:04 -07:00
Eugene Yurtsev
529cb2e30c
Update doc-string in few shot template (#8474)
Partial update of doc-string, need to update other instances in
documentation
2023-07-30 19:39:14 -07:00
Muneeb Ahmad
4923cf029a
Added Proper Documentation for faiss-gpu Installation (#8492)
### Description
In the LangChain Documentation and Comments, I've Noticed that `pip
install faiss` was mentioned, instead of `pip install faiss-gpu`, since
installing `pip install faiss` results in an error. I've gone ahead and
updated the Documentation, and `faiss.ipynb`. This Change will ensure
ease of use for the end user, trying to install `faiss-gpu`.

### Issue: 
Documentation / Comments Related.

### Dependencies:
No Dependencies we're changed only updated the files with the wrong
reference.

### Tag maintainer:
 @rlancemartin, @eyurtsev (Thank You for your contributions 😄 )
2023-07-30 13:24:30 -07:00
shibuiwilliam
549720ae51
add test to ensure values in time weighted retriever are updated (#8479)
# What
- add test to ensure values in time weighted retriever are updated

<!-- Thank you for contributing to LangChain!

Replace this comment with:
- Description: add test to ensure values in time weighted retriever are
updated
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @MlopsJ


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
 -->
2023-07-30 11:42:25 -07:00
Harrison Chase
18a2452121
prompt cleanup (#8470) 2023-07-30 10:47:31 -07:00
Harrison Chase
4d526c49ed
bump experimental to 008 (#8490) 2023-07-30 07:28:18 -07:00
Harrison Chase
8f14ddefdf
add anthropic functions wrapper (#8475)
a cheeky wrapper around claude that adds in function calling support
(kind of, hence it going in experimental)
2023-07-30 07:23:46 -07:00
Nuno Campos
b65a9414bb
runnable.bind().bind() should combine kwargs, instead of nesting wrappers (#8467)
<!-- 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
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-29 15:48:30 -07:00
Nuno Campos
872abb4198
Implement Runnable for Tools (#8460)
- Make _arun optional
- Pass run_manager to inner chains in tools that have them

<!-- 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
 -->
2023-07-29 10:01:18 -07:00
William FH
b7c0eb9ecb
Wfh/ref links (#8454) 2023-07-29 08:44:32 -07:00
Harrison Chase
13b4f465e2
log output parser (#8446) 2023-07-29 07:53:45 +01:00
William FH
d935573362
Partial formatting for chat messages (#8450) 2023-07-28 23:08:33 -07:00
William FH
3314f54383
Update supabase docstrings (#8443) 2023-07-28 23:08:14 -07:00
Harrison Chase
2448043b84
bump and fix (#8441) 2023-07-28 17:16:51 -07:00
Amélie
8ee56b9a5b
Feature: Add support for meilisearch vectorstore (#7649)
**Description:**

Add support for Meilisearch vector store.
Resolve #7603 

- No external dependencies added
- A notebook has been added

@rlancemartin

https://twitter.com/meilisearch

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-28 17:06:54 -07:00
Bearnardd
b7d6e1909c
fix empty ids when metadatas is provided (#8127)
Fixes https://github.com/hwchase17/langchain/issues/7865 and
https://github.com/hwchase17/langchain/issues/8061

- [x] fixes returning empty ids when metadatas argument is provided

@baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-28 16:17:31 -07:00
lvisdd
abe4c361f9
update get_num_tokens_from_messages model (#8431)
(#8430)

Co-authored-by: Kano Kunihiko <kkano@heroz.co.jp>
2023-07-28 15:07:03 -07:00
Jeffrey Wang
e0de62f6da
Add RoPE Scaling params from llamacpp (#8422)
Description:
Just adding parameters from `llama-python-cpp` that support RoPE
scaling.
@hwchase17, @baskaryan

sources:
papers and explanation:
https://kaiokendev.github.io/context
llamacpp conversation:
https://github.com/ggerganov/llama.cpp/discussions/1965 
Supports models like:
https://huggingface.co/conceptofmind/LLongMA-2-13b
2023-07-28 14:42:41 -07:00
Harrison Chase
fab24457bc
remove code (#8425) 2023-07-28 13:19:44 -07:00
Harrison Chase
3a78450883
update experimental (#8402)
some changes were made to experimental, porting them over
2023-07-28 13:01:36 -07:00
Harrison Chase
af7e70d4af
expose function for converting messages to messages (#8426) 2023-07-28 13:00:54 -07:00
Eugene Yurtsev
06bdbe06fe
PromptTemplate update documentation and expand kwarg (#8423)
# PromptTemplate

* Update documentation to highlight the classmethod for instantiating a
prompt template.
* Expand kwargs in the classmethod to make parameters easier to discover

This PR got reverted here:
https://github.com/langchain-ai/langchain/pull/8395/files
2023-07-28 14:11:49 -04:00
Eugene Yurtsev
e62a1686e2
ChatPromptTemplate: minor fix in doc string (#8424)
Minor fix in doc-string to use `ai` rather than `assistant`
2023-07-28 13:01:13 -04:00
Eugene Yurtsev
760c278fe0
ChatPromptTemplate: Expand support for message formats and documentation (#8244)
* Expands support for a variety of message formats in the
`from_messages` classmethod. Ideally, we could deprecate the other
on-ramps to reduce the amount of classmethods users need to know about.
* Expand documentation with code examples.
2023-07-28 12:48:08 -04:00
Bagatur
61dd92f821
bump 246 (#8410) 2023-07-28 01:18:37 -07:00
Harrison Chase
394b67ab92
add kwargs to llm runnables (#8388) 2023-07-28 09:13:11 +01:00
HeTaoPKU
d5884017a9
Add Minimax llm model to langchain (#7645)
- Description: Minimax is a great AI startup from China, recently they
released their latest model and chat API, and the API is widely-spread
in China. As a result, I'd like to add the Minimax llm model to
Langchain.
- Tag maintainer: @hwchase17, @baskaryan

---------

Co-authored-by: the <tao.he@hulu.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-27 22:53:23 -07:00
James Campbell
0ad2d5f27a
[nit] Add default value for ChatOpenAI client (#7939)
Micro convenience PR to avoid warning regarding missing `client`
parameter. It is always set during initialization.

@baskaryan

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-27 22:38:32 -07:00
Harrison Chase
82df923f37 Merge branch 'master' of github.com:hwchase17/langchain 2023-07-27 22:01:20 -07:00
Harrison Chase
1b0bfa54cf cr 2023-07-27 22:00:52 -07:00
Jeff Vestal
c7ff5f19a8
ElasticKnnSearch rewrite - bug fix - return Document (#8180)
Fixes: 
https://github.com/hwchase17/langchain/issues/7117
https://github.com/hwchase17/langchain/issues/5760

Adding back `create_index` , `add_texts`, `from_texts` to
ElasticKnnSearch

`from_texts` matches standard `from_texts` methods as quick start up
method

`knn_search` and `hybrid_result` return a list of [`Document()`,
`score`,]

# Test `from_texts` for quick start
```
# create new index using from_text

from langchain.vectorstores.elastic_vector_search import ElasticKnnSearch
from langchain.embeddings import ElasticsearchEmbeddings

model_id = "sentence-transformers__all-distilroberta-v1" 
dims = 768
es_cloud_id = ""
es_user = ""
es_password = ""
test_index = "knn_test_index_305"

embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id,
    #input_field=input_field,
    es_cloud_id=es_cloud_id,
    es_user=es_user,
    es_password=es_password,
)

# add texts and create class instance
texts = ["This is a test document", "This is another test document"]
knnvectorsearch = ElasticKnnSearch.from_texts(
    texts=texts,
    embedding=embeddings,
    index_name= test_index,
    vector_query_field='vector',
    query_field='text',
    model_id=model_id,
    dims=dims,
	es_cloud_id=es_cloud_id, 
	es_user=es_user, 
	es_password=es_password
)

# Test `add_texts` method
texts2 = ["Hello, world!", "Machine learning is fun.", "I love Python."]
knnvectorsearch.add_texts(texts2)

query = "Hello"
knn_result = knnvectorsearch.knn_search(query = query, model_id= model_id, k=2)

hybrid_result = knnvectorsearch.knn_hybrid_search(query = query, model_id= model_id, k=2)

```

The  mapping is as follows:
```
{
  "knn_test_index_012": {
    "mappings": {
      "properties": {
        "text": {
          "type": "text"
        },
        "vector": {
          "type": "dense_vector",
          "dims": 768,
          "index": true,
          "similarity": "dot_product"
        }
      }
    }
  }
}
```

# Check response type
```
>>> hybrid_result
[(Document(page_content='Hello, world!', metadata={}), 0.94232327), (Document(page_content='I love Python.', metadata={}), 0.5321523)]

>>> hybrid_result[0]
(Document(page_content='Hello, world!', metadata={}), 0.94232327)

>>> hybrid_result[0][0]
Document(page_content='Hello, world!', metadata={})

>>> type(hybrid_result[0][0])
<class 'langchain.schema.document.Document'>
```

# Test with existing Index
```
from langchain.vectorstores.elastic_vector_search import ElasticKnnSearch
from langchain.embeddings import ElasticsearchEmbeddings

## Initialize ElasticsearchEmbeddings
model_id = "sentence-transformers__all-distilroberta-v1" 
dims = 768
es_cloud_id = 
es_user = ""
es_password = ""
test_index = "knn_test_index_012"

embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id,
    es_cloud_id=es_cloud_id,
    es_user=es_user,
    es_password=es_password,
)

## Initialize ElasticKnnSearch
knn_search = ElasticKnnSearch(
	es_cloud_id=es_cloud_id, 
	es_user=es_user, 
	es_password=es_password, 
	index_name= test_index, 
	embedding= embeddings
)


## Test adding vectors

### Test `add_texts` method when index created
texts = ["Hello, world!", "Machine learning is fun.", "I love Python."]
knn_search.add_texts(texts)

```

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-27 22:00:18 -07:00
Harrison Chase
a221a9ced0
Harrison/sql query (#8370)
Co-authored-by: Nuno Campos <nuno@boringbits.io>
2023-07-27 21:55:17 -07:00
Bagatur
a1a650c743
Bagatur/from texts bug fix (#8394)
---------

Co-authored-by: Davit Buniatyan <davit@loqsh.com>
Co-authored-by: Davit Buniatyan <d@activeloop.ai>
Co-authored-by: adilkhan <adilkhan.sarsen@nu.edu.kz>
Co-authored-by: Ivo Stranic <istranic@gmail.com>
2023-07-27 21:52:38 -07:00
Jiayi Ni
1efb9bae5f
FEAT: Integrate Xinference LLMs and Embeddings (#8171)
- [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>
2023-07-27 21:23:19 -07:00
Bagatur
877d384bc9
Revert "PromptTemplate update documentation and expand kwargs (#8234)" (#8395)
fyi @eyurtsev was failing a unit test
2023-07-27 21:11:10 -07:00
Gordon Clark
e66759cc9d
Github add "Create PR" tool + Docs update (#8235)
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
2023-07-27 19:19:44 -07:00
William FH
ecd4aae818
Few Shot Chat Prompt (#8038)
Proposal for a few shot chat message example selector

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2023-07-27 18:46:10 -07:00
Eugene Yurtsev
6dd18eee26
PromptTemplate update documentation and expand kwargs (#8234)
# PromptTemplate

* Update documentation to highlight the classmethod for instantiating a
prompt template.
* Expand kwargs in the classmethod to make parameters easier to discover
2023-07-27 18:11:39 -07:00
Karan V
a003a0baf6
fix(petals) allows to run models that aren't Bloom (Support for LLama and newer models) (#8356)
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>
2023-07-27 18:01:04 -07:00
lars.gersmann
e758e9e7f5
fix(openapi): openapi chain will work without/empty description/summa… (#8351)
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>
2023-07-27 17:58:43 -07:00
ljeagle
caa6caeb8a
Upgrade the AwaDB from v0.3.7 to v0.3.9 and change the default embeddings (#8281)
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>
2023-07-27 17:20:50 -07:00
Holt Skinner
d7e6770de8
refactor: Code refactoring & simplification for Google Cloud Enterprise Search retriever (#8369)
Followup to https://github.com/langchain-ai/langchain/pull/7857

- Changes `_convert_search_response()` to use object attributes instead
of converting to dictionary
- Simplifies logic for readability
2023-07-27 17:13:49 -07:00
Taozhi Wang
594f195e54
Add embeddings for AwaEmbedding (#8353)
- 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>
2023-07-27 17:08:00 -07:00
thehunmonkgroup
ba4e82bb47
fix missing _identifying_params() in _VertexAICommon (#8303)
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.
2023-07-27 16:59:10 -07:00
Caitlin2694
b2e4b9dca4
Fix exception caused by restrictions in OWL (#8341)
Description: Fix exception caused by restrictions in OWL
Issue: #8331
Dependencies: none
Maintainer: @baskaryan
2023-07-27 16:51:32 -07:00
Nikita Pokidyshev
f499e6ea6a
Add FunctionMessage to _message_from_dict (#8374)
<!-- 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
 -->
2023-07-27 16:45:27 -07:00
emarco177
2ab13ab743
added unit tests for mrkl output_parser.py (#8321)
- Description: added unit tests for mrkl output_parser.py, 
  - Tag maintainer: @hinthornw
  - Twitter handle: EdenEmarco177
2023-07-27 13:46:06 -07:00
Harrison Chase
f5bf893035
rename to str output parser (#8373) 2023-07-27 12:57:34 -07:00
William FH
0e9e5b5202
Retry events on any run type (#8375) 2023-07-27 12:56:46 -07:00
William FH
ff98fad2d9
Add Retry Events (#8053)
![image](https://github.com/hwchase17/langchain/assets/13333726/59a5c3b4-4367-47e6-9f58-5b6557576a8a)

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-27 12:39:39 -07:00
Nuno Campos
0eca3e7d90
Add Runnable.bind method to attach kwargs to a Runnable that will be passed to all invoke/stream/batch calls when it is run (#8368)
<!-- 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
 -->
2023-07-27 11:16:30 -07:00
Nuno Campos
1bbadde77b
Support using RunnableMap directly (#8317)
<!-- 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
 -->
2023-07-27 17:24:29 +01:00
Bagatur
944321c6ab
bump 245 (#8359) 2023-07-27 06:53:24 -07:00
Rubén Barragán
ef6332ead6
Support loading files from Dropbox (#8271)
## 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/rubenbarragan
https://www.linkedin.com/in/rgbarragan/
https://twitter.com/RubenBarraganP

---------

Co-authored-by: Ruben Barragan <rbarragan@Rubens-MacBook-Air.local>
2023-07-27 06:36:08 -07:00
Pranay Chandekar
41bb3a6f9b
fixed the bug #8343 (#8345)
- Issue: #8343

Signed-off-by: Pranay Chandekar <pranayc6@gmail.com>
2023-07-27 06:33:15 -07:00
Martin Krasser
93260a9922
Fix broken make targets format_diff and lint_diff (#8344)
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
2023-07-27 01:56:55 -07:00
Harrison Chase
ae78ef7fe6
bump experimental to 005 (#8339) 2023-07-26 21:46:28 -07:00
Vadim Gubergrits
e7e5cb9d08
Tree of Thought introducing a new ToTChain. (#5167)
# [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>
2023-07-26 21:29:39 -07:00
William FH
9eb7e6e27f
Delete Old Evals Examples (#8252)
Still retain:
- Comparison Examples
- Data + QA walkthrough
- QA (but really minimize it)
2023-07-26 18:46:54 -07:00
Saurabh Misra
db9d5b213a
Optimize the cosine_similarity_top_k function performance (#8151)
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.
2023-07-26 18:03:49 -07:00
Fabrizio Ruocco
ddc353a768
Azure Cognitive Search: Custom index and scoring profile support (#6843)
Description: Adding support for custom index and scoring profile support
in Azure Cognitive Search
@hwchase17

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-26 17:58:01 -07:00
Kacper Łukawski
c5988c1d4b
Implement async support for Cohere (#8237)
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>
2023-07-26 15:51:18 -07:00
Daniel Alexander Brenot
bf1357f584
Added async support to PlanAndExecute Chain (#8239)
- Description: Adds async support to the PlanAndExecute Chain

Maintainer responsibilities:
  - Async: @agola11

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-26 15:16:07 -07:00
Bastin Florian
a3ac9b23eb
feat(confluence): add markdown format option (#8246)
# 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>
2023-07-26 15:00:27 -07:00
Leonid Ganeline
ee6ff96e28
docstrings cleanup (#8311)
- added missed docstrings
 - changed docstrings into consistent format
  
@baskaryan
2023-07-26 14:13:10 -07:00
Rohit Gupta
e5dba8978a
Avoid re-computation of embedding in weaviate similarity search (#8284)
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-26 13:31:55 -07:00
Nuno Campos
a612800ef0
Runnable single protocol (#7800)
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>
2023-07-26 12:16:46 -07:00
Bharat
04a4d3e312
Fixes #8310 Fix maximum recursion depth exceeded error (#8313)
ElasticsearchVectorStore.as_retriever() method is returning 
`RecursionError: maximum recursion depth exceeded` 
because of incorrect field reference in
 `embeddings()` method

  - Description: Fix RecursionError because of a typo
  - Issue: the issue #8310 
  - Dependencies: None,
  - Tag maintainer: @eyurtsev
  - Twitter handle: bpatel
2023-07-26 12:15:37 -07:00
Caitlin2694
b9db3dd09b
Fix "missing key op" RDFGraph OWL serialization (#8276)
Replace this comment with:
- Description: Fix "missing key op" error in RDFGraph OWL Serialization
  - Issue: #8263
  - Dependencies: None
  - Tag maintainer: @baskaryan
2023-07-26 12:14:56 -07:00
Eugene Yurtsev
862e9aed66
ChatPromptTemplate: Update doc-strings, update from_role_strings behavior (#8308)
* Update doc-strings in ChatPromptTemplate
* Update from_role_strings classmethod to use well known roles
2023-07-26 15:02:36 -04:00
Bagatur
2c2fd9ff13
bump 244 (#8314) 2023-07-26 11:58:26 -07:00
Lance Martin
77c0582243
Clean queries prior to search (#8309)
With some search tools, we see no results returned if the query is a
numeric list.

E.g., if we pass:
```
'1. "LangChain vs LangSmith: How do they differ?"'
```

We see:
```
No good Google Search Result was found
```

Local testing w/ Streamlit:

![image](https://github.com/langchain-ai/langchain/assets/122662504/0a7e3dca-59e8-415e-8df6-bd9e4ea962ee)
2023-07-26 11:48:28 -07:00
shibuiwilliam
6b88fbd9bb
add test for embedding distance evaluation (#8285)
Add tests for embedding distance evaluation

  - Description: Add tests for embedding distance evaluation
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @baskaryan
  - Twitter handle: @MlopsJ
2023-07-26 11:45:50 -07:00
Timon Palm
70604e590f
DuckDuckGoSearch News Tool (#8292)
Description: 
I wanted to use the DuckDuckGoSearch tool in an agent to let him get the
latest news for a topic. DuckDuckGoSearch has already an implemented
function for retrieving news articles. But there wasn't a tool to use
it. I simply adapted the SearchResult class with an extra argument
"backend". You can set it to "news" to only get news articles.

Furthermore, I added an example to the DuckDuckGo Notebook on how to
further customize the results by using the DuckDuckGoSearchAPIWrapper.

Dependencies: no new dependencies
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-26 11:30:01 -07:00
Byron Saltysiak
61347bd322
giving path to the copy command for *.toml files (#8294)
Description: in the .devcontainer, docker-compose build is currently
failing due to the src paths in the COPY command. This change adds the
full path to the pyproject.toml and poetry.toml to allow the build to
run.
Issue: 

You can see the issue if you try to build the dev docker image with:
```
cd .devcontainer
docker-compose build
```

Dependencies: none
Twitter handle: byronsalty
2023-07-26 10:37:03 -07:00
happyxhw
6384c1ec8f
fix: ElasticVectorSearch.from_documents failed #8293 (#8296)
- Description: fix ElasticVectorSearch.from_documents with
elasticsearch_url param,
- Issue: ElasticVectorSearch.from_documents failed #8293 # it fixes (if
applicable),


---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-26 10:33:52 -07:00
jacobswe
83a53e2126
Bug Fix: AzureChatOpenAI streaming with function calls (#8300)
- Description: During streaming, the first chunk may only contain the
name of an OpenAI function and not any arguments. In this case, the
current code presumes there is a streaming response and tries to append
to it, but gets a KeyError. This fixes that case by checking if the
arguments key exists, and if not, creates a new entry instead of
appending.
  - Issue: Related to #6462

Sample Code:
```python
llm = AzureChatOpenAI(
    deployment_name=deployment_name,
    model_name=model_name,
    streaming=True
)

tools = [PythonREPLTool()]
callbacks = [StreamingStdOutCallbackHandler()]

agent = initialize_agent(
    tools=tools,
    llm=llm,
    agent=AgentType.OPENAI_FUNCTIONS,
    callbacks=callbacks
)

agent('Run some python code to test your interpreter')
```

Previous Result:
```
File ...langchain/chat_models/openai.py:344, in ChatOpenAI._generate(self, messages, stop, run_manager, **kwargs)
    342         function_call = _function_call
    343     else:
--> 344         function_call["arguments"] += _function_call["arguments"]
    345 if run_manager:
    346     run_manager.on_llm_new_token(token)

KeyError: 'arguments'
```

New Result:
```python
{'input': 'Run some python code to test your interpreter',
 'output': "The Python code `print('Hello, World!')` has been executed successfully, and the output `Hello, World!` has been printed."}
```

Co-authored-by: jswe <jswe@polencapital.com>
2023-07-26 10:11:50 -07:00
German Martin
457a4730b2
Fix the mangling issue on several VectorStores child classes. (#8274)
- Description: Fix mangling issue affecting a couple of VectorStore
classes including Redis.
  - Issue: https://github.com/langchain-ai/langchain/issues/8185
  - @rlancemartin 
  
This is a simple issue but I lack of some context in the original
implementation.
My changes perhaps are not the definitive fix but to start a quick
discussion.

@hinthornw Tagging you since one of your changes introduced this
[here.](c38965fcba)
2023-07-26 09:48:55 -07:00
Alec Flett
4da43f77e5
Add ability to load (deserialize) objects from other namespaces (#7726)
I have some Prompt subclasses in my project that I'd like to be able to
deserialize in callbacks. Right now `loads()`/`load()` will bail when it
encounters my object, but I know I can trust the objects because they're
in my own projects.

<!-- 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!

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
 -->
2023-07-26 16:59:28 +01:00
Bagatur
5c6dcb1960
bump 243 (#8289) 2023-07-26 05:41:56 -07:00
William FH
adf019724f
unpack later (#8278)
Fix https://github.com/langchain-ai/langchain/issues/8272
2023-07-26 01:53:22 -07:00
Naveen Tatikonda
9cbefcc56c
[ OpenSearch ] : Add AOSS Support to OpenSearch (#8256)
### Description

This PR includes the following changes:

- Adds AOSS (Amazon OpenSearch Service Serverless) support to
OpenSearch. Please refer to the documentation on how to use it.
- While creating an index, AOSS only supports Approximate Search with
`nmslib` and `faiss` engines. During Search, only Approximate Search and
Script Scoring (on doc values) are supported.
- This PR also adds support to `efficient_filter` which can be used with
`faiss` and `lucene` engines.
- The `lucene_filter` is deprecated. Instead please use the
`efficient_filter` for the lucene engine.


Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-07-25 23:59:36 -07:00
Lance Martin
7a00f17033
Web research retriever (#8102)
Given a user question, this will -
* Use LLM to generate a set of queries.
* Query for each.
* The URLs from search results are stored in self.urls.
* A check is performed for any new URLs that haven't been processed yet
(not in self.url_database).
* Only these new URLs are loaded, transformed, and added to the
vectorstore.
* The vectorstore is queried for relevant documents based on the
questions generated by the LLM.
* Only unique documents are returned as the final result.

This code will avoid reprocessing of URLs across multiple runs of
similar queries, which should improve the performance of the retriever.
It also keeps track of all URLs that have been processed, which could be
useful for debugging or understanding the retriever's behavior.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-25 19:58:00 -07:00
Rithwik Ediga Lakhamsani
d1d691caa4
Added Databricks support to MLflow Callback (#7906)
Added a quick check to make integration easier with Databricks; another
option would be to make a new class, but this seemed more
straightfoward.

cc: @liangz1 Can this be done in a more straightfoward way?
2023-07-25 18:23:54 -07:00
William FH
479cc086ba
Rm Github Import (#8257)
It's not a required dep but would break peoples builds

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-25 18:20:58 -07:00
Erick Friis
c14571ab37
New enterprise support form (#8254) 2023-07-25 15:43:27 -07:00
Eugene Yurtsev
ec069381fb
Remove operator overloading for BaseMessage (#8245)
This PR removes operator overloading for base message.

Removing the `+` operating from base message will help make sure that:

1) There's no need to re-define `+` for message chunks
2) That there's no unexpected behavior in terms of types changing
(adding two messages yields a ChatPromptTemplate which is not a message)
2023-07-25 20:12:19 +01:00
jacobswe
0af48b06d0
Bug Fix #6462 (#8241)
- Description: Small change to fix broken Azure streaming. More complete
migration probably still necessary once the new API behavior is
finalized.
- Issue: Implements fix by @rock-you in #6462 
- Dependencies: N/A

There don't seem to be any tests specifically for this, and I was having
some trouble adding some. This is just a small temporary fix to allow
for the new API changes that OpenAI are releasing without breaking any
other code.

---------

Co-authored-by: Jacob Swe <jswe@polencapital.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-25 11:30:22 -07:00
Bagatur
c1ea8da9bc
bump 242 (#8238) 2023-07-25 08:01:37 -07:00
shibuiwilliam
af788b7cf0
Add/faiss test score threshold (#8224)
# What
- This is to add test for faiss vector store with score threshold

<!-- Thank you for contributing to LangChain!

Replace this comment with:
- Description: This is to add test for faiss vector store with score
threshold
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @MlopsJ

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
 -->
2023-07-25 09:56:29 -04:00
shibuiwilliam
bed8eb978e
use logger instead of logging (#8225)
# What
- Use `logger` instead of using logging directly.

<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: Use `logger` instead of using logging directly.
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @baskaryan
  - Twitter handle: @MlopsJ

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
 -->
2023-07-25 09:55:30 -04:00
Leonid Ganeline
afc55a4fee
Refactored requests (#8203)
Refactored `requests.py`. The same as
https://github.com/langchain-ai/langchain/pull/7961 #8098 #8099
requests.py is in the root code folder. This creates the
`langchain.requests: Requests` group on the API Reference navigation
ToC, on the same level as Chains and Agents which is incorrect.

Refactoring:

- copied requests.py content into utils/requests.py
- I added the backwards compatibility ref in the original requests.py. 
- updated imports to requests objects

@hwchase17, @baskaryan
2023-07-24 21:23:59 -07:00
Alex Stachowiak
a7efa95775
Update base chain type hints (#7680)
Addresses #7578. `run()` can return dictionaries, Pydantic objects or
strings, so the type hints should reflect that. See the chain from
`create_structured_output_chain` for an example of a non-string return
type from `run()`.

I've updated the BaseLLMChain return type hint from `str` to `Any`.
Although, the differences between `run()` and `__call__()` seem less
clear now.

CC: @baskaryan

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 21:16:41 -07:00
Ani peter benjamin
e58b1d7073
feat: temp fixed Could not parse LLM output on agents folder (#7746)
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 19:20:37 -07:00
Dayuan Jiang
125ae6d9de
add Hybrid retriever that not require any external service (#8108)
- Until now, hybrid search was limited to modules requiring external
services, such as Weaviate/Pinecone Hybrid Search. However, I have
developed a hybrid retriever that can merge a list of retrievers using
the [Reciprocal Rank
Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf)
algorithm. This new approach, similar to Weaviate hybrid search, does
not require the initialization of any external service.
  - Dependencies: No  - Twitter handle: dayuanjian21687

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 19:16:10 -07:00
earonesty
59a7c5877a
Update supabase.py, add filter to query (matches latest supabase docs & js) (#7721)
- Description: Update supabase to support optional filter argument (if
present, used, if not, doesn't break things)
- Tag maintainer: @rlancemartin, @eyurtsev

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 19:13:52 -07:00
Aditya S
00de334f81
Fixed sparql SELECT and UPDATE query function (#7758)
- Description: Changed "SELECT" and "UPDTAE" intent check from "=" to
"in",
- Issue: Based on my own testing, most of the LLM (StarCoder, NeoGPT3,
etc..) doesn't return a single word response ("SELECT" / "UPDATE")
through this modification, we can accomplish the same output without
curated prompt engineering.
  - Dependencies: None
  - Tag maintainer: @baskaryan
  - Twitter handle: @aditya_0290


Thank you for maintaining this library, Keep up the good efforts.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 18:29:30 -07:00
William FH
3662aca7d4
Add async support for transform chain (#8205) 2023-07-24 17:45:17 -07:00
Taqi Jaffri
8f158b72fc
Added stop sequence support to replicate (#8107)
Stop sequences are useful if you are doing long-running completions and
need to early-out rather than running for the full max_length... not
only does this save inference cost on Replicate, it is also much faster
if you are going to truncate the output later anyway.

Other LLMs support stop sequences natively (e.g. OpenAI) but I didn't
see this for Replicate so adding this via their prediction cancel
method.

Housekeeping: I ran `make format` and `make lint`, no issues reported in
the files I touched.

I did update the replicate integration test and ran `poetry run pytest
tests/integration_tests/llms/test_replicate.py` successfully.

Finally, I am @tjaffri https://twitter.com/tjaffri for feature
announcement tweets... or if you could please tag @docugami
https://twitter.com/docugami we would really appreciate that :-)

Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
2023-07-24 17:34:13 -07:00
glaze
f7ad14acfa
Add etherscan document loader (#7943)
@rlancemartin 
The modification includes:
* etherscanLoader
* test_etherscan
* document ipynb

I have run the test, lint, format, and spell check. I do encounter a
linting error on ipynb, I am not sure how to address that.
```
docs/extras/modules/data_connection/document_loaders/integrations/Etherscan.ipynb:55: error: Name "null" is not defined  [name-defined]
docs/extras/modules/data_connection/document_loaders/integrations/Etherscan.ipynb:76: error: Name "null" is not defined  [name-defined]
Found 2 errors in 1 file (checked 1 source file)
```
- Description: The Etherscan loader uses etherscan api to load
transaction histories under specific accounts on Ethereum Mainnet.
- No dependency is introduced by this PR.
- Twitter handle: glazecl

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 17:09:16 -07:00
Julien Salinas
73d5cba308
Allow user to modify the GPU and language settings when using NLP Cloud (#7985)
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 17:08:56 -07:00
Liu Ming
24f889f2bc
Change with_history option to False for ChatGLM by default (#8076)
ChatGLM LLM integration will by default accumulate conversation
history(with_history=True) to ChatGLM backend api, which is not expected
in most cases. This PR set with_history=False by default, user should
explicitly set llm.with_history=True to turn this feature on. Related
PR: #8048 #7774

---------

Co-authored-by: mlot <limpo2000@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 15:46:02 -07:00
Mahip Soni
1f055775f8
Fixing issue with MSSQL connection (#8040)
My team recently faced an issue while using MSSQL and passing a schema
name.

We noticed that "SET search_path TO {self.schema}" is being called for
us, which is not a valid ms-sql query, and is specific to postgresql
dialect.

We were able to run it locally after this fix.


---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 15:45:40 -07:00
Anthony Mahanna
76102971c0
ArangoDB/AQL support for Graph QA Chain (#7880)
**Description**: Serves as an introduction to LangChain's support for
[ArangoDB](https://github.com/arangodb/arangodb), similar to
https://github.com/hwchase17/langchain/pull/7165 and
https://github.com/hwchase17/langchain/pull/4881

**Issue**: No issue has been created for this feature

**Dependencies**: `python-arango` has been added as an optional
dependency via the `CONTRIBUTING.md` guidelines
 
**Twitter handle**: [at]arangodb

- Integration test has been added
- Notebook has been added:
[graph_arangodb_qa.ipynb](https://github.com/amahanna/langchain/blob/master/docs/extras/modules/chains/additional/graph_arangodb_qa.ipynb)

[![Open In
Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/amahanna/langchain/blob/master/docs/extras/modules/chains/additional/graph_arangodb_qa.ipynb)

```
docker run -p 8529:8529 -e ARANGO_ROOT_PASSWORD= arangodb/arangodb
```

```
pip install git+https://github.com/amahanna/langchain.git
```

```python
from arango import ArangoClient

from langchain.chat_models import ChatOpenAI
from langchain.graphs import ArangoGraph
from langchain.chains import ArangoGraphQAChain

db = ArangoClient(hosts="localhost:8529").db(name="_system", username="root", password="", verify=True)

graph = ArangoGraph(db)

chain = ArangoGraphQAChain.from_llm(ChatOpenAI(temperature=0), graph=graph)

chain.run("Is Ned Stark alive?")
```

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 15:16:52 -07:00
Adilkhan Sarsen
3e7d2a1b64
SelfQuery support for deeplake (#7888)
Added support SelfQuery for Deeplake
2023-07-24 14:22:33 -07:00
Leonid Ganeline
c580c81cca
docstrings experimental (#7969)
- added/changed docstring for `experimental`
- added/changed docstrings for different artifacts
- 
@baskaryan
2023-07-24 14:21:48 -07:00
Leonid Ganeline
3eb4112a1f
Refactored example_generator (#8099)
Refactored `example_generator.py`. The same as #7961 
`example_generator.py` is in the root code folder. This creates the
`langchain.example_generator: Example Generator ` group on the API
Reference navigation ToC, on the same level as `Chains` and `Agents`
which is not correct.

Refactoring:
- moved `example_generator.py` content into
`chains/example_generator.py` (not in `utils` because the
`example_generator` has dependencies on other LangChain classes. It also
doesn't work for moving into `utilities/`)
- added the backwards compatibility ref in the original
`example_generator.py`

@hwchase17
2023-07-24 13:36:44 -07:00
Leonid Ganeline
7cbe28ba9b
Refactored input (#8202)
Refactored `input.py`. The same as
https://github.com/langchain-ai/langchain/pull/7961 #8098 #8099
input.py is in the root code folder. This creates the `langchain.input:
Input` group on the API Reference navigation ToC, on the same level as
Chains and Agents which is incorrect.

Refactoring:

- copied input.py file into utils/input.py
- I added the backwards compatibility ref in the original input.py. 
- changed several imports to a new ref

@hwchase17, @baskaryan
2023-07-24 13:10:03 -07:00
Monty Evans
72eb4fa4e8
Change WebBaseLoader metadata parsing to set missing metadata to descriptive string instead of None (#8175)
Solves #8174 & #3542

Co-authored-by: mevans <mevans@palantir.com>
2023-07-24 12:17:49 -07:00
Bagatur
1a7d8667c8
Bagatur/gateway chat (#8198)
Signed-off-by: dbczumar <corey.zumar@databricks.com>
Co-authored-by: dbczumar <corey.zumar@databricks.com>
2023-07-24 12:17:00 -07:00
Ettore Di Giacinto
ae28568e2a
Add embeddings for LocalAI (#8134)
Description:

This PR adds embeddings for LocalAI (
https://github.com/go-skynet/LocalAI ), a self-hosted OpenAI drop-in
replacement. As LocalAI can re-use OpenAI clients it is mostly following
the lines of the OpenAI embeddings, however when embedding documents, it
just uses string instead of sending tokens as sending tokens is
best-effort depending on the model being used in LocalAI. Sending tokens
is also tricky as token id's can mismatch with the model - so it's safer
to just send strings in this case.

Partly related to: https://github.com/hwchase17/langchain/issues/5256

Dependencies: No new dependencies

Twitter: @mudler_it
---------

Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 12:16:49 -07:00
Mike Nitsenko
d983046f90
Extend Cube Semantic Loader functionality (#8186)
**PR Description:**

This pull request introduces several enhancements and new features to
the `CubeSemanticLoader`. The changes include the following:

1. Added imports for the `json` and `time` modules.
2. Added new constructor parameters: `load_dimension_values`,
`dimension_values_limit`, `dimension_values_max_retries`, and
`dimension_values_retry_delay`.
3. Updated the class documentation with descriptions for the new
constructor parameters.
4. Added a new private method `_get_dimension_values()` to retrieve
dimension values from Cube's REST API.
5. Modified the `load()` method to load dimension values for string
dimensions if `load_dimension_values` is set to `True`.
6. Updated the API endpoint in the `load()` method from the base URL to
the metadata endpoint.
7. Refactored the code to retrieve metadata from the response JSON.
8. Added the `column_member_type` field to the metadata dictionary to
indicate if a column is a measure or a dimension.
9. Added the `column_values` field to the metadata dictionary to store
the dimension values retrieved from Cube's API.
10. Modified the `page_content` construction to include the column title
and description instead of the table name, column name, data type,
title, and description.

These changes improve the functionality and flexibility of the
`CubeSemanticLoader` class by allowing the loading of dimension values
and providing more detailed metadata for each document.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 12:11:58 -07:00
Bagatur
82b8d8596c
bump lc241 exp3 (#8193) 2023-07-24 11:52:44 -07:00
Leonid Ganeline
848454d1e7
Refactored formatting (#8191)
Refactored `formatting.py`. The same as
https://github.com/langchain-ai/langchain/pull/7961 #8098 #8099
formatting.py is in the root code folder. This creates the
`langchain.formatting: Formatting` group on the API Reference navigation
ToC, on the same level as Chains and Agents which is incorrect.

Refactoring:

- moved formatting.py content into utils/formatting.py
- I did not add the backwards compatibility ref in the original
formatting.py. It seems unnecessary.
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-24 11:34:15 -07:00
Bagatur
4928f7a9f5
undo bump (#8192) 2023-07-24 11:32:17 -07:00
Leonid Ganeline
120cdf813d
docstrings memory (#8018)
docstrings `memory`:
- added module summary
- added missed docstrings
- updated docstrings into consistent format
- 
@baskaryan
2023-07-24 10:05:36 -07:00
Bagatur
d5689d58ab
Bagatur/bump 241 (#8182) 2023-07-24 07:47:40 -07:00
Harrison Chase
3caccf304c
Harrison/hugginggpt (#8162)
Co-authored-by: Yongliang Shen <withsyl@163.com>
2023-07-24 07:36:24 -07:00
rajib
f3908627ed
changed to mlflow-ai-gateway in llms/__init__.py (#8114)
- Description: In the llms/__init__.py, the key name is wrong for
mlflowaigateway. It should be mlflow-ai-gateway
  - Issue: NA
  - Dependencies: NA
  - Tag maintainer: @hwchase17, @baskaryan
  - Twitter handle: na

Without this fix, when we run the code for mlflowaigateway, we will get
error as below

ValueError: Loading mlflow-ai-gateway LLM not supported

---------

Co-authored-by: rajib76 <rajib76@yahoo.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-23 23:30:46 -07:00
Gordon Clark
80b3ec5869
GitHub toolkit improvements (#8121)
Fixes an issue with the github tool where the API returned special
objects but the tool was expecting dictionaries.

Also added proper docstrings to the GitHubAPIWraper methods and a (very
basic) integration test.

Maintainer responsibilities:
  - Agents / Tools / Toolkits: @hinthornw

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-23 20:17:53 -07:00
shibuiwilliam
8f5000146c
add faiss test for score threshold (#8143)
# What
- Add faiss vector search test for score threshold
- Fix failing faiss vector search test; filtering with list value is
wrong.

<!-- Thank you for contributing to LangChain!

Replace this comment with:
- Description: Add faiss vector search test for score threshold; Fix
failing faiss vector search test; filtering with list value is wrong.
  - Issue: None
  - Dependencies: None
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @MlopsJ

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
 -->
2023-07-23 19:36:38 -07:00
Nolan
7686dabd36
Unbreak devcontainer (#8154)
Codespaces and devcontainer was broken by the [repo
restructure](https://github.com/langchain-ai/langchain/discussions/8043).



- Description: Add libs/langchain to container so it can be built
without error.
  - Issue: -
  - Dependencies: -
  - Tag maintainer: @hwchase17 @baskaryan 
  - Twitter handle: @finnless

The failed build log says:
```
#10 [langchain-dev-dependencies 2/2] RUN poetry install --no-interaction --no-ansi --with dev,test,docs
#10 sha256:e850ee99fc966158bfd2d85e82b7c57244f47ecbb1462e75bd83b981a56a1929
2023-07-23 23:30:33.692Z: #10 0.827 
#10 0.827 Directory libs/langchain does not exist
2023-07-23 23:30:33.738Z: #10 ERROR: executor failed running [/bin/sh -c poetry install --no-interaction --no-ansi --with dev,test,docs]: exit code: 1
```

The new pyproject.toml imports from libs/langchain:

77bf75c236/pyproject.toml (L14-L16)

But libs/langchain is never added to the dev.Dockerfile:


77bf75c236/libs/langchain/dev.Dockerfile (L37-L39)
2023-07-23 19:33:47 -07:00
Harrison Chase
9205919ad2
actually use input key (#8136) 2023-07-23 18:02:45 -07:00
Leonid Ganeline
670304a8b3
simplified nmspace (#8152)
recreated #7894 (it is easy to recreate than resolve conflicts)
A small refactoring to improve the API Reference Agents table
 @baskaryan
2023-07-23 18:02:20 -07:00
William FH
c5b50be225
Function calling logging fixup (#8153)
Fix bad overwriting of "functions" arg in invocation params.
Cleanup precedence in the dict
Clean up some inappropriate types (mapping should be dict)


Example:
https://dev.smith.langchain.com/public/9a7a6817-1679-49d8-8775-c13916975aae/r


![image](https://github.com/langchain-ai/langchain/assets/13333726/94cd0775-b6ef-40c3-9e5a-3ab65e466ab9)
2023-07-23 18:01:33 -07:00
SlapDrone
961a0e200f
Implement AgentExecutorIterator (#6929)
- Description: Implements a `.iter()` method for the `AgentExecutor`
class. This allows hooking into and intercepting intermediate agent
steps.
  - Issue: #6925 
  - Dependencies: None
  - Tag maintainer: @vowelparrot @agola11 
  - Twitter handle: @SlapDron3 @lacicocodes

---------

Co-authored-by: Lacico <Lacicocodes@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-23 18:00:22 -07:00
Harrison Chase
77bf75c236
bump experimental to 002 (#8150) 2023-07-23 09:22:39 -07:00
Harrison Chase
e46126eac6
add llamaapi (#8140) 2023-07-23 09:16:16 -07:00
Harrison Chase
cbf2fc8af8
prompt ergonomics (#7799) 2023-07-22 14:19:17 -07:00
Harrison Chase
9f3073d418
bump versions (#8129) 2023-07-22 08:46:37 -07:00
Harrison Chase
86946a47a8
Harrison/add back in experimental (#8128) 2023-07-22 08:27:29 -07:00
Karthik Raja A
8b08687fc4
MultiOn client toolkit (#8110)
Addition of MultiOn Client Agent Toolkit
Dependencies: multion pip package
This PR consists of the following:
- MultiOn utility,tools and integration with agent
- sample jupyter notebook.
Request @hwchase17 , @hinthornw

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-22 08:19:01 -07:00
Harrison Chase
aa0e69bc98
Harrison/official pre release (#8106) 2023-07-21 18:44:32 -07:00
Philip Kiely - Baseten
95bcf68802
add kwargs support for Baseten models (#8091)
This bugfix PR adds kwargs support to Baseten model invocations so that
e.g. the following script works properly:

```python
chatgpt_chain = LLMChain(
    llm=Baseten(model="MODEL_ID"),
    prompt=prompt,
    verbose=False,
    memory=ConversationBufferWindowMemory(k=2),
    llm_kwargs={"max_length": 4096}
)
```
2023-07-21 13:56:27 -07:00
Harrison Chase
8dcabd9205
bump releases rc0 (#8097) 2023-07-21 13:54:57 -07:00
Harrison Chase
d353d668e4
remove CVEs (#8092)
This PR aims to move all code with CVEs into `langchain.experimental`.
Note that we are NOT yet removing from the core `langchain` package - we
will give people a week to migrate here.

See MIGRATE.md for how to migrate

Zero changes to functionality

Vulnerabilities this addresses:

PALChain:
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5752409
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759265

SQLDatabaseChain
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759268

`load_prompt` (Python files only)
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5725807
2023-07-21 13:32:39 -07:00
Bagatur
08c658d3f8
fix api ref (#8083) 2023-07-21 12:37:21 -07:00
Harrison Chase
da04760de1
Harrison/move experimental (#8084) 2023-07-21 10:36:28 -07:00
Harrison Chase
f35db9f43e
(WIP) set up experimental (#7959) 2023-07-21 09:20:24 -07:00