Commit Graph

208 Commits

Author SHA1 Message Date
Conrad Fernandez
6eff0fa2ca
Added documentation for add_texts function for Pinecone integration (#7134)
- Description: added some documentation to the Pinecone vector store
docs page.
- Issue: #7126 
- Dependencies: None
- Tag maintainer: @baskaryan 

I can add more documentation on the Pinecone integration functions as I
am going to go in great depth into this area. Just wanted to check with
the maintainers is if this is all good.
2023-07-05 13:11:37 -04:00
felixocker
db98c44f8f
Support for SPARQL (#7165)
# [SPARQL](https://www.w3.org/TR/rdf-sparql-query/) for
[LangChain](https://github.com/hwchase17/langchain)

## Description
LangChain support for knowledge graphs relying on W3C standards using
RDFlib: SPARQL/ RDF(S)/ OWL with special focus on RDF \
* Works with local files, files from the web, and SPARQL endpoints
* Supports both SELECT and UPDATE queries
* Includes both a Jupyter notebook with an example and integration tests

## Contribution compared to related PRs and discussions
* [Wikibase agent](https://github.com/hwchase17/langchain/pull/2690) -
uses SPARQL, but specifically for wikibase querying
* [Cypher qa](https://github.com/hwchase17/langchain/pull/5078) - graph
DB question answering for Neo4J via Cypher
* [PR 6050](https://github.com/hwchase17/langchain/pull/6050) - tries
something similar, but does not cover UPDATE queries and supports only
RDF
* Discussions on [w3c mailing list](mailto:semantic-web@w3.org) related
to the combination of LLMs (specifically ChatGPT) and knowledge graphs

## Dependencies
* [RDFlib](https://github.com/RDFLib/rdflib)

## Tag maintainer
Graph database related to memory -> @hwchase17
2023-07-05 13:00:16 -04:00
Prakul Agarwal
38f853dfa3
Fixed typos in MongoDB Atlas Vector Search documentation (#7174)
Fix for typos in MongoDB Atlas Vector Search documentation
<!-- 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
 -->
2023-07-05 12:48:00 -04:00
Raouf Chebri
6fc24743b7
Add pg_hnsw vectorstore integration (#6893)
Hi @rlancemartin, @eyurtsev!

- Description: Adding HNSW extension support for Postgres. Similar to
pgvector vectorstore, with 3 differences
      1. it uses HNSW extension for exact and ANN searches, 
      2. Vectors are of type array of real
      3. Only supports L2
      
- Dependencies: [HNSW](https://github.com/knizhnik/hnsw) extension for
Postgres
  
  - Example:
  ```python
    db = HNSWVectoreStore.from_documents(
      embedding=embeddings,
      documents=docs,
      collection_name=collection_name,
      connection_string=connection_string
  )
  
  query = "What did the president say about Ketanji Brown Jackson"
docs_with_score: List[Tuple[Document, float]] =
db.similarity_search_with_score(query)
  ```

The example notebook is in the PR too.
2023-07-05 08:10:10 -07:00
Simon Cheung
81eebc4070
Add HugeGraphQAChain to support gremlin generating chain (#7132)
[Apache HugeGraph](https://github.com/apache/incubator-hugegraph) is a
convenient, efficient, and adaptable graph database, compatible with the
Apache TinkerPop3 framework and the Gremlin query language.

In this PR, the HugeGraph and HugeGraphQAChain provide the same
functionality as the existing integration with Neo4j and enables query
generation and question answering over HugeGraph database. The
difference is that the graph query language supported by HugeGraph is
not cypher but another very popular graph query language
[Gremlin](https://tinkerpop.apache.org/gremlin.html).

A notebook example and a simple test case have also been added.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-04 10:21:21 -06:00
Saverio Proto
5585607654
Improve Bing Search example (#7128)
# Description

Improve Bing Search example:
2023-07-04 09:58:03 -06:00
Lance Martin
265c285057
Fix GPT4All bug w/ "n_ctx" param (#7093)
Running `GPT4All` per the
[docs](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/gpt4all),
I see:

```
$ from langchain.llms import GPT4All
$ model = GPT4All(model=local_path)
$ model("The capital of France is ", max_tokens=10)
TypeError: generate() got an unexpected keyword argument 'n_ctx'
```

It appears `n_ctx` is [no longer a supported
param](https://docs.gpt4all.io/gpt4all_python.html#gpt4all.gpt4all.GPT4All.generate)
in the GPT4All API from https://github.com/nomic-ai/gpt4all/pull/1090.

It now uses `max_tokens`, so I set this.

And I also set other defaults used in GPT4All client
[here](https://github.com/nomic-ai/gpt4all/blob/main/gpt4all-bindings/python/gpt4all/gpt4all.py).

Confirm it now works:
```
$ from langchain.llms import GPT4All
$ model = GPT4All(model=local_path)
$ model("The capital of France is ", max_tokens=10)
< Model logging > 
"....Paris."
```

---------

Co-authored-by: R. Lance Martin <rlm@Rs-MacBook-Pro.local>
2023-07-04 08:53:52 -07:00
Stefano Lottini
6631fd5168
Align cassio versions between examples for Cassandra integration (#7099)
Just reducing confusion by requiring cassio>=0.0.7 consistently across
examples.
2023-07-04 04:21:48 -06:00
Lance Martin
9ca4c54428
Minor updates to notebook for MultiQueryRetriever (#7102)
* Add an easier-to-run example.
* Add logging per https://github.com/hwchase17/langchain/pull/6891.
* Updated params per https://github.com/hwchase17/langchain/pull/5962.

---------

Co-authored-by: R. Lance Martin <rlm@Rs-MacBook-Pro.local>
Co-authored-by: Lance Martin <lance@langchain.dev>
2023-07-03 17:32:50 -07:00
genewoo
e49abd1277
Add Metal support to llama.cpp doc (#7092)
- Description: Add Metal support to llama.cpp doc
  - Issue: #7091 
  - Dependencies: N/A
  - Twitter handle: gene_wu
2023-07-03 13:35:39 -06:00
rjarun8
e2d61ab85a
Add SpacyEmbeddings class (#6967)
- Description: Added a new SpacyEmbeddings class for generating
embeddings using the Spacy library.
- Issue: Sentencebert/Bert/Spacy/Doc2vec embedding support #6952
- Dependencies: This change requires the Spacy library and the
'en_core_web_sm' Spacy model.
- Tag maintainer: @dev2049
- Twitter handle: N/A

This change includes a new SpacyEmbeddings class, but does not include a
test or an example notebook.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-03 09:38:31 -06:00
adam91holt
80e86b602e
Remove duplicate mongodb integration doc (#7006) 2023-07-03 02:23:33 -06:00
Johnny Lim
a081e419a0
Fix sample in FAISS section (#7050)
This PR fixes a sample in the FAISS section in the reference docs.
2023-07-03 02:18:32 -06:00
Leonid Ganeline
200be43da6
added Brave Search document_loader (#6989)
- Added `Brave Search` document loader.
- Refactored BraveSearch wrapper
- Added a Jupyter Notebook example
- Added `Ecosystem/Integrations` BraveSearch page 

Please review:
  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
2023-07-02 19:01:24 -07:00
Sergey Kozlov
6d15854cda
Add JSON Lines support to JSONLoader (#6913)
**Description**:

The JSON Lines format is used by some services such as OpenAI and
HuggingFace. It's also a convenient alternative to CSV.

This PR adds JSON Lines support to `JSONLoader` and also updates related
tests.

**Tag maintainer**: @rlancemartin, @eyurtsev.

PS I was not able to build docs locally so didn't update related
section.
2023-07-02 12:32:41 -07:00
Ofer Mendelevitch
153b56d19b
Vectara upd2 (#6506)
Update to Vectara integration 
- By user request added "add_files" to take advantage of Vectara
capabilities to process files on the backend, without the need for
separate loading of documents and chunking in the chain.
- Updated vectara.ipynb example notebook to be broader and added testing
of add_file()
 
  @hwchase17 - project lead

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-07-02 12:15:50 -07:00
Leonid Ganeline
77ae8084a0
docstrings document_loaders 1 (#6847)
- Updated docstrings in `document_loaders`
- several code fixes.
- added `docs/extras/ecosystem/integrations/airtable.md`

@rlancemartin, @eyurtsev
2023-07-02 12:13:04 -07:00
Stefano Lottini
8d2281a8ca
Second Attempt - Add concurrent insertion of vector rows in the Cassandra Vector Store (#7017)
Retrying with the same improvements as in #6772, this time trying not to
mess up with branches.

@rlancemartin doing a fresh new PR from a branch with a new name. This
should do. Thank you for your help!

---------

Co-authored-by: Jonathan Ellis <jbellis@datastax.com>
Co-authored-by: rlm <pexpresss31@gmail.com>
2023-07-01 11:09:52 -07:00
Matt Robinson
0498dad562
feat: enable UnstructuredEmailLoader to process attachments (#6977)
### Summary

Updates `UnstructuredEmailLoader` so that it can process attachments in
addition to the e-mail content. The loader will process attachments if
the `process_attachments` kwarg is passed when the loader is
instantiated.

### Testing

```python

file_path = "fake-email-attachment.eml"
loader = UnstructuredEmailLoader(
    file_path, mode="elements", process_attachments=True
)
docs = loader.load()
docs[-1]
```

### Reviewers

-  @rlancemartin 
-  @eyurtsev
- @hwchase17
2023-07-01 06:09:26 -07:00
Zander Chase
b0859c9b18
Add New Retriever Interface with Callbacks (#5962)
Handle the new retriever events in a way that (I think) is entirely
backwards compatible? Needs more testing for some of the chain changes
and all.

This creates an entire new run type, however. We could also just treat
this as an event within a chain run presumably (same with memory)

Adds a subclass initializer that upgrades old retriever implementations
to the new schema, along with tests to ensure they work.

First commit doesn't upgrade any of our retriever implementations (to
show that we can pass the tests along with additional ones testing the
upgrade logic).

Second commit upgrades the known universe of retrievers in langchain.

- [X] Add callback handling methods for retriever start/end/error (open
to renaming to 'retrieval' if you want that)
- [X] Update BaseRetriever schema to support callbacks
- [X] Tests for upgrading old "v1" retrievers for backwards
compatibility
- [X] Update existing retriever implementations to implement the new
interface
- [X] Update calls within chains to .{a]get_relevant_documents to pass
the child callback manager
- [X] Update the notebooks/docs to reflect the new interface
- [X] Test notebooks thoroughly


Not handled:
- Memory pass throughs: retrieval memory doesn't have a parent callback
manager passed through the method

---------

Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>
2023-06-30 14:44:03 -07:00
William FH
a5b206caf3
Remove Promptlayer Notebook (#6996)
It's breaking our docs build
2023-06-30 14:30:24 -07:00
Daniel Chalef
b26cca8008
Zep Authentication (#6728)
## Description: Add Zep API Key argument to ZepChatMessageHistory and
ZepRetriever
- correct docs site links
- add zep api_key auth to constructors

ZepChatMessageHistory: @hwchase17, 
ZepRetriever: @rlancemartin, @eyurtsev
2023-06-30 14:24:26 -07:00
William FH
64039b9f11
Promptlayer Callback (#6975)
Co-authored-by: Saleh Hindi <saleh.hindi.one@gmail.com>
Co-authored-by: jped <jonathanped@gmail.com>
2023-06-30 08:32:42 -07:00
Davis Chase
f780678910
Add back in clickhouse mongo vecstore notebooks (#6949) 2023-06-29 19:21:47 -07:00
Kacper Łukawski
140ba682f1
Support named vectors in Qdrant (#6871)
# Description

This PR makes it possible to use named vectors from Qdrant in Langchain.
That was requested multiple times, as people want to reuse externally
created collections in Langchain. It doesn't change anything for the
existing applications. The changes were covered with some integration
tests and included in the docs.

## Example

```python
Qdrant.from_documents(
    docs,
    embeddings,
    location=":memory:",
    collection_name="my_documents",
    vector_name="custom_vector",
)
```

### Issue: #2594 

Tagging @rlancemartin & @eyurtsev. I'd appreciate your review.
2023-06-29 15:14:22 -07:00
corranmac
20c6ade2fc
Grobid parser for Scientific Articles from PDF (#6729)
### Scientific Article PDF Parsing via Grobid

`Description:`
This change adds the GrobidParser class, which uses the Grobid library
to parse scientific articles into a universal XML format containing the
article title, references, sections, section text etc. The GrobidParser
uses a local Grobid server to return PDFs document as XML and parses the
XML to optionally produce documents of individual sentences or of whole
paragraphs. Metadata includes the text, paragraph number, pdf relative
bboxes, pages (text may overlap over two pages), section title
(Introduction, Methodology etc), section_number (i.e 1.1, 2.3), the
title of the paper and finally the file path.
      
Grobid parsing is useful beyond standard pdf parsing as it accurately
outputs sections and paragraphs within them. This allows for
post-fitering of results for specific sections i.e. limiting results to
the methodology section or results. While sections are split via
headings, ideally they could be classified specifically into
introduction, methodology, results, discussion, conclusion. I'm
currently experimenting with chatgpt-3.5 for this function, which could
later be implemented as a textsplitter.

`Dependencies:`
For use, the grobid repo must be cloned and Java must be installed, for
colab this is:

```
!apt-get install -y openjdk-11-jdk -q
!update-alternatives --set java /usr/lib/jvm/java-11-openjdk-amd64/bin/java
!git clone https://github.com/kermitt2/grobid.git
os.environ["JAVA_HOME"] = "/usr/lib/jvm/java-11-openjdk-amd64"
os.chdir('grobid')
!./gradlew clean install
```

Once installed the server is ran on localhost:8070 via
```
get_ipython().system_raw('nohup ./gradlew run > grobid.log 2>&1 &')
```

@rlancemartin, @eyurtsev

Twitter Handle: @Corranmac

Grobid Demo Notebook is
[here](https://colab.research.google.com/drive/1X-St_mQRmmm8YWtct_tcJNtoktbdGBmd?usp=sharing).

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-29 14:29:29 -07:00
Harrison Chase
0ba175e13f
move octo notebook (#6901) 2023-06-29 12:20:55 -07:00
Stefano Lottini
75fb9d2fdc
Cassandra support for chat history using CassIO library (#6771)
### Overview

This PR aims at building on #4378, expanding the capabilities and
building on top of the `cassIO` library to interface with the database
(as opposed to using the core drivers directly).

Usage of `cassIO` (a library abstracting Cassandra access for
ML/GenAI-specific purposes) is already established since #6426 was
merged, so no new dependencies are introduced.

In the same spirit, we try to uniform the interface for using Cassandra
instances throughout LangChain: all our appreciation of the work by
@jj701 notwithstanding, who paved the way for this incremental work
(thank you!), we identified a few reasons for changing the way a
`CassandraChatMessageHistory` is instantiated. Advocating a syntax
change is something we don't take lighthearted way, so we add some
explanations about this below.

Additionally, this PR expands on integration testing, enables use of
Cassandra's native Time-to-Live (TTL) features and improves the phrasing
around the notebook example and the short "integrations" documentation
paragraph.

We would kindly request @hwchase to review (since this is an elaboration
and proposed improvement of #4378 who had the same reviewer).

### About the __init__ breaking changes

There are
[many](https://docs.datastax.com/en/developer/python-driver/3.28/api/cassandra/cluster/)
options when creating the `Cluster` object, and new ones might be added
at any time. Choosing some of them and exposing them as `__init__`
parameters `CassandraChatMessageHistory` will prove to be insufficient
for at least some users.

On the other hand, working through `kwargs` or adding a long, long list
of arguments to `__init__` is not a desirable option either. For this
reason, (as done in #6426), we propose that whoever instantiates the
Chat Message History class provide a Cassandra `Session` object, ready
to use. This also enables easier injection of mocks and usage of
Cassandra-compatible connections (such as those to the cloud database
DataStax Astra DB, obtained with a different set of init parameters than
`contact_points` and `port`).

We feel that a breaking change might still be acceptable since LangChain
is at `0.*`. However, while maintaining that the approach we propose
will be more flexible in the future, room could be made for a
"compatibility layer" that respects the current init method. Honestly,
we would to that only if there are strong reasons for it, as that would
entail an additional maintenance burden.

### Other changes

We propose to remove the keyspace creation from the class code for two
reasons: first, production Cassandra instances often employ RBAC so that
the database user reading/writing from tables does not necessarily (and
generally shouldn't) have permission to create keyspaces, and second
that programmatic keyspace creation is not a best practice (it should be
done more or less manually, with extra care about schema mismatched
among nodes, etc). Removing this (usually unnecessary) operation from
the `__init__` path would also improve initialization performance
(shorter time).

We suggest, likewise, to remove the `__del__` method (which would close
the database connection), for the following reason: it is the
recommended best practice to create a single Cassandra `Session` object
throughout an application (it is a resource-heavy object capable to
handle concurrency internally), so in case Cassandra is used in other
ways by the app there is the risk of truncating the connection for all
usages when the history instance is destroyed. Moreover, the `Session`
object, in typical applications, is best left to garbage-collect itself
automatically.

As mentioned above, we defer the actual database I/O to the `cassIO`
library, which is designed to encode practices optimized for LLM
applications (among other) without the need to expose LangChain
developers to the internals of CQL (Cassandra Query Language). CassIO is
already employed by the LangChain's Vector Store support for Cassandra.

We added a few more connection options in the companion notebook example
(most notably, Astra DB) to encourage usage by anyone who cannot run
their own Cassandra cluster.

We surface the `ttl_seconds` option for automatic handling of an
expiration time to chat history messages, a likely useful feature given
that very old messages generally may lose their importance.

We elaborated a bit more on the integration testing (Time-to-live,
separation of "session ids", ...).

### Remarks from linter & co.

We reinstated `cassio` as a dependency both in the "optional" group and
in the "integration testing" group of `pyproject.toml`. This might not
be the right thing do to, in which case the author of this PR offer his
apologies (lack of confidence with Poetry - happy to be pointed in the
right direction, though!).

During linter tests, we were hit by some errors which appear unrelated
to the code in the PR. We left them here and report on them here for
awareness:

```
langchain/vectorstores/mongodb_atlas.py:137: error: Argument 1 to "insert_many" of "Collection" has incompatible type "List[Dict[str, Sequence[object]]]"; expected "Iterable[Union[MongoDBDocumentType, RawBSONDocument]]"  [arg-type]
langchain/vectorstores/mongodb_atlas.py:186: error: Argument 1 to "aggregate" of "Collection" has incompatible type "List[object]"; expected "Sequence[Mapping[str, Any]]"  [arg-type]

langchain/vectorstores/qdrant.py:16: error: Name "grpc" is not defined  [name-defined]
langchain/vectorstores/qdrant.py:19: error: Name "grpc" is not defined  [name-defined]
langchain/vectorstores/qdrant.py:20: error: Name "grpc" is not defined  [name-defined]
langchain/vectorstores/qdrant.py:22: error: Name "grpc" is not defined  [name-defined]
langchain/vectorstores/qdrant.py:23: error: Name "grpc" is not defined  [name-defined]
```

In the same spirit, we observe that to even get `import langchain` run,
it seems that a `pip install bs4` is missing from the minimal package
installation path.

Thank you!
2023-06-29 10:50:34 -07:00
Shashank Deshpande
99cfe192da
added example notebook - use custom functions with openai agent (#6865)
<!-- 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: @dev2049
  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
  - Models / Prompts: @hwchase17, @dev2049
  - Memory: @hwchase17
  - Agents / Tools / Toolkits: @vowelparrot
  - 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
 -->
2023-06-28 22:07:33 -07:00
Robert Lewis
c9c8d2599e
Update Zapier Jupyter notebook to include brief OAuth example (#6892)
Description: Adds a brief example of using an OAuth access token with
the Zapier wrapper. Also links to the Zapier documentation to learn more
about OAuth flows.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-28 18:06:22 -07:00
Yaohui Wang
9d1bd18596
feat (documents): add LarkSuite document loader (#6420)
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

<!-- Remove if not applicable -->

### Summary

This PR adds a LarkSuite (FeiShu) document loader. 
> [LarkSuite](https://www.larksuite.com/) is an enterprise collaboration
platform developed by ByteDance.

### Tests

- an integration test case is added
- an example notebook showing usage is added. [Notebook
preview](https://github.com/yaohui-wyh/langchain/blob/master/docs/extras/modules/data_connection/document_loaders/integrations/larksuite.ipynb)

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

### Who can review?

- PTAL @eyurtsev @hwchase17

<!-- For a quicker response, figure out the right person to tag with @

  @hwchase17 - project lead

  Tracing / Callbacks
  - @agola11

  Async
  - @agola11

  DataLoaders
  - @eyurtsev

  Models
  - @hwchase17
  - @agola11

  Agents / Tools / Toolkits
  - @hwchase17

  VectorStores / Retrievers / Memory
  - @dev2049

 -->

---------

Co-authored-by: Yaohui Wang <wangyaohui.01@bytedance.com>
2023-06-27 23:08:05 -07:00
Jingsong Gao
a435a436c1
feat(document_loaders): add tencent cos directory and file loader (#6401)
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

<!-- Remove if not applicable -->

- add tencent cos directory and file support for document-loader

#### Before submitting

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

#### Who can review?

@eyurtsev
2023-06-27 23:07:20 -07:00
Lance Martin
3f9900a864
Create MultiQueryRetriever (#6833)
Distance-based vector database retrieval embeds (represents) queries in
high-dimensional space and finds similar embedded documents based on
"distance". But, retrieval may produce difference results with subtle
changes in query wording or if the embeddings do not capture the
semantics of the data well. Prompt engineering / tuning is sometimes
done to manually address these problems, but can be tedious.

The `MultiQueryRetriever` automates the process of prompt tuning by
using an LLM to generate multiple queries from different perspectives
for a given user input query. For each query, it retrieves a set of
relevant documents and takes the unique union across all queries to get
a larger set of potentially relevant documents. By generating multiple
perspectives on the same question, the `MultiQueryRetriever` might be
able to overcome some of the limitations of the distance-based retrieval
and get a richer set of results.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-27 22:59:40 -07:00
Tim Asp
3ca1a387c2
Web Loader: Add proxy support (#6792)
Proxies are helpful, especially when you start querying against more
anti-bot websites.

[Proxy
services](https://developers.oxylabs.io/advanced-proxy-solutions/web-unblocker/making-requests)
(of which there are many) and `requests` make it easy to rotate IPs to
prevent banning by just passing along a simple dict to `requests`.

CC @rlancemartin, @eyurtsev
2023-06-27 22:27:49 -07:00
Matt Robinson
dd2a151543
Docs/unstructured api key (#6781)
### Summary

The Unstructured API will soon begin requiring API keys. This PR updates
the Unstructured integrations docs with instructions on how to generate
Unstructured API keys.

### Reviewers

@rlancemartin
@eyurtsev
@hwchase17
2023-06-27 16:54:15 -07:00
Matt Robinson
b24472eae3
feat: Add UnstructuredOrgModeLoader (#6842)
### Summary

Adds `UnstructuredOrgModeLoader` for processing
[Org-mode](https://en.wikipedia.org/wiki/Org-mode) documents.

### Testing

```python
from langchain.document_loaders import UnstructuredOrgModeLoader

loader = UnstructuredOrgModeLoader(
    file_path="example_data/README.org", mode="elements"
)
docs = loader.load()
print(docs[0])
```

### Reviewers

- @rlancemartin
- @eyurtsev
- @hwchase17
2023-06-27 16:34:17 -07:00
Cristóbal Carnero Liñán
e494b0a09f
feat (documents): add a source code loader based on AST manipulation (#6486)
#### Summary

A new approach to loading source code is implemented:

Each top-level function and class in the code is loaded into separate
documents. Then, an additional document is created with the top-level
code, but without the already loaded functions and classes.

This could improve the accuracy of QA chains over source code.

For instance, having this script:

```
class MyClass:
    def __init__(self, name):
        self.name = name

    def greet(self):
        print(f"Hello, {self.name}!")

def main():
    name = input("Enter your name: ")
    obj = MyClass(name)
    obj.greet()

if __name__ == '__main__':
    main()
```

The loader will create three documents with this content:

First document:
```
class MyClass:
    def __init__(self, name):
        self.name = name

    def greet(self):
        print(f"Hello, {self.name}!")
```

Second document:
```
def main():
    name = input("Enter your name: ")
    obj = MyClass(name)
    obj.greet()
```

Third document:
```
# Code for: class MyClass:

# Code for: def main():

if __name__ == '__main__':
    main()
```

A threshold parameter is added to control whether small scripts are
split in this way or not.

At this moment, only Python and JavaScript are supported. The
appropriate parser is determined by examining the file extension.

#### Tests

This PR adds:

- Unit tests
- Integration tests

#### Dependencies

Only one dependency was added as optional (needed for the JavaScript
parser).

#### Documentation

A notebook is added showing how the loader can be used.

#### Who can review?

@eyurtsev @hwchase17

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-27 15:58:47 -07:00
Robert Lewis
da462d9dd4
Zapier update oauth support (#6780)
Description: Update documentation to

1) point to updated documentation links at Zapier.com (we've revamped
our help docs and paths), and
2) To provide clarity how to use the wrapper with an access token for
OAuth support

Demo:

Initializing the Zapier Wrapper with an OAuth Access Token

`ZapierNLAWrapper(zapier_nla_oauth_access_token="<redacted>")`

Using LangChain to resolve the current weather in Vancouver BC
leveraging Zapier NLA to lookup weather by coords.

```
> Entering new  chain...
 I need to use a tool to get the current weather.
Action: The Weather: Get Current Weather
Action Input: Get the current weather for Vancouver BC
Observation: {"coord__lon": -123.1207, "coord__lat": 49.2827, "weather": [{"id": 802, "main": "Clouds", "description": "scattered clouds", "icon": "03d", "icon_url": "http://openweathermap.org/img/wn/03d@2x.png"}], "weather[]icon_url": ["http://openweathermap.org/img/wn/03d@2x.png"], "weather[]icon": ["03d"], "weather[]id": [802], "weather[]description": ["scattered clouds"], "weather[]main": ["Clouds"], "base": "stations", "main__temp": 71.69, "main__feels_like": 71.56, "main__temp_min": 67.64, "main__temp_max": 76.39, "main__pressure": 1015, "main__humidity": 64, "visibility": 10000, "wind__speed": 3, "wind__deg": 155, "wind__gust": 11.01, "clouds__all": 41, "dt": 1687806607, "sys__type": 2, "sys__id": 2011597, "sys__country": "CA", "sys__sunrise": 1687781297, "sys__sunset": 1687839730, "timezone": -25200, "id": 6173331, "name": "Vancouver", "cod": 200, "summary": "scattered clouds", "_zap_search_was_found_status": true}
Thought: I now know the current weather in Vancouver BC.
Final Answer: The current weather in Vancouver BC is scattered clouds with a temperature of 71.69 and wind speed of 3
```
2023-06-27 11:46:32 -07:00
Joshua Carroll
24e4ae95ba
Initial Streamlit callback integration doc (md) (#6788)
**Description:** Add a documentation page for the Streamlit Callback
Handler integration (#6315)

Notes:
- Implemented as a markdown file instead of a notebook since example
code runs in a Streamlit app (happy to discuss / consider alternatives
now or later)
- Contains an embedded Streamlit app ->
https://mrkl-minimal.streamlit.app/ Currently this app is hosted out of
a Streamlit repo but we're working to migrate the code to a LangChain
owned repo


![streamlit_docs](https://github.com/hwchase17/langchain/assets/116604821/0b7a6239-361f-470c-8539-f22c40098d1a)

cc @dev2049 @tconkling
2023-06-27 11:43:49 -07:00
WaseemH
7ac9b22886
RecusiveUrlLoader to RecursiveUrlLoader (#6787) 2023-06-26 23:12:14 -07:00
Leonid Ganeline
49c864fa18
docs: vectorstore upgrades 2 (#6796)
updated vectorstores/ notebooks; added new integrations into
ecosystem/integrations/
@dev2049
@rlancemartin, @eyurtsev
2023-06-26 22:55:04 -07:00
Chris Pappalardo
70f7c2bb2e
align chroma vectorstore get with chromadb to enable where filtering (#6686)
allows for where filtering on collection via get

- Description: aligns langchain chroma vectorstore get with underlying
[chromadb collection
get](https://github.com/chroma-core/chroma/blob/main/chromadb/api/models/Collection.py#L103)
allowing for where filtering, etc.
  - Issue: NA
  - Dependencies: none
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: @pappanaka
2023-06-26 10:51:20 -07:00
Santiago Delgado
d84a3bcf7a
Office365 Tool (#6306)
#### Background
With the development of [structured
tools](https://blog.langchain.dev/structured-tools/), the LangChain team
expanded the platform's functionality to meet the needs of new
applications. The GMail tool, empowered by structured tools, now
supports multiple arguments and powerful search capabilities,
demonstrating LangChain's ability to interact with dynamic data sources
like email servers.

#### Challenge
The current GMail tool only supports GMail, while users often utilize
other email services like Outlook in Office365. Additionally, the
proposed calendar tool in PR
https://github.com/hwchase17/langchain/pull/652 only works with Google
Calendar, not Outlook.

#### Changes
This PR implements an Office365 integration for LangChain, enabling
seamless email and calendar functionality with a single authentication
process.

#### Future Work
With the core Office365 integration complete, future work could include
integrating other Office365 tools such as Tasks and Address Book.

#### Who can review?
@hwchase17 or @vowelparrot can review this PR

#### Appendix
@janscas, I utilized your [O365](https://github.com/O365/python-o365)
library extensively. Given the rising popularity of LangChain and
similar AI frameworks, the convergence of libraries like O365 and tools
like this one is likely. So, I wanted to keep you updated on our
progress.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-26 02:59:09 -07:00
Pau Ramon Revilla
87802c86d9
Added a MHTML document loader (#6311)
MHTML is a very interesting format since it's used both for emails but
also for archived webpages. Some scraping projects want to store pages
in disk to process them later, mhtml is perfect for that use case.

This is heavily inspired from the beautifulsoup html loader, but
extracting the html part from the mhtml file.

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-25 13:12:08 -07:00
Matt Robinson
be68f6f8ce
feat: Add UnstructuredRSTLoader (#6594)
### Summary

Adds an `UnstructuredRSTLoader` for loading
[reStructuredText](https://en.wikipedia.org/wiki/ReStructuredText) file.

### Testing

```python
from langchain.document_loaders import UnstructuredRSTLoader

loader = UnstructuredRSTLoader(
    file_path="example_data/README.rst", mode="elements"
)
docs = loader.load()
print(docs[0])
```

### Reviewers

- @hwchase17 
- @rlancemartin 
- @eyurtsev
2023-06-25 12:41:57 -07:00
Baichuan Sun
9fbe346860
Amazon API Gateway hosted LLM (#6673)
This PR adds a new LLM class for the Amazon API Gateway hosted LLM. The
PR also includes example notebooks for using the LLM class in an Agent
chain.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-23 21:27:25 -07:00
Davis Chase
f1e1ac2a01
chroma nb close img tag (#6669) 2023-06-23 15:41:54 -07:00
Davis Chase
5e5b30b74f
openapi -> openai nit (#6667) 2023-06-23 15:09:02 -07:00
Jeff Huber
2acf109c4b
update chroma notebook (#6664)
@rlancemartin I updated the notebook for Chroma to hopefully be a lot
easier for users.
2023-06-23 15:03:06 -07:00
Piyush Jain
b1de927f1b
Kendra retriever api (#6616)
## Description
Replaces [Kendra
Retriever](https://github.com/hwchase17/langchain/blob/master/langchain/retrievers/aws_kendra_index_retriever.py)
with an updated version that uses the new [retriever
API](https://docs.aws.amazon.com/kendra/latest/dg/searching-retrieve.html)
which is better suited for retrieval augmented generation (RAG) systems.

**Note**: This change requires the latest version (1.26.159) of boto3 to
work. `pip install -U boto3` to upgrade the boto3 version.

cc @hupe1980
cc @dev2049
2023-06-23 14:59:35 -07:00
Ikko Eltociear Ashimine
73da193a4b
Fix typo in myscale_self_query.ipynb (#6601) 2023-06-23 14:57:12 -07:00
Lance Martin
c2b25c17c5
Recursive URL loader (#6455)
We may want to process load all URLs under a root directory.

For example, let's look at the [LangChain JS
documentation](https://js.langchain.com/docs/).

This has many interesting child pages that we may want to read in bulk.

Of course, the `WebBaseLoader` can load a list of pages. 

But, the challenge is traversing the tree of child pages and actually
assembling that list!
 
We do this using the `RecusiveUrlLoader`.

This also gives us the flexibility to exclude some children (e.g., the
`api` directory with > 800 child pages).
2023-06-23 13:09:00 -07:00
Lance Martin
393f469eb3
Create merge loader that combines documents from a set of loaders (#6659)
Simple utility loader that combines documents from a set of specified
loaders.
2023-06-23 13:02:48 -07:00
Davis Chase
6988039975
openapi_openai docstring (#6661) 2023-06-23 11:38:33 -07:00
Davis Chase
e013459b18
Openapi to openai (#6658) 2023-06-23 11:00:34 -07:00
Lance Martin
6e69bfbb28
Loader for OpenCityData and minor cleanups to Pandas, Airtable loaders (#6301)
Many cities have open data portals for events like crime, traffic, etc.

Socrata provides an API for many, including SF (e.g., see
[here](https://dev.socrata.com/foundry/data.sfgov.org/tmnf-yvry)).

This is a new data loader for city data that uses Socrata API.
2023-06-22 22:20:42 -07:00
Christoph Kahl
9d42621fa4
added redis method to delete entries by keys (#6222)
In addition to my last pr (return keys of added entries), we also need a
method to delete the entries by keys.

@dev2049
2023-06-22 13:26:47 -07:00
Harrison Chase
a9108c1809
add mongo (HOLD) (#6437)
do not merge in
2023-06-22 11:08:12 -07:00
Lance Martin
30f7288082
MD header text splitter returns Documents (#6571)
Return `Documents` from MD header text splitter to simplify UX.

Updates the test as well as example notebooks.
2023-06-22 09:25:38 -07:00
minhajul-clarifai
6e57306a13
Clarifai integration (#5954)
# Changes
This PR adds [Clarifai](https://www.clarifai.com/) integration to
Langchain. Clarifai is an end-to-end AI Platform. Clarifai offers user
the ability to use many types of LLM (OpenAI, cohere, ect and other open
source models). As well, a clarifai app can be treated as a vector
database to upload and retrieve data. The integrations includes:
- Clarifai LLM integration: Clarifai supports many types of language
model that users can utilize for their application
- Clarifai VectorDB: A Clarifai application can hold data and
embeddings. You can run semantic search with the embeddings

#### Before submitting
- [x] Added integration test for LLM 
- [x] Added integration test for VectorDB 
- [x] Added notebook for LLM 
- [x] Added notebook for VectorDB 

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-22 08:00:15 -07:00
Jeroen Van Goey
7f6f5c2a6a
Add missing word in comment (#6587)
Changed

```
# Do this so we can exactly what's going on under the hood
```
to
```
# Do this so we can see exactly what's going on under the hood
```
2023-06-22 07:54:28 -07:00
Davis Chase
d50de2728f
Add AzureML endpoint LLM wrapper (#6580)
### Description

We have added a new LLM integration `azureml_endpoint` that allows users
to leverage models from the AzureML platform. Microsoft recently
announced the release of [Azure Foundation

Models](https://learn.microsoft.com/en-us/azure/machine-learning/concept-foundation-models?view=azureml-api-2)
which users can find in the AzureML Model Catalog. The Model Catalog
contains a variety of open source and Hugging Face models that users can
deploy on AzureML. The `azureml_endpoint` allows LangChain users to use
the deployed Azure Foundation Models.

### Dependencies

No added dependencies were required for the change.

### Tests

Integration tests were added in
`tests/integration_tests/llms/test_azureml_endpoint.py`.

### Notebook

A Jupyter notebook demonstrating how to use `azureml_endpoint` was added
to `docs/modules/llms/integrations/azureml_endpoint_example.ipynb`.

### Twitters

[Prakhar Gupta](https://twitter.com/prakhar_in)
[Matthew DeGuzman](https://twitter.com/matthew_d13)

---------

Co-authored-by: Matthew DeGuzman <91019033+matthewdeguzman@users.noreply.github.com>
Co-authored-by: prakharg-msft <75808410+prakharg-msft@users.noreply.github.com>
2023-06-22 01:46:01 -07:00
Davis Chase
4fabd02d25
Add OpenLLM wrapper(#6578)
LLM wrapper for models served with OpenLLM

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Authored-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
Co-authored-by: Chaoyu <paranoyang@gmail.com>
2023-06-22 01:18:14 -07:00
Muhammad Vaid
ae81b96b60
Detailed using the Twilio tool to send messages with 3rd party apps incl. WhatsApp (#6562)
Everything needed to support sending messages over WhatsApp Business
Platform (GA), Facebook Messenger (Public Beta) and Google Business
Messages (Private Beta) was present. Just added some details on
leveraging it.
2023-06-21 19:26:50 -07:00
Andrey E. Vedishchev
a2a0715bd4
Minor Grammar Fixes in Docs and Comments (#6536)
Just some grammar fixes: I found "retriver" instead of "retriever" in
several comments across the documentation and in the comments. I fixed
it.


Co-authored-by: andrey.vedishchev <andrey.vedishchev@rgigroup.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-21 09:53:31 -07:00
dirtysalt
57cc3d1d3d
[Feature][VectorStore] Support StarRocks as vector db (#6119)
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

<!-- Remove if not applicable -->

Fixes # (issue)

#### Before submitting

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

Here are some examples to use StarRocks as vectordb

```
from langchain.vectorstores import StarRocks
from langchain.vectorstores.starrocks import StarRocksSettings

embeddings = OpenAIEmbeddings()

# conifgure starrocks settings
settings = StarRocksSettings()
settings.port = 41003
settings.host = '127.0.0.1'
settings.username = 'root'
settings.password = ''
settings.database = 'zya'

# to fill new embeddings
docsearch = StarRocks.from_documents(split_docs, embeddings, config = settings)   


# or to use already-built embeddings in database.
docsearch = StarRocks(embeddings, settings)
```

#### Who can review?

Tag maintainers/contributors who might be interested:

@dev2049 

<!-- For a quicker response, figure out the right person to tag with @

  @hwchase17 - project lead

  Tracing / Callbacks
  - @agola11

  Async
  - @agola11

  DataLoaders
  - @eyurtsev

  Models
  - @hwchase17
  - @agola11

  Agents / Tools / Toolkits
  - @hwchase17

  VectorStores / Retrievers / Memory
  - @dev2049

 -->

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-21 09:02:33 -07:00
Harrison Chase
ace442b992
bump to ver 208 (#6540) 2023-06-21 07:32:36 -07:00
Harrison Chase
53c1f120a8
Harrison/multi tool (#6518) 2023-06-21 07:19:52 -07:00
Naman Modi
37a89918e0
Infino integration for simplified logs, metrics & search across LLM data & token usage (#6218)
### Integration of Infino with LangChain for Enhanced Observability

This PR aims to integrate [Infino](https://github.com/infinohq/infino),
an open source observability platform written in rust for storing
metrics and logs at scale, with LangChain, providing users with a
streamlined and efficient method of tracking and recording LangChain
experiments. By incorporating Infino into LangChain, users will be able
to gain valuable insights and easily analyze the behavior of their
language models.

#### Please refer to the following files related to integration:
- `InfinoCallbackHandler`: A [callback
handler](https://github.com/naman-modi/langchain/blob/feature/infino-integration/langchain/callbacks/infino_callback.py)
specifically designed for storing chain responses within Infino.
- Example `infino.ipynb` file: A comprehensive notebook named
[infino.ipynb](https://github.com/naman-modi/langchain/blob/feature/infino-integration/docs/extras/modules/callbacks/integrations/infino.ipynb)
has been included to guide users on effectively leveraging Infino for
tracking LangChain requests.
- [Integration
Doc](https://github.com/naman-modi/langchain/blob/feature/infino-integration/docs/extras/ecosystem/integrations/infino.mdx)
for Infino integration.

By integrating Infino, LangChain users will gain access to powerful
visualization and debugging capabilities. Infino enables easy tracking
of inputs, outputs, token usage, execution time of LLMs. This
comprehensive observability ensures a deeper understanding of individual
executions and facilitates effective debugging.

Co-authors: @vinaykakade @savannahar68
---------

Co-authored-by: Vinay Kakade <vinaykakade@gmail.com>
2023-06-21 01:38:20 -07:00
Anubhav Bindlish
94c7899257
Integrate Rockset as Vectorstore (#6216)
This PR adds Rockset as a vectorstore for langchain.
[Rockset](https://rockset.com/blog/introducing-vector-search-on-rockset/)
is a real time OLAP database which provides a fast and efficient vector
search functionality. Further since it is entirely schemaless, it can
store metadata in separate columns thereby allowing fast metadata
filters during vector similarity search (as opposed to storing the
entire metadata in a single JSON column). It currently supports three
distance functions: `COSINE_SIMILARITY`, `EUCLIDEAN_DISTANCE`, and
`DOT_PRODUCT`.

This PR adds `rockset` client as an optional dependency. 

We would love a twitter shoutout, our handle is
https://twitter.com/RocksetCloud

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-21 01:22:27 -07:00
ElReyZero
ab7ecc9c30
Feat: Add a prompt template parameter to qa with structure chains (#6495)
This pull request introduces a new feature to the LangChain QA Retrieval
Chains with Structures. The change involves adding a prompt template as
an optional parameter for the RetrievalQA chains that utilize the
recently implemented OpenAI Functions.

The main purpose of this enhancement is to provide users with the
ability to input a more customizable prompt to the chain. By introducing
a prompt template as an optional parameter, users can tailor the prompt
to their specific needs and context, thereby improving the flexibility
and effectiveness of the RetrievalQA chains.

## Changes Made
- Created a new optional parameter, "prompt", for the RetrievalQA with
structure chains.
- Added an example to the RetrievalQA with sources notebook.

My twitter handle is @El_Rey_Zero

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-21 00:23:36 -07:00
Hassan Ouda
456ca3d587
Be able to use Codey models on Vertex AI (#6354)
Added the functionality to leverage 3 new Codey models from Vertex AI:
- code-bison - Code generation using the existing LLM integration
- code-gecko - Code completion using the existing LLM integration
- codechat-bison - Code chat using the existing chat_model integration

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-20 23:11:54 -07:00
囧囧
0fce8ef178
Add KuzuQAChain (#6454)
This PR adds `KuzuGraph` and `KuzuQAChain` for interacting with [Kùzu
database](https://github.com/kuzudb/kuzu). Kùzu is an in-process
property graph database management system (GDBMS) built for query speed
and scalability. The `KuzuGraph` and `KuzuQAChain` provide the same
functionality as the existing integration with NebulaGraph and Neo4j and
enables query generation and question answering over Kùzu database.

A notebook example and a simple test case have also been added.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-20 22:07:00 -07:00
TheOnlyWayUp
bb437646fc
typo(llamacpp.ipynb): 'condiser' -> 'consider' (#6474) 2023-06-20 18:48:25 -07:00
Davis Chase
3298bf4f00
docs/fix links (#6498) 2023-06-20 14:06:50 -07:00
Lance Martin
ae6196507d
Update notebook for MD header splitter and create new cookbook (#6399)
Move MD header text splitter example to its own cookbook.
2023-06-20 13:53:41 -07:00
Stefano Lottini
22af93d851
Vector store support for Cassandra (#6426)
This addresses #6291 adding support for using Cassandra (and compatible
databases, such as DataStax Astra DB) as a [Vector
Store](https://cwiki.apache.org/confluence/display/CASSANDRA/CEP-30%3A+Approximate+Nearest+Neighbor(ANN)+Vector+Search+via+Storage-Attached+Indexes).

A new class `Cassandra` is introduced, which complies with the contract
and interface for a vector store, along with the corresponding
integration test, a sample notebook and modified dependency toml.

Dependencies: the implementation relies on the library `cassio`, which
simplifies interacting with Cassandra for ML- and LLM-oriented
workloads. CassIO, in turn, uses the `cassandra-driver` low-lever
drivers to communicate with the database. The former is added as
optional dependency (+ in `extended_testing`), the latter was already in
the project.

Integration testing relies on a locally-running instance of Cassandra.
[Here](https://cassio.org/more_info/#use-a-local-vector-capable-cassandra)
a detailed description can be found on how to compile and run it (at the
time of writing the feature has not made it yet to a release).

During development of the integration tests, I added a new "fake
embedding" class for what I consider a more controlled way of testing
the MMR search method. Likewise, I had to amend what looked like a
glitch in the behaviour of `ConsistentFakeEmbeddings` whereby an
`embed_query` call would have bypassed storage of the requested text in
the class cache for use in later repeated invocations.

@dev2049 might be the right person to tag here for a review. Thank you!

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-20 10:46:20 -07:00
zhaoshengbo
ab44c24333
Add Alibaba Cloud OpenSearch as a new vector store (#6154)
Hello Folks,

Thanks for creating and maintaining this great project. I'm excited to
submit this PR to add Alibaba Cloud OpenSearch as a new vector store.

OpenSearch is a one-stop platform to develop intelligent search
services. OpenSearch was built based on the large-scale distributed
search engine developed by Alibaba. OpenSearch serves more than 500
business cases in Alibaba Group and thousands of Alibaba Cloud
customers. OpenSearch helps develop search services in different search
scenarios, including e-commerce, O2O, multimedia, the content industry,
communities and forums, and big data query in enterprises.

OpenSearch provides the vector search feature. In specific scenarios,
especially test question search and image search scenarios, you can use
the vector search feature together with the multimodal search feature to
improve the accuracy of search results.


This PR includes:

A AlibabaCloudOpenSearch class that can connect to the Alibaba Cloud
OpenSearch instance.
add embedings and metadata into a opensearch datasource.
querying by squared euclidean and metadata.
integration tests.
ipython notebook and docs.

I have read your contributing guidelines. And I have passed the tests
below

- [x]  make format
- [x]  make lint
- [x]  make coverage
- [x]  make test

---------

Co-authored-by: zhaoshengbo <shengbo.zsb@alibaba-inc.com>
2023-06-20 10:07:40 -07:00
Davis Chase
b7ad4c4c30
fix openai qa chain (#6487) 2023-06-20 10:01:13 -07:00
Harrison Chase
9eec7c3206
Harrison/unstructured page number (#6464)
Co-authored-by: Reza Sanaie <reza@sanaie.ca>
2023-06-19 22:31:43 -07:00
volodymyr-memsql
d2e9b621ab
Update SinglStoreDB vectorstore (#6423)
1. Introduced new distance strategies support: **DOT_PRODUCT** and
**EUCLIDEAN_DISTANCE** for enhanced flexibility.
2. Implemented a feature to filter results based on metadata fields.
3. Incorporated connection attributes specifying "langchain python sdk"
usage for enhanced traceability and debugging.
4. Expanded the suite of integration tests for improved code
reliability.
5. Updated the existing notebook with the usage example

@dev2049

---------

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-19 22:08:58 -07:00
Harrison Chase
02c0a1e77e
Harrison/functions in retrieval (#6463) 2023-06-19 22:07:58 -07:00
kYLe
3a58c4c3a0
Fixed a link typo /-/route -> /-/routes. and change endpoint format (#6186)
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

<!-- Remove if not applicable -->

Fixes a link typo from `/-/route` to `/-/routes`. 
and change endpoint format
from `f"{self.anyscale_service_url}/{self.anyscale_service_route}"` to
`f"{self.anyscale_service_url}{self.anyscale_service_route}"`
Also adding documentation about the format of the endpoint
#### Before submitting

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

#### Who can review?

Tag maintainers/contributors who might be interested:

<!-- For a quicker response, figure out the right person to tag with @

  @hwchase17 - project lead

  Tracing / Callbacks
  - @agola11

  Async
  - @agola11

  DataLoaders
  - @eyurtsev

  Models
  - @hwchase17
  - @agola11

  Agents / Tools / Toolkits
  - @hwchase17

  VectorStores / Retrievers / Memory
  - @dev2049

 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-19 22:05:54 -07:00
Leonid Ganeline
03b16ed2b1
docs retrievers fixes (#6299)
Fixed several inconsistencies:
- file names and notebook titles should be similar otherwise ToC on the
[retrievers
page](https://python.langchain.com/en/latest/modules/indexes/retrievers.html)
and on the left ToC tab are different. For example, now, `Self-querying
with Chroma` is not correctly alphabetically sorted because its file
named `chroma_self_query.ipynb`
- `Stringing compressors and document transformers...` demoted from `#`
to `##`. Otherwise, it appears in Toc.
- several formatting problems

#### Who can review?

@hwchase17 
@dev2049

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-19 22:04:35 -07:00
Dhruvil Shah
9494623869
Update web_base.ipynb (#6430)
Minor new line character in the markdown.

Also, this option is not yet in the latest version of LangChain
(0.0.190) from Conda. Maybe in the next update.

@eyurtsev
@hwchase17
2023-06-19 21:43:35 -07:00
Ismail Pelaseyed
d4e8e0f5ab
Add example for question answering over documents with OpenAI Function Agent (#6448)
This PR adds an example of doing question answering over documents using
OpenAI Function Agents.

#### Who can review?

@hwchase17

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-19 21:35:45 -07:00
Harrison Chase
286452c7f0 remove mongo 2023-06-19 10:04:14 -07:00
Harrison Chase
e9c2b280db
Harrison/refactor functions (#6408) 2023-06-18 23:13:42 -07:00
Harrison Chase
6a4a950a3c
changes to llm chain (#6328)
- return raw and full output (but keep run shortcut method functional)
- change output parser to take in generations (good for working with
messages)
- add output parser to base class, always run (default to same as
current)

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2023-06-18 22:49:47 -07:00
Fei Wang
50556f3b35
support memory for functions (#6165)
#### Before submitting
Add memory support for `OpenAIFunctionsAgent` like
`StructuredChatAgent`.


#### Who can review?
 @hwchase17

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-18 19:00:40 -07:00
Dhruvil Shah
ba90e3c990
Update web_base.ipynb for guiding purposes (#6248)
To bypass SSL verification errors during fetching, you can include the
`verify=False` parameter. This markdown proves useful, especially for
beginners in the field of web scraping.

<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

Fixes #6079 

#### Who can review?

Tag maintainers/contributors who might be interested:
@hwchase17 
@eyurtsev

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-18 17:47:10 -07:00
Dhruvil Shah
92f05a67a4
Add markdown to specify important arguments (#6246)
To bypass SSL verification errors during web scraping, you can include
the ssl_verify=False parameter along with the headers parameter. This
combination of arguments proves useful, especially for beginners in the
field of web scraping.

<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

Fixes #1829 

#### Before submitting

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->

#### Who can review?

Tag maintainers/contributors who might be interested:
@hwchase17 @eyurtsev 
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-18 17:47:00 -07:00
Harrison Chase
495128ba95
Harrison/functions docs improvements (#6389)
Co-authored-by: Sumanth Donthula <46747610+sumanthdonthula@users.noreply.github.com>
2023-06-18 16:57:33 -07:00
Harrison Chase
c0c2fd0782
Harrison/zep mem (#6388)
Co-authored-by: Daniel Chalef <131175+danielchalef@users.noreply.github.com>
2023-06-18 16:53:35 -07:00
Harrison Chase
b7159c15cc
Harrison/metaphor search fix (#6387)
Co-authored-by: jeffzwang <jeffreyzhiyuanwang@gmail.com>
2023-06-18 16:53:24 -07:00
Harrison Chase
9bf5b0defa
Harrison/myscale self query (#6376)
Co-authored-by: Fangrui Liu <fangruil@moqi.ai>
Co-authored-by: 刘 方瑞 <fangrui.liu@outlook.com>
Co-authored-by: Fangrui.Liu <fangrui.liu@ubc.ca>
2023-06-18 16:53:10 -07:00
Harrison Chase
bd8d418a95 Merge branch 'master' of github.com:hwchase17/langchain 2023-06-18 16:45:49 -07:00
Harrison Chase
3a75d59c3d searx - docs 2023-06-18 16:45:42 -07:00
Harrison Chase
a8cb9ee013
Harrison/gdrive enhancements (#6375)
Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io>
2023-06-18 11:07:23 -07:00
Lance Martin
370becdfc2
Add self query retriever example with MD header splitting (#6359)
Flesh out the notebook example for `MarkdownHeaderTextSplitter`
2023-06-17 21:40:20 -07:00
Lance Martin
2c97fbabbd
Update MD header text splitter notebook (#6339)
Highlight use case for maintaining header groups when splitting.
2023-06-17 13:19:27 -07:00
Harrison Chase
a2bbe3dda4
Harrison/mmr support for opensearch (#6349)
Co-authored-by: Mehmet Öner Yalçın <oneryalcin@gmail.com>
2023-06-17 12:22:37 -07:00
Harrison Chase
680d6bbbf8 fix titles in documentation 2023-06-17 11:09:11 -07:00
Saba Sturua
427551eabf
DocArray as a Retriever (#6031)
## DocArray as a Retriever

[DocArray](https://github.com/docarray/docarray) is an open-source tool
for managing your multi-modal data. It offers flexibility to store and
search through your data using various document index backends. This PR
introduces `DocArrayRetriever` - which works with any available backend
and serves as a retriever for Langchain apps.

Also, I added 2 notebooks:
DocArray Backends - intro to all 5 currently supported backends, how to
initialize, index, and use them as a retriever
DocArray Usage - showcasing what additional search parameters you can
pass to create versatile retrievers

Example:
```python
from docarray.index import InMemoryExactNNIndex
from docarray import BaseDoc, DocList
from docarray.typing import NdArray
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.retrievers import DocArrayRetriever


# define document schema
class MyDoc(BaseDoc):
    description: str
    description_embedding: NdArray[1536]


embeddings = OpenAIEmbeddings()
# create documents
descriptions = ["description 1", "description 2"]
desc_embeddings = embeddings.embed_documents(texts=descriptions)
docs = DocList[MyDoc](
    [
        MyDoc(description=desc, description_embedding=embedding)
        for desc, embedding in zip(descriptions, desc_embeddings)
    ]
)

# initialize document index with data
db = InMemoryExactNNIndex[MyDoc](docs)

# create a retriever
retriever = DocArrayRetriever(
    index=db,
    embeddings=embeddings,
    search_field="description_embedding",
    content_field="description",
)

# find the relevant document
doc = retriever.get_relevant_documents("action movies")
print(doc)
```

#### Who can review?

@dev2049

---------

Signed-off-by: jupyterjazz <saba.sturua@jina.ai>
2023-06-17 09:09:33 -07:00
Francisco Ingham
83eea230f3
changed height in the nb example (#6327)
changed height in the example to a more reasonable number (from 9 feet
to 6 feet)
2023-06-17 00:05:48 -07:00
Harrison Chase
af18413d97
Harrison/deeplake new features (#6263)
Co-authored-by: adilkhan <adilkhan.sarsen@nu.edu.kz>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-16 17:53:55 -07:00
ljeagle
ad324a39ae
Improve the performance of add_texts interface and upgrade the AwaDB from 0.3.2 to 0.3.3 (#6316)
1. Changed the implementation of add_texts interface for the AwaDB
vector store in order to improve the performance
2. Upgrade the AwaDB from 0.3.2 to 0.3.3

---------

Co-authored-by: vincent <awadb.vincent@gmail.com>
2023-06-16 16:50:01 -07:00
Davis Chase
87e502c6bc
Doc refactor (#6300)
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 11:52:56 -07:00