Commit Graph

242 Commits

Author SHA1 Message Date
Matt Rickard
de6a401a22
Add OpenLM LLM multi-provider (#4993)
OpenLM is a zero-dependency OpenAI-compatible LLM provider that can call
different inference endpoints directly via HTTP. It implements the
OpenAI Completion class so that it can be used as a drop-in replacement
for the OpenAI API. This changeset utilizes BaseOpenAI for minimal added
code.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-22 18:09:53 -07:00
Gergely Imreh
69de33e024
Add Mastodon toots loader (#5036)
# Add Mastodon toots loader.

Loader works either with public toots, or Mastodon app credentials. Toot
text and user info is loaded.

I've also added integration test for this new loader as it works with
public data, and a notebook with example output run now.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-22 16:43:07 -07:00
Donger
039f8f1abb
Add the usage of SSL certificates for Elasticsearch and user password authentication (#5058)
Enhance the code to support SSL authentication for Elasticsearch when
using the VectorStore module, as previous versions did not provide this
capability.
@dev2049

---------

Co-authored-by: caidong <zhucaidong1992@gmail.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-22 11:51:32 -07:00
Harrison Chase
10ba201d05
Harrison/neo4j (#5078)
Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-22 07:31:48 -07:00
Zander Chase
785502edb3
Add 'get_token_ids' method (#4784)
Let user inspect the token ids in addition to getting th enumber of tokens

---------

Co-authored-by: Zach Schillaci <40636930+zachschillaci27@users.noreply.github.com>
2023-05-22 13:17:26 +00:00
Matt Robinson
bf3f554357
feat: batch multiple files in a single Unstructured API request (#4525)
### Submit Multiple Files to the Unstructured API

Enables batching multiple files into a single Unstructured API requests.
Support for requests with multiple files was added to both
`UnstructuredAPIFileLoader` and `UnstructuredAPIFileIOLoader`. Note that
if you submit multiple files in "single" mode, the result will be
concatenated into a single document. We recommend using this feature in
"elements" mode.

### Testing

The following should load both documents, using two of the example docs
from the integration tests folder.

```python
    from langchain.document_loaders import UnstructuredAPIFileLoader

    file_paths = ["examples/layout-parser-paper.pdf",  "examples/whatsapp_chat.txt"]

    loader = UnstructuredAPIFileLoader(
        file_paths=file_paths,
        api_key="FAKE_API_KEY",
        strategy="fast",
        mode="elements",
    )
    docs = loader.load()
```
2023-05-21 20:48:20 -07:00
Davis Chase
080eb1b3fc
Fix graphql tool (#4984)
Fix construction and add unit test.
2023-05-19 15:27:50 -07:00
Eugene Yurtsev
0ff59569dc
Adds 'IN' metadata filter for pgvector for checking set presence (#4982)
# Adds "IN" metadata filter for pgvector to all checking for set
presence

PGVector currently supports metadata filters of the form:
```
{"filter": {"key": "value"}}
```
which will return documents where the "key" metadata field is equal to
"value".

This PR adds support for metadata filters of the form:
```
{"filter": {"key": { "IN" : ["list", "of", "values"]}}}
```

Other vector stores support this via an "$in" syntax. I chose to use
"IN" to match postgres' syntax, though happy to switch.
Tested locally with PGVector and ChatVectorDBChain.


@dev2049

---------

Co-authored-by: jade@spanninglabs.com <jade@spanninglabs.com>
2023-05-19 13:53:23 -07:00
Eugene Yurtsev
06e524416c
power bi api wrapper integration tests & bug fix (#4983)
# Powerbi API wrapper bug fix + integration tests

- Bug fix by removing `TYPE_CHECKING` in in utilities/powerbi.py
- Added integration test for power bi api in
utilities/test_powerbi_api.py
- Added integration test for power bi agent in
agent/test_powerbi_agent.py
- Edited .env.examples to help set up power bi related environment
variables
- Updated demo notebook with working code in
docs../examples/powerbi.ipynb - AzureOpenAI -> ChatOpenAI

Notes: 

Chat models (gpt3.5, gpt4) are much more capable than davinci at writing
DAX queries, so that is important to getting the agent to work properly.
Interestingly, gpt3.5-turbo needed the examples=DEFAULT_FEWSHOT_EXAMPLES
to write consistent DAX queries, so gpt4 seems necessary as the smart
llm.

Fixes #4325

## Before submitting

Azure-core and Azure-identity are necessary dependencies

check integration tests with the following:
`pytest tests/integration_tests/utilities/test_powerbi_api.py`
`pytest tests/integration_tests/agent/test_powerbi_agent.py`

You will need a power bi account with a dataset id + table name in order
to test. See .env.examples for details.

## Who can review?
@hwchase17
@vowelparrot

---------

Co-authored-by: aditya-pethe <adityapethe1@gmail.com>
2023-05-19 11:25:52 -04:00
Davis Chase
55baa0d153
Update redis integration tests (#4937) 2023-05-18 10:22:17 -07:00
Harrison Chase
c9a362e482
add alias for model (#4553)
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-18 09:12:23 -07:00
Harrison Chase
9e2227ba11
Harrison/serper api bug (#4902)
Co-authored-by: Jerry Luan <xmaswillyou@gmail.com>
2023-05-17 21:40:39 -07:00
Eugene Yurtsev
0dc304ca80
Add html parsers (#4874)
# Add bs4 html parser

* Some minor refactors
* Extract the bs4 html parsing code from the bs html loader
* Move some tests from integration tests to unit tests
2023-05-17 22:39:11 -04:00
yujiosaka
2f8eb95a91
Remove unnecessary comment (#4845)
# Remove unnecessary comment

Remove unnecessary comment accidentally included in #4800

## Before submitting

- no test
- no document

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
2023-05-17 11:53:03 -04:00
yujiosaka
6561efebb7
Accept uuids kwargs for weaviate (#4800)
# Accept uuids kwargs for weaviate

Fixes #4791
2023-05-16 15:26:46 -07:00
Magnus Friberg
d126276693
Specify which data to return from chromadb (#4393)
# Improve the Chroma get() method by adding the optional "include"
parameter.

The Chroma get() method excludes embeddings by default. You can
customize the response by specifying the "include" parameter to
selectively retrieve the desired data from the collection.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-16 14:43:09 -07:00
Raduan Al-Shedivat
00c6ec8a2d
fix(document_loaders/telegram): fix pandas calls + add tests (#4806)
# Fix Telegram API loader + add tests.
I was testing this integration and it was broken with next error:
```python
message_threads = loader._get_message_threads(df)
KeyError: False
```
Also, this particular loader didn't have any tests / related group in
poetry, so I added those as well.

@hwchase17 / @eyurtsev please take a look on this fix PR.

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-16 14:35:25 -07:00
了空
f7e3d97b19
Remove unnecessary spaces from document object’s page_content of BiliBiliLoader (#4619)
- Remove unnecessary spaces from document object’s page_content of
BiliBiliLoader
- Fix BiliBiliLoader document and test file
2023-05-16 13:13:57 -04:00
Harrison Chase
a7af32c274
Cassandra support for chat history (#4378) (#4764)
# Cassandra support for chat history

### Description

- Store chat messages in cassandra

### Dependency

- cassandra-driver - Python Module

## Before submitting

- Added Integration Test

## Who can review?

@hwchase17
@agola11

# Your PR Title (What it does)

<!--
Thank you for contributing to LangChain! Your PR will appear in our next
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.
-->

<!-- Remove if not applicable -->

Fixes # (issue)

## Before submitting

<!-- If you're adding a new integration, include an integration test and
an example notebook showing its use! -->

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:

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

        @hwchase17 - project lead

        Tracing / Callbacks
        - @agola11

        Async
        - @agola11

        DataLoaders
        - @eyurtsev

        Models
        - @hwchase17
        - @agola11

        Agents / Tools / Toolkits
        - @vowelparrot
        
        VectorStores / Retrievers / Memory
        - @dev2049
        
 -->

Co-authored-by: Jinto Jose <129657162+jj701@users.noreply.github.com>
2023-05-15 23:43:09 -07:00
Anirudh Suresh
03ac39368f
Fixing DeepLake Overwrite Flag (#4683)
# Fix DeepLake Overwrite Flag Issue

Fixes Issue #4682: essentially, setting overwrite to False in the
DeepLake constructor still triggers an overwrite, because the logic is
just checking for the presence of "overwrite" in kwargs. The fix is
simple--just add some checks to inspect if "overwrite" in kwargs AND
kwargs["overwrite"]==True.

Added a new test in
tests/integration_tests/vectorstores/test_deeplake.py to reflect the
desired behavior.


Co-authored-by: Anirudh Suresh <ani@Anirudhs-MBP.cable.rcn.com>
Co-authored-by: Anirudh Suresh <ani@Anirudhs-MacBook-Pro.local>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-15 17:39:16 -07:00
whuwxl
3f0357f94a
Add summarization task type for HuggingFace APIs (#4721)
# Add summarization task type for HuggingFace APIs

Add summarization task type for HuggingFace APIs.
This task type is described by [HuggingFace inference
API](https://huggingface.co/docs/api-inference/detailed_parameters#summarization-task)

My project utilizes LangChain to connect multiple LLMs, including
various HuggingFace models that support the summarization task.
Integrating this task type is highly convenient and beneficial.

Fixes #4720
2023-05-15 16:26:17 -07:00
Roma
cb802edf75
[Feature] Add GraphQL Query Tool (#4409)
# Add GraphQL Query Support

This PR introduces a GraphQL API Wrapper tool that allows LLM agents to
query GraphQL databases. The tool utilizes the httpx and gql Python
packages to interact with GraphQL APIs and provides a simple interface
for running queries with LLM agents.

@vowelparrot

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-15 14:06:12 -07:00
Lester Yang
cd3f9865f3
Feature: pdfplumber PDF loader with BaseBlobParser (#4552)
# Feature: pdfplumber PDF loader with BaseBlobParser

* Adds pdfplumber as a PDF loader
* Adds pdfplumber as a blob parser.
2023-05-15 09:47:02 -04:00
Harrison Chase
b6e3ac17c4
Harrison/sitemap local (#4704)
Co-authored-by: Lukas Bauer <lukas.bauer@mayflower.de>
2023-05-14 22:04:38 -07:00
Harrison Chase
12b4ee1fc7
Harrison/telegram chat loader (#4698)
Co-authored-by: Akinwande Komolafe <47945512+Sensei-akin@users.noreply.github.com>
Co-authored-by: Akinwande Komolafe <akhinoz@gmail.com>
2023-05-14 22:04:27 -07:00
Leonid Ganeline
e17d0319d5
Add arxiv retriever (#4538) 2023-05-11 22:48:38 -07:00
SimFG
7bcf238a1a
Optimize the initialization method of GPTCache (#4522)
Optimize the initialization method of GPTCache, so that users can use GPTCache more quickly.
2023-05-11 16:15:23 -07:00
kYLe
0d51a1f12b
Add LLMs support for Anyscale Service (#4350)
Add Anyscale service integration under LLM

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-11 00:39:59 -07:00
Evan Jones
f668251948
parameterized distance metrics; lint; format; tests (#4375)
# Parameterize Redis vectorstore index

Redis vectorstore allows for three different distance metrics: `L2`
(flat L2), `COSINE`, and `IP` (inner product). Currently, the
`Redis._create_index` method hard codes the distance metric to COSINE.

I've parameterized this as an argument in the `Redis.from_texts` method
-- pretty simple.

Fixes #4368 

## Before submitting

I've added an integration test showing indexes can be instantiated with
all three values in the `REDIS_DISTANCE_METRICS` literal. An example
notebook seemed overkill here. Normal API documentation would be more
appropriate, but no standards are in place for that yet.

## Who can review?

Not sure who's responsible for the vectorstore module... Maybe @eyurtsev
/ @hwchase17 / @agola11 ?
2023-05-11 00:20:01 -07:00
Davis Chase
9ec60ad832
Add azure cognitive search retriever (#4467)
All credit to @UmerHA, made a couple small changes

---------

Co-authored-by: UmerHA <40663591+UmerHA@users.noreply.github.com>
2023-05-10 15:27:27 -07:00
Davis Chase
46b100ea63
Add DocArray vector stores (#4483)
Thanks to @anna-charlotte and @jupyterjazz for the contribution! Made
few small changes to get it across the finish line

---------

Signed-off-by: anna-charlotte <charlotte.gerhaher@jina.ai>
Signed-off-by: jupyterjazz <saba.sturua@jina.ai>
Co-authored-by: anna-charlotte <charlotte.gerhaher@jina.ai>
Co-authored-by: jupyterjazz <saba.sturua@jina.ai>
Co-authored-by: Saba Sturua <45267439+jupyterjazz@users.noreply.github.com>
2023-05-10 15:22:16 -07:00
Harrison Chase
b2f920e891
add tracing v2 env var (#4465)
Co-authored-by: Ankush Gola <ankush.gola@gmail.com>
2023-05-10 11:08:29 -07:00
Matt Robinson
3637d6da6e
feat: add loader for open office odt files (#4405)
# ODF File Loader

Adds a data loader for handling Open Office ODT files. Requires
`unstructured>=0.6.3`.

### Testing

The following should work using the `fake.odt` example doc from the
[`unstructured` repo](https://github.com/Unstructured-IO/unstructured).

```python
from langchain.document_loaders import UnstructuredODTLoader

loader = UnstructuredODTLoader(file_path="fake.odt", mode="elements")
loader.load()

loader = UnstructuredODTLoader(file_path="fake.odt", mode="single")
loader.load()
```
2023-05-10 01:37:17 -07:00
Rukmani
2b14036126
Update WhatsAppChatLoader to include the character ~ in the sender name (#4420)
Fixes #4153

If the sender of a message in a group chat isn't in your contact list,
they will appear with a ~ prefix in the exported chat. This PR adds
support for parsing such lines.
2023-05-09 15:00:04 -07:00
Aivin V. Solatorio
6335cb5b3a
Add support for Qdrant nested filter (#4354)
# Add support for Qdrant nested filter

This extends the filter functionality for the Qdrant vectorstore. The
current filter implementation is limited to a single-level metadata
structure; however, Qdrant supports nested metadata filtering. This
extends the functionality for users to maximize the filter functionality
when using Qdrant as the vectorstore.

Reference: https://qdrant.tech/documentation/filtering/#nested-key

---------

Signed-off-by: Aivin V. Solatorio <avsolatorio@gmail.com>
2023-05-09 10:34:11 -07:00
Martin Holzhauer
872605a5c5
Add an option to extract more metadata from crawled websites (#4347)
This pr makes it possible to extract more metadata from websites for
later use.

my usecase:
parsing ld+json or microdata from sites and store it as structured data
in the metadata field
2023-05-09 10:18:33 -07:00
Leonid Ganeline
ce15ffae6a
added Wikipedia retriever (#4302)
- added `Wikipedia` retriever. It is effectively a wrapper for
`WikipediaAPIWrapper`. It wrapps load() into get_relevant_documents()
- sorted `__all__` in the `retrievers/__init__`
- added integration tests for the WikipediaRetriever
- added an example (as Jupyter notebook) for the WikipediaRetriever
2023-05-09 10:08:39 -07:00
Eugene Yurtsev
2ceb807da2
Add PDF parser implementations (#4356)
# Add PDF parser implementations

This PR separates the data loading from the parsing for a number of
existing PDF loaders.

Parser tests have been designed to help encourage developers to create a
consistent interface for parsing PDFs.

This interface can be made more consistent in the future by adding
information into the initializer on desired behavior with respect to splitting by
page etc.

This code is expected to be backwards compatible -- with the exception
of a bug fix with pymupdf parser which was returning `bytes` in the page
content rather than strings.

Also changing the lazy parser method of document loader to return an
Iterator rather than Iterable over documents.

## Before submitting

<!-- If you're adding a new integration, include an integration test and
an example notebook showing its use! -->

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:

@

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

        @hwchase17 - project lead

        Tracing / Callbacks
        - @agola11

        Async
        - @agola11

        DataLoader Abstractions
        - @eyurtsev

        LLM/Chat Wrappers
        - @hwchase17
        - @agola11

        Tools / Toolkits
        - @vowelparrot
 -->
2023-05-09 10:24:17 -04:00
Davis Chase
ba0057c077
Check OpenAI model kwargs (#4366)
Handle duplicate and incorrectly specified OpenAI params

Thanks @PawelFaron for the fix! Made small update

Closes #4331

---------

Co-authored-by: PawelFaron <42373772+PawelFaron@users.noreply.github.com>
Co-authored-by: Pawel Faron <ext-pawel.faron@vaisala.com>
2023-05-08 16:37:34 -07:00
Davis Chase
02ebb15c4a
Fix TextSplitter.from_tiktoken(#4361)
Thanks to @danb27 for the fix! Minor update

Fixes https://github.com/hwchase17/langchain/issues/4357

---------

Co-authored-by: Dan Bianchini <42096328+danb27@users.noreply.github.com>
2023-05-08 16:36:38 -07:00
Naveen Tatikonda
782df1db10
OpenSearch: Add Similarity Search with Score (#4089)
### Description
Add `similarity_search_with_score` method for OpenSearch to return
scores along with documents in the search results

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-05-08 16:35:21 -07:00
Jinto Jose
8a338412fa
mongodb support for chat history (#4266) 2023-05-08 08:34:05 -07:00
Leonid Ganeline
9544b30821
added Wikipedia document loader (#4141)
- Added the `Wikipedia` document loader. It is based on the existing
`unilities/WikipediaAPIWrapper`
- Added a respective ut-s and example notebook
- Sorted list of classes in __init__
2023-05-06 09:32:45 -07:00
Davis Chase
5ca13cc1f0
Dev2049/pypdfium2 (#4209)
thanks @jerrytigerxu for the addition!

---------

Co-authored-by: Jere Xu <jtxu2008@gmail.com>
Co-authored-by: jerrytigerxu <jere.tiger.xu@gmailc.om>
2023-05-05 17:55:31 -07:00
George
2324f19c85
Update qdrant interface (#3971)
Hello

1) Passing `embedding_function` as a callable seems to be outdated and
the common interface is to pass `Embeddings` instance

2) At the moment `Qdrant.add_texts` is designed to be used with
`embeddings.embed_query`, which is 1) slow 2) causes ambiguity due to 1.
It should be used with `embeddings.embed_documents`

This PR solves both problems and also provides some new tests
2023-05-05 16:46:40 -07:00
Mike Wang
c3044b1bf0
[test] Add integration_test for PandasAgent (#4056)
- confirm creation
- confirm functionality with a simple dimension check.

The test now is calling OpenAI API directly, but learning from
@vowelparrot that we’re caching the requests, so that it’s not that
expensive. I also found we’re calling OpenAI api in other integration
tests. Please lmk if there is any concern of real external API calls. I
can alternatively make a fake LLM for this test. Thanks
2023-05-05 14:49:02 -07:00
Aivin V. Solatorio
6567b73e1a
JSON loader (#4067)
This implements a loader of text passages in JSON format. The `jq`
syntax is used to define a schema for accessing the relevant contents
from the JSON file. This requires dependency on the `jq` package:
https://pypi.org/project/jq/.

---------

Signed-off-by: Aivin V. Solatorio <avsolatorio@gmail.com>
2023-05-05 14:48:13 -07:00
hp0404
2a3c5f8353
Update WhatsAppChatLoader regex to handle multiple date-time formats (#4186)
This PR updates the `message_line_regex` used by `WhatsAppChatLoader` to
support different date-time formats used in WhatsApp chat exports;
resolves #4153.

The new regex handles the following input formats:
```terminal
[05.05.23, 15:48:11] James: Hi here
[11/8/21, 9:41:32 AM] User name: Message 123
1/23/23, 3:19 AM - User 2: Bye!
1/23/23, 3:22_AM - User 1: And let me know if anything changes
```

Tests have been added to verify that the loader works correctly with all
formats.
2023-05-05 13:13:05 -07:00
Zander Chase
84cfa76e00
Update Cohere Reranker (#4180)
The forward ref annotations don't get updated if we only iimport with
type checking

---------

Co-authored-by: Abhinav Verma <abhinav_win12@yahoo.co.in>
2023-05-05 09:11:37 -07:00
Harrison Chase
d4cf1eb60a
Add firestore memory (#3792) (#3941)
If you have any other suggestions or feedback, please let me know.

---------

Co-authored-by: yakigac <10434946+yakigac@users.noreply.github.com>
2023-05-03 22:55:47 -07:00