Commit Graph

140 Commits

Author SHA1 Message Date
seamusp
16945c9922
docs: misc retrievers fixes (#9791)
Various miscellaneous fixes to most pages in the 'Retrievers' section of
the documentation:
- "VectorStore" and "vectorstore" changed to "vector store" for
consistency
- Various spelling, grammar, and formatting improvements for readability

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-09-03 20:26:49 -07:00
Pu Cao
05664a6f20
docs(text_splitter): update document of character splitter with tiktoken (#10001)
The current document has not mentioned that splits larger than chunk
size would happen. I update the related document and explain why it
happens and how to solve it.

related issue #1349 #3838 #2140
2023-09-03 14:45:45 -07:00
Bagatur
71c418725f
index rename delete_mode -> cleanup (#10103) 2023-09-01 11:12:10 -07:00
Harrison Chase
709a67d9bf
multivector notebook (#9740) 2023-08-25 07:07:27 -07:00
Harrison Chase
9963b32e59
Harrison/multi vector (#9700) 2023-08-24 06:42:42 -07:00
Eugene Yurtsev
b88dfcb42a
Add indexing support (#9614)
This PR introduces a persistence layer to help with indexing workflows
into
vectostores.

The indexing code helps users to:

1. Avoid writing duplicated content into the vectostore
2. Avoid over-writing content if it's unchanged

Importantly, this keeps on working even if the content being written is
derived
via a set of transformations from some source content (e.g., indexing
children
documents that were derived from parent documents by chunking.)

The two main components are:

1. Persistence layer that keeps track of which keys were updated and
when.
Keeping track of the timestamp of updates, allows to clean up old
content
   safely, and with minimal complexity.
2. HashedDocument which is used to hash the contents (including
metadata) of
   the documents. We rely on the hashes for identifying duplicates.


The indexing code works with **ANY** document loader. To add
transformations
to the documents, users for now can add a custom document loader
that composes an existing loader together with document transformers.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-23 21:41:38 -04:00
Bagatur
d8e2dd4c89 mv 2023-08-23 11:30:44 -07:00
Jacob Lee
0fea987dd2
Add missing param to parent document retriever notebook (#9569) 2023-08-21 15:02:12 -07:00
RajneeshSinghShorthillsAI
129d056085
fixed spelling mistake and added missing bracket in parent_document_r… (#9380)
…etriever.ipynb


Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2023-08-18 21:36:56 -07:00
Bagatur
bfbb97b74c
Bagatur/deeplake docs fixes (#9275)
Co-authored-by: adilkhan <adilkhan.sarsen@nu.edu.kz>
2023-08-15 15:56:36 -07:00
Joseph McElroy
5e9687a196
Elasticsearch self-query retriever (#9248)
Now with ElasticsearchStore VectorStore merged, i've added support for
the self-query retriever.

I've added a notebook also to demonstrate capability. I've also added
unit tests.

**Credit**
@elastic and @phoey1 on twitter.
2023-08-15 10:53:43 -04:00
Eugene Yurtsev
a5a4c53280
RedisStore: Update init and Documentation updates (#9044)
* Update Redis Store to support init from parameters
* Update notebook to show how to use redis store, and some fixes in
documentation
2023-08-10 15:30:29 -04:00
Eugene Yurtsev
5e05ba2140
Add embeddings cache (#8976)
This PR adds the ability to temporarily cache or persistently store
embeddings. 

A notebook has been included showing how to set up the cache and how to
use it with a vectorstore.
2023-08-10 11:15:30 -04:00
Harrison Chase
7de6a1b78e
parent document retriever (#8941) 2023-08-08 22:39:08 -07:00
Ikko Eltociear Ashimine
6b93670410
Fix typo in long_context_reorder.ipynb (#8811)
begining -> beginning

<!-- 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
 -->
2023-08-06 15:31:38 -07:00
Bagatur
2311d57df4
mv dropbox (#8438) 2023-07-28 16:07:56 -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
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
William FH
0a16b3d84b
Update Integrations links (#8206) 2023-07-24 21:20:32 -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
Adilkhan Sarsen
3e7d2a1b64
SelfQuery support for deeplake (#7888)
Added support SelfQuery for Deeplake
2023-07-24 14:22:33 -07:00
Bagatur
c8c8635dc9
mv module integrations docs (#8101) 2023-07-23 23:23:16 -07:00
Lance Martin
5a084e1b20
Async HTML loader and HTML2Text transformer (#8036)
New HTML loader that asynchronously loader a list of urls. 
 
New transformer using [HTML2Text](https://github.com/Alir3z4/html2text/)
for HTML to clean, easy-to-read plain ASCII text (valid Markdown).
2023-07-20 22:30:59 -07:00
Jacob Lee
56c6ab1715
Fix bad docs sidebar header (#7966)
Quick fix for:

<img width="283" alt="Screenshot 2023-07-19 at 2 49 44 PM"
src="https://github.com/hwchase17/langchain/assets/6952323/91e4868c-b75e-413d-9f8f-d34762abf164">

CC @baskaryan
2023-07-20 19:06:57 -07:00
Kacper Łukawski
ed6a5532ac
Implement async support in Qdrant local mode (#8001)
I've extended the support of async API to local Qdrant mode. It is faked
but allows prototyping without spinning a container. The tests are
improved to test the in-memory case as well.

@baskaryan @rlancemartin @eyurtsev @agola11
2023-07-20 19:04:33 -07:00
Dwai Banerjee
d8c40253c3
Adding endpoint_url to embeddings/bedrock.py and updated docs (#7927)
BedrockEmbeddings does not have endpoint_url so that switching to custom
endpoint is not possible. I have access to Bedrock custom endpoint and
cannot use BedrockEmbeddings

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-20 07:25:59 -07:00
Jeff Huber
5694e7b8cf
Update chroma notebook (#7978)
Fix up the Chroma notebook
- remove `.persist()` -- this is no longer in Chroma as of `0.4.0`
- update output to match `0.4.0`
- other cleanup work
2023-07-20 06:25:31 -07:00
Julien Salinas
3adab5e5be
Integrate NLP Cloud embeddings endpoint (#7931)
Add embeddings for [NLPCloud](https://docs.nlpcloud.com/#embeddings).

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Lance Martin <lance@langchain.dev>
2023-07-19 15:27:34 -07:00
Brendan Collins
9aef79c2e3
Add Geopandas.GeoDataFrame Document Loader (#3817)
Work in Progress.
WIP
Not ready...

Adds Document Loader support for
[Geopandas.GeoDataFrames](https://geopandas.org/)

Example:
- [x] stub out `GeoDataFrameLoader` class
- [x] stub out integration tests
- [ ] Experiment with different geometry text representations
- [ ] Verify CRS is successfully added in metadata
- [ ] Test effectiveness of searches on geometries
- [ ] Test with different geometry types (point, line, polygon with
multi-variants).
- [ ] Add documentation

---------

Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Lance Martin <122662504+rlancemartin@users.noreply.github.com>
2023-07-19 12:14:41 -07:00
Jarek Kazmierczak
f2ef3ff54a
Google Cloud Enterprise Search retriever (#7857)
Added a retriever that encapsulated Google Cloud Enterprise Search.


---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-18 18:24:08 -07:00
Jeff Huber
2139d0197e
upgrade chroma to 0.4.0 (#7749)
** This should land Monday the 17th ** 

Chroma is upgrading from `0.3.29` to `0.4.0`. `0.4.0` is easier to
build, more durable, faster, smaller, and more extensible. This comes
with a few changes:

1. A simplified and improved client setup. Instead of having to remember
weird settings, users can just do `EphemeralClient`, `PersistentClient`
or `HttpClient` (the underlying direct `Client` implementation is also
still accessible)

2. We migrated data stores away from `duckdb` and `clickhouse`. This
changes the api for the `PersistentClient` that used to reference
`chroma_db_impl="duckdb+parquet"`. Now we simply set
`is_persistent=true`. `is_persistent` is set for you to `true` if you
use `PersistentClient`.

3. Because we migrated away from `duckdb` and `clickhouse` - this also
means that users need to migrate their data into the new layout and
schema. Chroma is committed to providing extension notification and
tooling around any schema and data migrations (for example - this PR!).

After upgrading to `0.4.0` - if users try to access their data that was
stored in the previous regime, the system will throw an `Exception` and
instruct them how to use the migration assistant to migrate their data.
The migration assitant is a pip installable CLI: `pip install
chroma_migrate`. And is runnable by calling `chroma_migrate`

-- TODO ADD here is a short video demonstrating how it works. 

Please reference the readme at
[chroma-core/chroma-migrate](https://github.com/chroma-core/chroma-migrate)
to see a full write-up of our philosophy on migrations as well as more
details about this particular migration.

Please direct any users facing issues upgrading to our Discord channel
called
[#get-help](https://discord.com/channels/1073293645303795742/1129200523111841883).
We have also created a [email
listserv](https://airtable.com/shrHaErIs1j9F97BE) to notify developers
directly in the future about breaking changes.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-18 17:20:54 -07:00
maciej-skorupka
c6d1d6d7fc
feat: moving azure OpenAI API version to the latest 2023-05-15 (#7764)
Moving to the latest non-preview Azure OpenAI API version=2023-05-15.
The previous 2023-03-15-preview doesn't have support, SLA etc. For
instance, OpenAI SDK has moved to this version
https://github.com/openai/openai-python/releases/tag/v0.27.7

@baskaryan
2023-07-18 09:50:15 -07:00
satorioh
259a409998
docs(zilliz): connection_args add token description for serverless cl… (#7810)
Description:

Currently, Zilliz only support dedicated clusters using a pair of
username and password for connection. Regarding serverless clusters,
they can connect to them by using API keys( [ see official note
detail](https://docs.zilliz.com/docs/manage-cluster-credentials)), so I
add API key(token) description in Zilliz docs to make it more obvious
and convenient for this group of users to better utilize Zilliz. No
changes done to code.

---------

Co-authored-by: Robin.Wang <3Jg$94sbQ@q1>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-18 09:31:39 -07:00
Bill Zhang
dda11d2a05
WeaviateHybridSearchRetriever option to enable scores. (#7861)
Description: This PR adds the option to retrieve scores and explanations
in the WeaviateHybridSearchRetriever. This feature improves the
usability of the retriever by allowing users to understand the scoring
logic behind the search results and further refine their search queries.

Issue: This PR is a solution to the issue #7855 
Dependencies: This PR does not introduce any new dependencies.

Tag maintainer: @rlancemartin, @eyurtsev

I have included a unit test for the added feature, ensuring that it
retrieves scores and explanations correctly. I have also included an
example notebook demonstrating its use.
2023-07-18 07:57:17 -07:00
German Martin
f1eaa9b626
Lost in the middle: We have been ordering documents the WRONG way. (for long context) (#7520)
Motivation, it seems that when dealing with a long context and "big"
number of relevant documents we must avoid using out of the box score
ordering from vector stores.
See: https://arxiv.org/pdf/2306.01150.pdf

So, I added an additional parameter that allows you to reorder the
retrieved documents so we can work around this performance degradation.
The relevance respect the original search score but accommodates the
lest relevant document in the middle of the context.
Extract from the paper (one image speaks 1000 tokens):

![image](https://github.com/hwchase17/langchain/assets/1821407/fafe4843-6e18-4fa6-9416-50cc1d32e811)
This seems to be common to all diff arquitectures. SO I think we need a
good generic way to implement this reordering and run some test in our
already running retrievers.
It could be that my approach is not the best one from the architecture
point of view, happy to have a discussion about that.
For me this was the best place to introduce the change and start
retesting diff implementations.

@rlancemartin, @eyurtsev

---------

Co-authored-by: Lance Martin <lance@langchain.dev>
2023-07-18 07:45:15 -07:00
Jasper
5b4d53e8ef
Add text_content kwarg to BrowserlessLoader (#7856)
Added keyword argument to toggle between getting the text content of a
site versus its HTML when using the `BrowserlessLoader`
2023-07-17 17:02:19 -07:00
Matt Robinson
3c489be773
feat: optional post-processing for Unstructured loaders (#7850)
### Summary

Adds a post-processing method for Unstructured loaders that allows users
to optionally modify or clean extracted elements.

### Testing

```python
from langchain.document_loaders import UnstructuredFileLoader
from unstructured.cleaners.core import clean_extra_whitespace

loader = UnstructuredFileLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="elements",
    post_processors=[clean_extra_whitespace],
)

docs = loader.load()
docs[:5]
```


### Reviewrs
  - @rlancemartin
  - @eyurtsev
  - @hwchase17
2023-07-17 12:13:05 -07:00
Bagatur
2a315dbee9
fix nb (#7843) 2023-07-17 09:39:11 -07:00
Bagatur
98c48f303a
fix (#7838) 2023-07-17 07:53:11 -07:00
Dayuan Jiang
ee40d37098
add bm25 module (#7779)
- Description: Add a BM25 Retriever that do not need Elastic search
- Dependencies: rank_bm25(if it is not installed it will be install by
using pip, just like TFIDFRetriever do)
  - Tag maintainer: @rlancemartin, @eyurtsev
  - Twitter handle: DayuanJian21687

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-17 07:30:17 -07:00
sseide
25e3d3f283
Support Redis Sentinel database connections (#5196)
# Support Redis Sentinel database connections

This PR adds the support to connect not only to Redis standalone servers
but High Availability Replication sets too
(https://redis.io/docs/management/sentinel/)
Redis Replica Sets have on Master allowing to write data and 2+ replicas
with read-only access to the data. The additional Redis Sentinel
instances monitor all server and reconfigure the RW-Master on the fly if
it comes unavailable.

Therefore all connections must be made through the Sentinels the query
the current master for a read-write connection. This PR adds basic
support to also allow a redis connection url specifying a Sentinel as
Redis connection.

Redis documentation and Jupyter notebook with Redis examples are updated
to mention how to connect to a redis Replica Set with Sentinels

        - 

Remark - i did not found test cases for Redis server connections to add
new cases here. Therefor i tests the new utility class locally with
different kind of setups to make sure different connection urls are
working as expected. But no test case here as part of this PR.
2023-07-17 07:18:51 -07:00
Lance Martin
b015647e31
Add GPT4All embeddings (#7743)
Support for [GPT4All
embeddings](https://docs.gpt4all.io/gpt4all_python_embedding.html)

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-15 10:04:29 -04:00
Lorenzo
77e6bbe6f0
fix typo in deeplake.ipynb (#7718)
- Fixing typos in deeplake documentation
- @baskaryan
2023-07-14 13:38:31 -04:00
Aarav Borthakur
210296a71f
Integrate Rockset as a document loader (#7681)
<!-- 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
 -->

Integrate [Rockset](https://rockset.com/docs/) as a document loader.

Issue: None
Dependencies: Nothing new (rockset's dependency was already added
[here](https://github.com/hwchase17/langchain/pull/6216))
Tag maintainer: @rlancemartin

I have added a test for the integration and an example notebook showing
its use. I ran `make lint` and everything looks good.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-14 07:58:13 -07:00
Daniel
6d88b23ef7
Update pgembedding.ipynb (#7699)
Update the extension name. It changed from pg_hnsw to pg_embedding.

Thank you. I missed this in my previous commit.
2023-07-14 08:39:01 -04:00
Lance Martin
6325a3517c
Make recursive loader yield while crawling (#7568)
Support actual lazy_load since it can take a while to crawl larger
directories.
2023-07-13 21:55:20 -07:00
UmerHA
82f3e32d8d
[Small upgrade] Allow document limit in AzureCognitiveSearchRetriever (#7690)
Multiple people have asked in #5081 for a way to limit the documents
returned from an AzureCognitiveSearchRetriever. This PR adds the `top_n`
parameter to allow that.


Twitter handle:
 [@UmerHAdil](twitter.com/umerHAdil)
2023-07-13 23:04:40 -04:00
Daniel
854f3fe9b1
Update pgembedding.ipynb (#7682)
Correct links to the pg_embedding repository and the Neon documentation.
2023-07-13 19:54:07 -04:00
Jasper
fbc97a77ed
add browserless loader (#7562)
# Browserless

Added support for Browserless' `/content` endpoint as a document loader.

### About Browserless

Browserless is a cloud service that provides access to headless Chrome
browsers via a REST API. It allows developers to automate Chromium in a
serverless fashion without having to configure and maintain their own
Chrome infrastructure.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Lance Martin <lance@langchain.dev>
2023-07-13 13:18:28 -07:00
Bagatur
7f8ff2a317
add tagger nb (#7637) 2023-07-13 01:48:23 -04:00