# 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 ?
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>
# 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()
```
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.
# 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>
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
- 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
# 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
-->
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>
### 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>
- 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__
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
- 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
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>
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.
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>
* implemented arun, results, and aresults. Reuses aiosession if
available.
* helper tools GoogleSerperRun and GoogleSerperResults
* support for Google Images, Places and News (examples given) and
filtering based on time (e.g. past hour)
* updated docs
This PR includes two main changes:
- Refactor the `TelegramChatLoader` and `FacebookChatLoader` classes by
removing the dependency on pandas and simplifying the message filtering
process.
- Add test cases for the `TelegramChatLoader` and `FacebookChatLoader`
classes. This test ensures that the class correctly loads and processes
the example chat data, providing better test coverage for this
functionality.
The Blockchain Document Loader's default behavior is to return 100
tokens at a time which is the Alchemy API limit. The Document Loader
exposes a startToken that can be used for pagination against the API.
This enhancement includes an optional get_all_tokens param (default:
False) which will:
- Iterate over the Alchemy API until it receives all the tokens, and
return the tokens in a single call to the loader.
- Manage all/most tokenId formats (this can be int, hex16 with zero or
all the leading zeros). There aren't constraints as to how smart
contracts can represent this value, but these three are most common.
Note that a contract with 10,000 tokens will issue 100 calls to the
Alchemy API, and could take about a minute, which is why this param will
default to False. But I've been using the doc loader with these
utilities on the side, so figured it might make sense to build them in
for others to use.
Seems the pyllamacpp package is no longer the supported bindings from
gpt4all. Tested that this works locally.
Given that the older models weren't very performant, I think it's better
to migrate now without trying to include a lot of try / except blocks
---------
Co-authored-by: Nissan Pow <npow@users.noreply.github.com>
Co-authored-by: Nissan Pow <pownissa@amazon.com>
- ActionAgent has a property called, `allowed_tools`, which is declared
as `List`. It stores all provided tools which is available to use during
agent action.
- This collection shouldn’t allow duplicates. The original datatype List
doesn’t make sense. Each tool should be unique. Even when there are
variants (assuming in the future), it would be named differently in
load_tools.
Test:
- confirm the functionality in an example by initializing an agent with
a list of 2 tools and confirm everything works.
```python3
def test_agent_chain_chat_bot():
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.chat_models import ChatOpenAI
from langchain.llms import OpenAI
from langchain.utilities.duckduckgo_search import DuckDuckGoSearchAPIWrapper
chat = ChatOpenAI(temperature=0)
llm = OpenAI(temperature=0)
tools = load_tools(["ddg-search", "llm-math"], llm=llm)
agent = initialize_agent(tools, chat, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent.run("Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?")
test_agent_chain_chat_bot()
```
Result:
<img width="863" alt="Screenshot 2023-05-01 at 7 58 11 PM"
src="https://user-images.githubusercontent.com/62768671/235572157-0937594c-ddfb-4760-acb2-aea4cacacd89.png">
Modified Modern Treasury and Strip slightly so credentials don't have to
be passed in explicitly. Thanks @mattgmarcus for adding Modern Treasury!
---------
Co-authored-by: Matt Marcus <matt.g.marcus@gmail.com>
- Add langchain.llms.GooglePalm for text completion,
- Add langchain.chat_models.ChatGooglePalm for chat completion,
- Add langchain.embeddings.GooglePalmEmbeddings for sentence embeddings,
- Add example field to HumanMessage and AIMessage so that users can feed
in examples into the PaLM Chat API,
- Add system and unit tests.
Note async completion for the Text API is not yet supported and will be
included in a future PR.
Happy for feedback on any aspect of this PR, especially our choice of
adding an example field to Human and AI Message objects to enable
passing example messages to the API.
This PR includes some minor alignment updates, including:
- metadata object extended to support contractAddress, blockchainType,
and tokenId
- notebook doc better aligned to standard langchain format
- startToken changed from int to str to support multiple hex value types
on the Alchemy API
The updated metadata will look like the below. It's possible for a
single contractAddress to exist across multiple blockchains (e.g.
Ethereum, Polygon, etc.) so it's important to include the
blockchainType.
```
metadata = {"source": self.contract_address,
"blockchain": self.blockchainType,
"tokenId": tokenId}
```
This PR
* Adds `clear` method for `BaseCache` and implements it for various
caches
* Adds the default `init_func=None` and fixes gptcache integtest
* Since right now integtest is not running in CI, I've verified the
changes by running `docs/modules/models/llms/examples/llm_caching.ipynb`
(until proper e2e integtest is done in CI)
## Background
fixes#2695
## Changes
The `add_text` method uses the internal embedding function if one was
passes to the `Weaviate` constructor.
NOTE: the latest merge on the `Weaviate` class made the specification of
a `weaviate_api_key` mandatory which might not be desirable for all
users and connection methods (for example weaviate also support Embedded
Weaviate which I am happy to add support to here if people think it's
desirable). I wrapped the fetching of the api key into a try catch in
order to allow the `weaviate_api_key` to be unspecified. Do let me know
if this is unsatisfactory.
## Test Plan
added test for `add_texts` method.
It makes sense to use `arxiv` as another source of the documents for
downloading.
- Added the `arxiv` document_loader, based on the
`utilities/arxiv.py:ArxivAPIWrapper`
- added tests
- added an example notebook
- sorted `__all__` in `__init__.py` (otherwise it is hard to find a
class in the very long list)
Tools for Bing, DDG and Google weren't consistent even though the
underlying implementations were.
All three services now have the same tools and implementations to easily
switch and experiment when building chains.
Test for #3434 @eavanvalkenburg
Initially, I was unaware and had submitted a pull request #3450 for the
same purpose, but I have now repurposed the one I used for that. And it
worked.
### Background
Continuing to implement all the interface methods defined by the
`VectorStore` class. This PR pertains to implementation of the
`max_marginal_relevance_search_by_vector` method.
### Changes
- a `max_marginal_relevance_search_by_vector` method implementation has
been added in `weaviate.py`
- tests have been added to the the new method
- vcr cassettes have been added for the weaviate tests
### Test Plan
Added tests for the `max_marginal_relevance_search_by_vector`
implementation
### Change Safety
- [x] I have added tests to cover my changes
Improvements
* set default num_workers for ingestion to 0
* upgraded notebooks for avoiding dataset creation ambiguity
* added `force_delete_dataset_by_path`
* bumped deeplake to 3.3.0
* creds arg passing to deeplake object that would allow custom S3
Notes
* please double check if poetry is not messed up (thanks!)
Asks
* Would be great to create a shared slack channel for quick questions
---------
Co-authored-by: Davit Buniatyan <d@activeloop.ai>
This PR addresses several improvements:
- Previously it was not possible to load spaces of more than 100 pages.
The `limit` was being used both as an overall page limit *and* as a per
request pagination limit. This, in combination with the fact that
atlassian seem to use a server-side hard limit of 100 when page content
is expanded, meant it wasn't possible to download >100 pages. Now
`limit` is used *only* as a per-request pagination limit and `max_pages`
is introduced as the way to limit the total number of pages returned by
the paginator.
- Document metadata now includes `source` (the source url), making it
compatible with `RetrievalQAWithSourcesChain`.
- It is now possible to include inline and footer comments.
- It is now possible to pass `verify_ssl=False` and other parameters to
the confluence object for use cases that require it.
Hi there！
I'm excited to open this PR to add support for using a fully Postgres
syntax compatible database 'AnalyticDB' as a vector.
As AnalyticDB has been proved can be used with AutoGPT,
ChatGPT-Retrieve-Plugin, and LLama-Index, I think it is also good for
you.
AnalyticDB is a distributed Alibaba Cloud-Native vector database. It
works better when data comes to large scale. The PR includes:
- [x] A new memory: AnalyticDBVector
- [x] A suite of integration tests verifies the AnalyticDB integration
I have read your [contributing
guidelines](72b7d76d79/.github/CONTRIBUTING.md).
And I have passed the tests below
- [x] make format
- [x] make lint
- [x] make coverage
- [x] make test
### Description
Add Support for Lucene Filter. When you specify a Lucene filter for a
k-NN search, the Lucene algorithm decides whether to perform an exact
k-NN search with pre-filtering or an approximate search with modified
post-filtering. This filter is supported only for approximate search
with the indexes that are created using `lucene` engine.
OpenSearch Documentation -
https://opensearch.org/docs/latest/search-plugins/knn/filter-search-knn/#lucene-k-nn-filter-implementation
Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
### Background
Continuing to implement all the interface methods defined by the
`VectorStore` class. This PR pertains to implementation of the
`max_marginal_relevance_search` method.
### Changes
- a `max_marginal_relevance_search` method implementation has been added
in `weaviate.py`
- tests have been added to the the new method
- vcr cassettes have been added for the weaviate tests
### Test Plan
Added tests for the `max_marginal_relevance_search` implementation
### Change Safety
- [x] I have added tests to cover my changes
Add a method that exposes a similarity search with corresponding
normalized similarity scores. Implement only for FAISS now.
### Motivation:
Some memory definitions combine `relevance` with other scores, like
recency , importance, etc.
While many (but not all) of the `VectorStore`'s expose a
`similarity_search_with_score` method, they don't all interpret the
units of that score (depends on the distance metric and whether or not
the the embeddings are normalized).
This PR proposes a `similarity_search_with_normalized_similarities`
method that lets consumers of the vector store not have to worry about
the metric and embedding scale.
*Most providers default to euclidean distance, with Pinecone being one
exception (defaults to cosine _similarity_).*
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Minor cosmetic changes
- Activeloop environment cred authentication in notebooks with
`getpass.getpass` (instead of CLI which not always works)
- much faster tests with Deep Lake pytest mode on
- Deep Lake kwargs pass
Notes
- I put pytest environment creds inside `vectorstores/conftest.py`, but
feel free to suggest a better location. For context, if I put in
`test_deeplake.py`, `ruff` doesn't let me to set them before import
deeplake
---------
Co-authored-by: Davit Buniatyan <d@activeloop.ai>
Note to self: Always run integration tests, even on "that last minute
change you thought would be safe" :)
---------
Co-authored-by: Mike Lambert <mike.lambert@anthropic.com>
* Adds an Anthropic ChatModel
* Factors out common code in our LLMModel and ChatModel
* Supports streaming llm-tokens to the callbacks on a delta basis (until
a future V2 API does that for us)
* Some fixes
Fixes linting issue from #2835
Adds a loader for Slack Exports which can be a very valuable source of
knowledge to use for internal QA bots and other use cases.
```py
# Export data from your Slack Workspace first.
from langchain.document_loaders import SLackDirectoryLoader
SLACK_WORKSPACE_URL = "https://awesome.slack.com"
loader = ("Slack_Exports", SLACK_WORKSPACE_URL)
docs = loader.load()
```
Currently, the function still fails if `continue_on_failure` is set to
True, because `elements` is not set.
---------
Co-authored-by: leecjohnny <johnny-lee1255@users.noreply.github.com>
Add more missed imports for integration tests. Bump `pytest` to the
current latest version.
Fix `tests/integration_tests/vectorstores/test_elasticsearch.py` to
update its cassette(easy fix).
Related PR: https://github.com/hwchase17/langchain/pull/2560
I've added a bilibili loader, bilibili is a very active video site in
China and I think we need this loader.
Example:
```python
from langchain.document_loaders.bilibili import BiliBiliLoader
loader = BiliBiliLoader(
["https://www.bilibili.com/video/BV1xt411o7Xu/",
"https://www.bilibili.com/video/av330407025/"]
)
docs = loader.load()
```
Co-authored-by: 了空 <568250549@qq.com>
**Description**
Add custom vector field name and text field name while indexing and
querying for OpenSearch
**Issues**
https://github.com/hwchase17/langchain/issues/2500
Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
Adds a new pdf loader using the existing dependency on PDFMiner.
The new loader can be helpful for chunking texts semantically into
sections as the output html content can be parsed via `BeautifulSoup` to
get more structured and rich information about font size, page numbers,
pdf headers/footers, etc. which may not be available otherwise with
other pdf loaders
Using `pytest-vcr` in integration tests has several benefits. Firstly,
it removes the need to mock external services, as VCR records and
replays HTTP interactions on the fly. Secondly, it simplifies the
integration test setup by eliminating the need to set up and tear down
external services in some cases. Finally, it allows for more reliable
and deterministic integration tests by ensuring that HTTP interactions
are always replayed with the same response.
Overall, `pytest-vcr` is a valuable tool for simplifying integration
test setup and improving their reliability
This commit adds the `pytest-vcr` package as a dependency for
integration tests in the `pyproject.toml` file. It also introduces two
new fixtures in `tests/integration_tests/conftest.py` files for managing
cassette directories and VCR configurations.
In addition, the
`tests/integration_tests/vectorstores/test_elasticsearch.py` file has
been updated to use the `@pytest.mark.vcr` decorator for recording and
replaying HTTP interactions.
Finally, this commit removes the `documents` fixture from the
`test_elasticsearch.py` file and replaces it with a new fixture defined
in `tests/integration_tests/vectorstores/conftest.py` that yields a list
of documents to use in any other tests.
This also includes my second attempt to fix issue :
https://github.com/hwchase17/langchain/issues/2386
Maybe related https://github.com/hwchase17/langchain/issues/2484
### Features include
- Metadata based embedding search
- Choice of distance metric function (`L2` for Euclidean, `L1` for
Nuclear, `max` L-infinity distance, `cos` for cosine similarity, 'dot'
for dot product. Defaults to `L2`
- Returning scores
- Max Marginal Relevance Search
- Deleting samples from the dataset
### Notes
- Added numerous tests, let me know if you would like to shorten them or
make smarter
---------
Co-authored-by: Davit Buniatyan <d@activeloop.ai>
- Create a new docker-compose file to start an Elasticsearch instance
for integration tests.
- Add new tests to `test_elasticsearch.py` to verify Elasticsearch
functionality.
- Include an optional group `test_integration` in the `pyproject.toml`
file. This group should contain dependencies for integration tests and
can be installed using the command `poetry install --with
test_integration`. Any new dependencies should be added by running
`poetry add some_new_deps --group "test_integration" `
Note:
New tests running in live mode, which involve end-to-end testing of the
OpenAI API. In the future, adding `pytest-vcr` to record and replay all
API requests would be a nice feature for testing process.More info:
https://pytest-vcr.readthedocs.io/en/latest/
Fixes https://github.com/hwchase17/langchain/issues/2386
This PR updates Qdrant to 1.1.1 and introduces local mode, so there is
no need to spin up the Qdrant server. By that occasion, the Qdrant
example notebooks also got updated, covering more cases and answering
some commonly asked questions. All the Qdrant's integration tests were
switched to local mode, so no Docker container is required to launch
them.
## Description
Thanks for the quick maintenance for great repository!!
I modified wikipedia api wrapper
## Details
- Add output for missing search results
- Add tests
Solves #2247. Noted that the only test I added checks for the
BeautifulSoup behaviour change. Happy to add a test for
`DirectoryLoader` if deemed necessary.
@3coins + @zoltan-fedor.... heres the pr + some minor changes i made.
thoguhts? can try to get it into tmrws release
---------
Co-authored-by: Zoltan Fedor <zoltan.0.fedor@gmail.com>
Co-authored-by: Piyush Jain <piyushjain@duck.com>
Technically a duplicate fix to #1619 but with unit tests and a small
documentation update
- Propagate `filter` arg in Chroma `similarity_search` to delegated call
to `similarity_search_with_score`
- Add `filter` arg to `similarity_search_by_vector`
- Clarify doc strings on FakeEmbeddings
The `CollectionStore` for `PGVector` has a `cmetadata` field but it's
never used. This PR add the ability to save metadata information to the
collection.
Fix#1756
Use the `namespace` argument of `Pinecone.from_exisiting_index` to set
the default value of `namespace` for other methods. Leads to more
expected behavior and easier integration in chains.
For the test, I've added a line to delete and rebuild the
`langchain-demo` index at the beginning of the test. I'm not 100% sure
if it's a good idea but it makes the test reproducible.
Given that different models have very different latencies and pricings,
it's benefitial to pass the information about the model that generated
the response. Such information allows implementing custom callback
managers and track usage and price per model.
Addresses https://github.com/hwchase17/langchain/issues/1557.
This `BSHTMLLoader` document_loader loads an HTML document, extracts
text and adds the page title to the returned Document's metadata. The
loader uses the already installed bs4 package to extract both text
content and the page title.
Included in this PR is an example HTML file and an integration test that
tests against this file.
---------
Co-authored-by: Daniel Chalef <daniel.chalef@private.org>
This PR implements a basic metadata filtering mechanism similar to the
ones in Chroma and Pinecone. It still cannot express complex conditions,
as there are no operators, but some users requested to have that feature
available.
# Description
Add `RediSearch` vectorstore for LangChain
RediSearch: [RediSearch quick
start](https://redis.io/docs/stack/search/quick_start/)
# How to use
```
from langchain.vectorstores.redisearch import RediSearch
rds = RediSearch.from_documents(docs, embeddings,redisearch_url="redis://localhost:6379")
```
`OnlinePDFLoader` and `PagedPDFSplitter` lived separate from the rest of
the pdf loaders.
Because they're all similar, I propose moving all to `pdy.py` and the
same docs/examples page.
Additionally, `PagedPDFSplitter` naming doesn't match the pattern the
rest of the loaders follow, so I renamed to `PyPDFLoader` and had it
inherit from `BasePDFLoader` so it can now load from remote file
sources.
for https://github.com/hwchase17/langchain/issues/1582
I simply added the `return_intermediate_steps` and changed the
`output_keys` function.
I added 2 simple tests, 1 for SQLDatabaseSequentialChain without the
intermediate steps and 1 with
Co-authored-by: brad-nemetski <115185478+brad-nemetski@users.noreply.github.com>
Different PDF libraries have different strengths and weaknesses. PyMuPDF
does a good job at extracting the most amount of content from the doc,
regardless of the source quality, extremely fast (especially compared to
Unstructured).
https://pymupdf.readthedocs.io/en/latest/index.html
This PR:
- Increases `qdrant-client` version to 1.0.4
- Introduces custom content and metadata keys (as requested in #1087)
- Moves all the `QdrantClient` parameters into the method parameters to
simplify code completion
iFixit is a wikipedia-like site that has a huge amount of open content
on how to fix things, questions/answers for common troubleshooting and
"things" related content that is more technical in nature. All content
is licensed under CC-BY-SA-NC 3.0
Adding docs from iFixit as context for user questions like "I dropped my
phone in water, what do I do?" or "My macbook pro is making a whining
noise, what's wrong with it?" can yield significantly better responses
than context free response from LLMs.
### Description
This PR adds a wrapper which adds support for the OpenSearch vector
database. Using opensearch-py client we are ingesting the embeddings of
given text into opensearch cluster using Bulk API. We can perform the
`similarity_search` on the index using the 3 popular searching methods
of OpenSearch k-NN plugin:
- `Approximate k-NN Search` use approximate nearest neighbor (ANN)
algorithms from the [nmslib](https://github.com/nmslib/nmslib),
[faiss](https://github.com/facebookresearch/faiss), and
[Lucene](https://lucene.apache.org/) libraries to power k-NN search.
- `Script Scoring` extends OpenSearch’s script scoring functionality to
execute a brute force, exact k-NN search.
- `Painless Scripting` adds the distance functions as painless
extensions that can be used in more complex combinations. Also, supports
brute force, exact k-NN search like Script Scoring.
### Issues Resolved
https://github.com/hwchase17/langchain/issues/1054
---------
Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
Pydantic validation breaks tests for example (`test_qdrant.py`) because
fake embeddings contain an integer.
This PR casts the embeddings array to all floats.
Now the `qdrant` test passes, `poetry run pytest
tests/integration_tests/vectorstores/test_qdrant.py`
Fix KeyError 'items' when no result found.
## Problem
When no result found for a query, google search crashed with `KeyError
'items'`.
## Solution
I added a check for an empty response before accessing the 'items' key.
It will handle the case correctly.
## Other
my twitter: yakigac
(I don't mind even if you don't mention me for this PR. But just because
last time my real name was shout out :) )
Alternate implementation to PR #960 Again - only FAISS is implemented.
If accepted can add this to other vectorstores or leave as
NotImplemented? Suggestions welcome...
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
This PR adds persistence to the Chroma vector store.
Users can supply a `persist_directory` with any of the `Chroma` creation
methods. If supplied, the store will be automatically persisted at that
directory.
If a user creates a new `Chroma` instance with the same persistence
directory, it will get loaded up automatically. If they use `from_texts`
or `from_documents` in this way, the documents will be loaded into the
existing store.
There is the chance of some funky behavior if the user passes a
different embedding function from the one used to create the collection
- we will make this easier in future updates. For now, we log a warning.
Chroma is a simple to use, open-source, zero-config, zero setup
vectorstore.
Simply `pip install chromadb`, and you're good to go.
Out-of-the-box Chroma is suitable for most LangChain workloads, but is
highly flexible. I tested to 1M embs on my M1 mac, with out issues and
reasonably fast query times.
Look out for future releases as we integrate more Chroma features with
LangChain!
Co-authored-by: Andrew White <white.d.andrew@gmail.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
Co-authored-by: Peng Qu <82029664+pengqu123@users.noreply.github.com>
Supporting asyncio in langchain primitives allows for users to run them
concurrently and creates more seamless integration with
asyncio-supported frameworks (FastAPI, etc.)
Summary of changes:
**LLM**
* Add `agenerate` and `_agenerate`
* Implement in OpenAI by leveraging `client.Completions.acreate`
**Chain**
* Add `arun`, `acall`, `_acall`
* Implement them in `LLMChain` and `LLMMathChain` for now
**Agent**
* Refactor and leverage async chain and llm methods
* Add ability for `Tools` to contain async coroutine
* Implement async SerpaPI `arun`
Create demo notebook.
Open questions:
* Should all the async stuff go in separate classes? I've seen both
patterns (keeping the same class and having async and sync methods vs.
having class separation)
Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
Signed-off-by: Frank Liu <frank.liu@zilliz.com>
Co-authored-by: Filip Haltmayer <81822489+filip-halt@users.noreply.github.com>
Co-authored-by: Frank Liu <frank@frankzliu.com>
This does not involve a separator, and will naively chunk input text at
the appropriate boundaries in token space.
This is helpful if we have strict token length limits that we need to
strictly follow the specified chunk size, and we can't use aggressive
separators like spaces to guarantee the absence of long strings.
CharacterTextSplitter will let these strings through without splitting
them, which could cause overflow errors downstream.
Splitting at arbitrary token boundaries is not ideal but is hopefully
mitigated by having a decent overlap quantity. Also this results in
chunks which has exact number of tokens desired, instead of sometimes
overcounting if we concatenate shorter strings.
Potentially also helps with #528.
- This uses the faiss built-in `write_index` and `load_index` to save
and load faiss indexes locally
- Also fixes#674
- The save/load functions also use the faiss library, so I refactored
the dependency into a function
https://github.com/hwchase17/langchain/issues/354
Add support for running your own HF pipeline locally. This would allow
you to get a lot more dynamic with what HF features and models you
support since you wouldn't be beholden to what is hosted in HF hub. You
could also do stuff with HF Optimum to quantize your models and stuff to
get pretty fast inference even running on a laptop.
Add support for calling HuggingFace embedding models
using the HuggingFaceHub Inference API. New class mirrors
the existing HuggingFaceHub LLM implementation. Currently
only supports 'sentence-transformers' models.
Closes#86
this will break atm but wanted to get thoughts on implementation.
1. should add() be on docstore interface?
2. should InMemoryDocstore change to take a list of documents as init?
(makes this slightly easier to implement in FAISS -- if we think it is
less clean then could expose a method to get the number of documents
currently in the dict, and perform the logic of creating the necessary
dictionary in the FAISS.add_texts method.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
