## Description
The following PR enables the [grammar-based
sampling](https://github.com/ggerganov/llama.cpp/tree/master/grammars)
in llama-cpp LLM.
In short, loading file with formal grammar definition will constrain
model outputs. For instance, one can force the model to generate valid
JSON or generate only python lists.
In the follow-up PR we will add:
* docs with some description why it is cool and how it works
* maybe some code sample for some task such as in llama repo
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Description
The previous Redis implementation did not allow for the user to specify
the index configuration (i.e. changing the underlying algorithm) or add
additional metadata to use for querying (i.e. hybrid or "filtered"
search).
This PR introduces the ability to specify custom index attributes and
metadata attributes as well as use that metadata in filtered queries.
Overall, more structure was introduced to the Redis implementation that
should allow for easier maintainability moving forward.
# New Features
The following features are now available with the Redis integration into
Langchain
## Index schema generation
The schema for the index will now be automatically generated if not
specified by the user. For example, the data above has the multiple
metadata categories. The the following example
```python
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores.redis import Redis
embeddings = OpenAIEmbeddings()
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users"
)
```
Loading the data in through this and the other ``from_documents`` and
``from_texts`` methods will now generate index schema in Redis like the
following.
view index schema with the ``redisvl`` tool. [link](redisvl.com)
```bash
$ rvl index info -i users
```
Index Information:
| Index Name | Storage Type | Prefixes | Index Options | Indexing |
|--------------|----------------|---------------|-----------------|------------|
| users | HASH | ['doc:users'] | [] | 0 |
Index Fields:
| Name | Attribute | Type | Field Option | Option Value |
|----------------|----------------|---------|----------------|----------------|
| user | user | TEXT | WEIGHT | 1 |
| job | job | TEXT | WEIGHT | 1 |
| credit_score | credit_score | TEXT | WEIGHT | 1 |
| content | content | TEXT | WEIGHT | 1 |
| age | age | NUMERIC | | |
| content_vector | content_vector | VECTOR | | |
### Custom Metadata specification
The metadata schema generation has the following rules
1. All text fields are indexed as text fields.
2. All numeric fields are index as numeric fields.
If you would like to have a text field as a tag field, users can specify
overrides like the following for the example data
```python
# this can also be a path to a yaml file
index_schema = {
"text": [{"name": "user"}, {"name": "job"}],
"tag": [{"name": "credit_score"}],
"numeric": [{"name": "age"}],
}
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users"
)
```
This will change the index specification to
Index Information:
| Index Name | Storage Type | Prefixes | Index Options | Indexing |
|--------------|----------------|----------------|-----------------|------------|
| users2 | HASH | ['doc:users2'] | [] | 0 |
Index Fields:
| Name | Attribute | Type | Field Option | Option Value |
|----------------|----------------|---------|----------------|----------------|
| user | user | TEXT | WEIGHT | 1 |
| job | job | TEXT | WEIGHT | 1 |
| content | content | TEXT | WEIGHT | 1 |
| credit_score | credit_score | TAG | SEPARATOR | , |
| age | age | NUMERIC | | |
| content_vector | content_vector | VECTOR | | |
and throw a warning to the user (log output) that the generated schema
does not match the specified schema.
```text
index_schema does not match generated schema from metadata.
index_schema: {'text': [{'name': 'user'}, {'name': 'job'}], 'tag': [{'name': 'credit_score'}], 'numeric': [{'name': 'age'}]}
generated_schema: {'text': [{'name': 'user'}, {'name': 'job'}, {'name': 'credit_score'}], 'numeric': [{'name': 'age'}]}
```
As long as this is on purpose, this is fine.
The schema can be defined as a yaml file or a dictionary
```yaml
text:
- name: user
- name: job
tag:
- name: credit_score
numeric:
- name: age
```
and you pass in a path like
```python
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users3",
index_schema=Path("sample1.yml").resolve()
)
```
Which will create the same schema as defined in the dictionary example
Index Information:
| Index Name | Storage Type | Prefixes | Index Options | Indexing |
|--------------|----------------|----------------|-----------------|------------|
| users3 | HASH | ['doc:users3'] | [] | 0 |
Index Fields:
| Name | Attribute | Type | Field Option | Option Value |
|----------------|----------------|---------|----------------|----------------|
| user | user | TEXT | WEIGHT | 1 |
| job | job | TEXT | WEIGHT | 1 |
| content | content | TEXT | WEIGHT | 1 |
| credit_score | credit_score | TAG | SEPARATOR | , |
| age | age | NUMERIC | | |
| content_vector | content_vector | VECTOR | | |
### Custom Vector Indexing Schema
Users with large use cases may want to change how they formulate the
vector index created by Langchain
To utilize all the features of Redis for vector database use cases like
this, you can now do the following to pass in index attribute modifiers
like changing the indexing algorithm to HNSW.
```python
vector_schema = {
"algorithm": "HNSW"
}
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users3",
vector_schema=vector_schema
)
```
A more complex example may look like
```python
vector_schema = {
"algorithm": "HNSW",
"ef_construction": 200,
"ef_runtime": 20
}
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users3",
vector_schema=vector_schema
)
```
All names correspond to the arguments you would set if using Redis-py or
RedisVL. (put in doc link later)
### Better Querying
Both vector queries and Range (limit) queries are now available and
metadata is returned by default. The outputs are shown.
```python
>>> query = "foo"
>>> results = rds.similarity_search(query, k=1)
>>> print(results)
[Document(page_content='foo', metadata={'user': 'derrick', 'job': 'doctor', 'credit_score': 'low', 'age': '14', 'id': 'doc:users:657a47d7db8b447e88598b83da879b9d', 'score': '7.15255737305e-07'})]
>>> results = rds.similarity_search_with_score(query, k=1, return_metadata=False)
>>> print(results) # no metadata, but with scores
[(Document(page_content='foo', metadata={}), 7.15255737305e-07)]
>>> results = rds.similarity_search_limit_score(query, k=6, score_threshold=0.0001)
>>> print(len(results)) # range query (only above threshold even if k is higher)
4
```
### Custom metadata filtering
A big advantage of Redis in this space is being able to do filtering on
data stored alongside the vector itself. With the example above, the
following is now possible in langchain. The equivalence operators are
overridden to describe a new expression language that mimic that of
[redisvl](redisvl.com). This allows for arbitrarily long sequences of
filters that resemble SQL commands that can be used directly with vector
queries and range queries.
There are two interfaces by which to do so and both are shown.
```python
>>> from langchain.vectorstores.redis import RedisFilter, RedisNum, RedisText
>>> age_filter = RedisFilter.num("age") > 18
>>> age_filter = RedisNum("age") > 18 # equivalent
>>> results = rds.similarity_search(query, filter=age_filter)
>>> print(len(results))
3
>>> job_filter = RedisFilter.text("job") == "engineer"
>>> job_filter = RedisText("job") == "engineer" # equivalent
>>> results = rds.similarity_search(query, filter=job_filter)
>>> print(len(results))
2
# fuzzy match text search
>>> job_filter = RedisFilter.text("job") % "eng*"
>>> results = rds.similarity_search(query, filter=job_filter)
>>> print(len(results))
2
# combined filters (AND)
>>> combined = age_filter & job_filter
>>> results = rds.similarity_search(query, filter=combined)
>>> print(len(results))
1
# combined filters (OR)
>>> combined = age_filter | job_filter
>>> results = rds.similarity_search(query, filter=combined)
>>> print(len(results))
4
```
All the above filter results can be checked against the data above.
### Other
- Issue: #3967
- Dependencies: No added dependencies
- Tag maintainer: @hwchase17 @baskaryan @rlancemartin
- Twitter handle: @sampartee
---------
Co-authored-by: Naresh Rangan <naresh.rangan0@walmart.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This adds Xata as a memory store also to the python version of
LangChain, similar to the [one for
LangChain.js](https://github.com/hwchase17/langchainjs/pull/2217).
I have added a Jupyter Notebook with a simple and a more complex example
using an agent.
To run the integration test, you need to execute something like:
```
XATA_API_KEY='xau_...' XATA_DB_URL="https://demo-uni3q8.eu-west-1.xata.sh/db/langchain" poetry run pytest tests/integration_tests/memory/test_xata.py
```
Where `langchain` is the database you create in Xata.
Still working out interface/notebooks + need discord data dump to test
out things other than copy+paste
Update:
- Going to remove the 'user_id' arg in the loaders themselves and just
standardize on putting the "sender" arg in the extra kwargs. Then can
provide a utility function to map these to ai and human messages
- Going to move the discord one into just a notebook since I don't have
a good dump to test on and copy+paste maybe isn't the greatest thing to
support in v0
- Need to do more testing on slack since it seems the dump only includes
channels and NOT 1 on 1 convos
-
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Uses the shorter import path
`from langchain.document_loaders import` instead of the full path
`from langchain.document_loaders.assemblyai`
Applies those changes to the docs and the unit test.
See #9667 that adds this new loader.
Note: There are no changes in the file names!
- The group name on the main navbar changed: `Agent toolkits` -> `Agents
& Toolkits`. Examples here are the mix of the Agent and Toolkit examples
because Agents and Toolkits in examples are always used together.
- Titles changed: removed "Agent" and "Toolkit" suffixes. The reason is
the same.
- Formatting: mostly cleaning the header structure, so it could be
better on the right-side navbar.
Main navbar is looking much cleaner now.
This PR adds a new document loader `AssemblyAIAudioTranscriptLoader`
that allows to transcribe audio files with the [AssemblyAI
API](https://www.assemblyai.com) and loads the transcribed text into
documents.
- Add new document_loader with class `AssemblyAIAudioTranscriptLoader`
- Add optional dependency `assemblyai`
- Add unit tests (using a Mock client)
- Add docs notebook
This is the equivalent to the JS integration already available in
LangChain.js. See the [LangChain JS docs AssemblyAI
page](https://js.langchain.com/docs/modules/data_connection/document_loaders/integrations/web_loaders/assemblyai_audio_transcription).
At its simplest, you can use the loader to get a transcript back from an
audio file like this:
```python
from langchain.document_loaders.assemblyai import AssemblyAIAudioTranscriptLoader
loader = AssemblyAIAudioTranscriptLoader(file_path="./testfile.mp3")
docs = loader.load()
```
To use it, it needs the `assemblyai` python package installed, and the
environment variable `ASSEMBLYAI_API_KEY` set with your API key.
Alternatively, the API key can also be passed as an argument.
Twitter handles to shout out if so kindly 🙇
[@AssemblyAI](https://twitter.com/AssemblyAI) and
[@patloeber](https://twitter.com/patloeber)
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Improve internal consistency in LangChain documentation
- Change occurrences of eg and eg. to e.g.
- Fix headers containing unnecessary capital letters.
- Change instances of "few shot" to "few-shot".
- Add periods to end of sentences where missing.
- Minor spelling and grammar fixes.
The Docugami loader was not returning the source metadata key. This was
triggering this exception when used with retrievers, per
https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/schema/prompt_template.py#L193C1-L195C41
The fix is simple and just updates the metadata key name for the
document each chunk is sourced from, from "name" to "source" as
expected.
I tested by running the python notebook that has an end to end scenario
in it.
Tagging DataLoader maintainers @rlancemartin @eyurtsev
Not obvious what the error is when you cannot index. This pr adds the
ability to log the first errors reason, to help the user diagnose the
issue.
Also added some more documentation for when you want to use the
vectorstore with an embedding model deployed in elasticsearch.
Credit: @elastic and @phoey1
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: Added the capability to handles structured data from
google enterprise search,
- Issue: Retriever failed when underline search engine was integrated
with structured data,
- Dependencies: google-api-core
- Tag maintainer: @jarokaz
- Twitter handle: anifort
Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: Christos Aniftos <aniftos@google.com>
Co-authored-by: Holt Skinner <13262395+holtskinner@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
# Description
This PR introduces a new toolkit for interacting with the AINetwork
blockchain. The toolkit provides a set of tools for performing various
operations on the AINetwork blockchain, such as transferring AIN,
reading and writing values to the blockchain database, managing apps,
setting rules and owners.
# Dependencies
[ain-py](https://github.com/ainblockchain/ain-py) >= 1.0.2
# Misc
The example notebook
(langchain/docs/extras/integrations/toolkits/ainetwork.ipynb) is in the
PR
---------
Co-authored-by: kriii <kriii@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Description
Polars is a DataFrame interface on top of an OLAP Query Engine
implemented in Rust.
Polars is faster to read than pandas, so I'm looking forward to seeing
it added to the document loader.
### Dependencies
polars (https://pola-rs.github.io/polars-book/user-guide/)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Add PromptGuard integration
-------
There are two approaches to integrate PromptGuard with a LangChain
application.
1. PromptGuardLLMWrapper
2. functions that can be used in LangChain expression.
-----
- Dependencies
`promptguard` python package, which is a runtime requirement if you'd
try out the demo.
- @baskaryan @hwchase17 Thanks for the ideas and suggestions along the
development process.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Improved docs
- Improved performance in multiple ways through batching, threading,
etc.
- fixed error message
- Added support for metadata filtering during similarity search.
@baskaryan PTAL
[Epsilla](https://github.com/epsilla-cloud/vectordb) vectordb is an
open-source vector database that leverages the advanced academic
parallel graph traversal techniques for vector indexing.
This PR adds basic integration with
[pyepsilla](https://github.com/epsilla-cloud/epsilla-python-client)(Epsilla
vectordb python client) as a vectorstore.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: support [ERNIE
Embedding-V1](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/alj562vvu),
which is part of ERNIE ecology
- Issue: None
- Dependencies: None
- Tag maintainer: @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: Updating documentation to add AmazonTextractPDFLoader
according to
[comment](https://github.com/langchain-ai/langchain/pull/8661#issuecomment-1666572992)
from [baskaryan](https://github.com/baskaryan)
Adding one notebook and instructions to the
modules/data_connection/document_loaders/pdf.mdx
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
### Summary
Fixes a bug from #7850 where post processing functions in Unstructured
loaders were not apply. Adds a assertion to the test to verify the post
processing function was applied and also updates the explanation in the
example notebook.
- Description: Added improvements in Nebula LLM to perform auto-retry;
more generation parameters supported. Conversation is no longer required
to be passed in the LLM object. Examples are updated.
- Issue: N/A
- Dependencies: N/A
- Tag maintainer: @baskaryan
- Twitter handle: symbldotai
---------
Co-authored-by: toshishjawale <toshish@symbl.ai>
Update documentation and URLs for the Langchain Context integration.
We've moved from getcontext.ai to context.ai \o/
Thanks in advance for the review!
Todo:
- [x] Connection options (cloud, localhost url, es_connection) support
- [x] Logging support
- [x] Customisable field support
- [x] Distance Similarity support
- [x] Metadata support
- [x] Metadata Filter support
- [x] Retrieval Strategies
- [x] Approx
- [x] Approx with Hybrid
- [x] Exact
- [x] Custom
- [x] ELSER (excluding hybrid as we are working on RRF support)
- [x] integration tests
- [x] Documentation
👋 this is a contribution to improve Elasticsearch integration with
Langchain. Its based loosely on the changes that are in master but with
some notable changes:
## Package name & design improvements
The import name is now `ElasticsearchStore`, to aid discoverability of
the VectorStore.
```py
## Before
from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch, ElasticKnnSearch
## Now
from langchain.vectorstores.elasticsearch import ElasticsearchStore
```
## Retrieval Strategy support
Before we had a number of classes, depending on the strategy you wanted.
`ElasticKnnSearch` for approx, `ElasticVectorSearch` for exact / brute
force.
With `ElasticsearchStore` we have retrieval strategies:
### Approx Example
Default strategy for the vast majority of developers who use
Elasticsearch will be inferring the embeddings from outside of
Elasticsearch. Uses KNN functionality of _search.
```py
texts = ["foo", "bar", "baz"]
docsearch = ElasticsearchStore.from_texts(
texts,
FakeEmbeddings(),
es_url="http://localhost:9200",
index_name="sample-index"
)
output = docsearch.similarity_search("foo", k=1)
```
### Approx, with hybrid
Developers who want to search, using both the embedding and the text
bm25 match. Its simple to enable.
```py
texts = ["foo", "bar", "baz"]
docsearch = ElasticsearchStore.from_texts(
texts,
FakeEmbeddings(),
es_url="http://localhost:9200",
index_name="sample-index",
strategy=ElasticsearchStore.ApproxRetrievalStrategy(hybrid=True)
)
output = docsearch.similarity_search("foo", k=1)
```
### Approx, with `query_model_id`
Developers who want to infer within Elasticsearch, using the model
loaded in the ml node.
This relies on the developer to setup the pipeline and index if they
wish to embed the text in Elasticsearch. Example of this in the test.
```py
texts = ["foo", "bar", "baz"]
docsearch = ElasticsearchStore.from_texts(
texts,
FakeEmbeddings(),
es_url="http://localhost:9200",
index_name="sample-index",
strategy=ElasticsearchStore.ApproxRetrievalStrategy(
query_model_id="sentence-transformers__all-minilm-l6-v2"
),
)
output = docsearch.similarity_search("foo", k=1)
```
### I want to provide my own custom Elasticsearch Query
You might want to have more control over the query, to perform
multi-phase retrieval such as LTR, linearly boosting on document
parameters like recently updated or geo-distance. You can do this with
`custom_query_fn`
```py
def my_custom_query(query_body: dict, query: str) -> dict:
return {"query": {"match": {"text": {"query": "bar"}}}}
texts = ["foo", "bar", "baz"]
docsearch = ElasticsearchStore.from_texts(
texts, FakeEmbeddings(), **elasticsearch_connection, index_name=index_name
)
docsearch.similarity_search("foo", k=1, custom_query=my_custom_query)
```
### Exact Example
Developers who have a small dataset in Elasticsearch, dont want the cost
of indexing the dims vs tradeoff on cost at query time. Uses
script_score.
```py
texts = ["foo", "bar", "baz"]
docsearch = ElasticsearchStore.from_texts(
texts,
FakeEmbeddings(),
es_url="http://localhost:9200",
index_name="sample-index",
strategy=ElasticsearchStore.ExactRetrievalStrategy(),
)
output = docsearch.similarity_search("foo", k=1)
```
### ELSER Example
Elastic provides its own sparse vector model called ELSER. With these
changes, its really easy to use. The vector store creates a pipeline and
index thats setup for ELSER. All the developer needs to do is configure,
ingest and query via langchain tooling.
```py
texts = ["foo", "bar", "baz"]
docsearch = ElasticsearchStore.from_texts(
texts,
FakeEmbeddings(),
es_url="http://localhost:9200",
index_name="sample-index",
strategy=ElasticsearchStore.SparseVectorStrategy(),
)
output = docsearch.similarity_search("foo", k=1)
```
## Architecture
In future, we can introduce new strategies and allow us to not break bwc
as we evolve the index / query strategy.
## Credit
On release, could you credit @elastic and @phoey1 please? Thank you!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Adds [DeepSparse](https://github.com/neuralmagic/deepsparse) as an LLM
backend. DeepSparse supports running various open-source sparsified
models hosted on [SparseZoo](https://sparsezoo.neuralmagic.com/) for
performance gains on CPUs.
Twitter handles: @mgoin_ @neuralmagic
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit adds the LangChain utility which allows for the real-time
retrieval of cryptocurrency exchange prices. With LangChain, users can
easily access up-to-date pricing information by running the command
".run(from_currency, to_currency)". This new feature provides a
convenient way to stay informed on the latest exchange rates and make
informed decisions when trading crypto.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Adds the ArcGISLoader class to
`langchain.document_loaders`
- Allows users to load data from ArcGIS Online, Portal, and similar
- Users can authenticate with `arcgis.gis.GIS` or retrieve public data
anonymously
- Uses the `arcgis.features.FeatureLayer` class to retrieve the data
- Defines the most relevant keywords arguments and accepts `**kwargs`
- Dependencies: Using this class requires `arcgis` and, optionally,
`bs4.BeautifulSoup`.
Tagging maintainers:
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Added a new use case category called "Web Scraping", and
a tutorial to scrape websites using OpenAI Functions Extraction chain to
the docs.
- Tag maintainer:@baskaryan @hwchase17 ,
- Twitter handle: https://www.linkedin.com/in/haiphunghiem/ (I'm on
LinkedIn mostly)
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
This PR introduces [Label Studio](https://labelstud.io/) integration
with LangChain via `LabelStudioCallbackHandler`:
- sending data to the Label Studio instance
- labeling dataset for supervised LLM finetuning
- rating model responses
- tracking and displaying chat history
- support for custom data labeling workflow
### Example
```
chat_llm = ChatOpenAI(callbacks=[LabelStudioCallbackHandler(mode="chat")])
chat_llm([
SystemMessage(content="Always use emojis in your responses."),
HumanMessage(content="Hey AI, how's your day going?"),
AIMessage(content="🤖 I don't have feelings, but I'm running smoothly! How can I help you today?"),
HumanMessage(content="I'm feeling a bit down. Any advice?"),
AIMessage(content="🤗 I'm sorry to hear that. Remember, it's okay to seek help or talk to someone if you need to. 💬"),
HumanMessage(content="Can you tell me a joke to lighten the mood?"),
AIMessage(content="Of course! 🎭 Why did the scarecrow win an award? Because he was outstanding in his field! 🌾"),
HumanMessage(content="Haha, that was a good one! Thanks for cheering me up."),
AIMessage(content="Always here to help! 😊 If you need anything else, just let me know."),
HumanMessage(content="Will do! By the way, can you recommend a good movie?"),
])
```
<img width="906" alt="image"
src="https://github.com/langchain-ai/langchain/assets/6087484/0a1cf559-0bd3-4250-ad96-6e71dbb1d2f3">
### Dependencies
- [label-studio](https://pypi.org/project/label-studio/)
- [label-studio-sdk](https://pypi.org/project/label-studio-sdk/)
https://twitter.com/labelstudiohq
---------
Co-authored-by: nik <nik@heartex.net>
As of the recent PR at #9043, after some testing we've realised that the
default values were not being used for `api_key` and `api_url`. Besides
that, the default for `api_key` was set to `argilla.apikey`, but since
the default values are intended for people using the Argilla Quickstart
(easy to run and setup), the defaults should be instead `owner.apikey`
if using Argilla 1.11.0 or higher, or `admin.apikey` if using a lower
version of Argilla.
Additionally, we've removed the f-string replacements from the
docstrings.
---------
Co-authored-by: Gabriel Martin <gabriel@argilla.io>
In second section it looks like a copy/paste from the first section and
doesn't include the specific embedding model mentioned in the example so
I added it for clarity.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
The table creation process in these examples commands do not match what
the recently updated functions in these example commands is looking for.
This change updates the type in the table creation command.
Issue Number for my report of the doc problem #7446
@rlancemartin and @eyurtsev I believe this is your area
Twitter: @j1philli
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description**: [BagelDB](bageldb.ai) a collaborative vector
database. Integrated the bageldb PyPi package with langchain with
related tests and code.
- **Issue**: Not applicable.
- **Dependencies**: `betabageldb` PyPi package.
- **Tag maintainer**: @rlancemartin, @eyurtsev, @baskaryan
- **Twitter handle**: bageldb_ai (https://twitter.com/BagelDB_ai)
We ran `make format`, `make lint` and `make test` locally.
Followed the contribution guideline thoroughly
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
---------
Co-authored-by: Towhid1 <nurulaktertowhid@gmail.com>
## Description
This PR adds the `aembed_query` and `aembed_documents` async methods for
improving the embeddings generation for large documents. The
implementation uses asyncio tasks and gather to achieve concurrency as
there is no bedrock async API in boto3.
### Maintainers
@agola11
@aarora79
### Open questions
To avoid throttling from the Bedrock API, should there be an option to
limit the concurrency of the calls?
## Description:
This PR adds the Titan Takeoff Server to the available LLMs in
LangChain.
Titan Takeoff is an inference server created by
[TitanML](https://www.titanml.co/) that allows you to deploy large
language models locally on your hardware in a single command. Most
generative model architectures are included, such as Falcon, Llama 2,
GPT2, T5 and many more.
Read more about Titan Takeoff here:
-
[Blog](https://medium.com/@TitanML/introducing-titan-takeoff-6c30e55a8e1e)
- [Docs](https://docs.titanml.co/docs/titan-takeoff/getting-started)
#### Testing
As Titan Takeoff runs locally on port 8000 by default, no network access
is needed. Responses are mocked for testing.
- [x] Make Lint
- [x] Make Format
- [x] Make Test
#### Dependencies
No new dependencies are introduced. However, users will need to install
the titan-iris package in their local environment and start the Titan
Takeoff inferencing server in order to use the Titan Takeoff
integration.
Thanks for your help and please let me know if you have any questions.
cc: @hwchase17 @baskaryan
- Description: Improvement in the Grobid loader documentation, typos and
suggesting to use the docker image instead of installing Grobid in local
(the documentation was also limited to Mac, while docker allow running
in any platform)
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @whitenoise
This pull request aims to ensure that the `OpenAICallbackHandler` can
properly calculate the total cost for Azure OpenAI chat models. The
following changes have resolved this issue:
- The `model_name` has been added to the ChatResult llm_output. Without
this, the default values of `gpt-35-turbo` were applied. This was
causing the total cost for Azure OpenAI's GPT-4 to be significantly
inaccurate.
- A new parameter `model_version` has been added to `AzureChatOpenAI`.
Azure does not include the model version in the response. With the
addition of `model_name`, this is not a significant issue for GPT-4
models, but it's an issue for GPT-3.5-Turbo. Version 0301 (default) of
GPT-3.5-Turbo on Azure has a flat rate of 0.002 per 1k tokens for both
prompt and completion. However, version 0613 introduced a split in
pricing for prompt and completion tokens.
- The `OpenAICallbackHandler` implementation has been updated with the
proper model names, versions, and cost per 1k tokens.
Unit tests have been added to ensure the functionality works as
expected; the Azure ChatOpenAI notebook has been updated with examples.
Maintainers: @hwchase17, @baskaryan
Twitter handle: @jjczopek
---------
Co-authored-by: Jerzy Czopek <jerzy.czopek@avanade.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Instruction for integration with Log10: an [open
source](https://github.com/log10-io/log10) proxiless LLM data management
and application development platform that lets you log, debug and tag
your Langchain calls
- Tag maintainer: @baskaryan
- Twitter handle: @log10io @coffeephoenix
Several examples showing the integration included
[here](https://github.com/log10-io/log10/tree/main/examples/logging) and
in the PR
Description: Adds Rockset as a chat history store
Dependencies: no changes
Tag maintainer: @hwchase17
This PR passes linting and testing.
I added a test for the integration and an example notebook showing its
use.
This PR adds 8 new loaders:
* `AirbyteCDKLoader` This reader can wrap and run all python-based
Airbyte source connectors.
* Separate loaders for the most commonly used APIs:
* `AirbyteGongLoader`
* `AirbyteHubspotLoader`
* `AirbyteSalesforceLoader`
* `AirbyteShopifyLoader`
* `AirbyteStripeLoader`
* `AirbyteTypeformLoader`
* `AirbyteZendeskSupportLoader`
## Documentation and getting started
I added the basic shape of the config to the notebooks. This increases
the maintenance effort a bit, but I think it's worth it to make sure
people can get started quickly with these important connectors. This is
also why I linked the spec and the documentation page in the readme as
these two contain all the information to configure a source correctly
(e.g. it won't suggest using oauth if that's avoidable even if the
connector supports it).
## Document generation
The "documents" produced by these loaders won't have a text part
(instead, all the record fields are put into the metadata). If a text is
required by the use case, the caller needs to do custom transformation
suitable for their use case.
## Incremental sync
All loaders support incremental syncs if the underlying streams support
it. By storing the `last_state` from the reader instance away and
passing it in when loading, it will only load updated records.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This addresses some issues with introducing the Nebula LLM to LangChain
in this PR:
https://github.com/langchain-ai/langchain/pull/8876
This fixes the following:
- Removes `SYMBLAI` from variable names
- Fixes bug with `Bearer` for the API KEY
Thanks again in advance for your help!
cc: @hwchase17, @baskaryan
---------
Co-authored-by: dvonthenen <david.vonthenen@gmail.com>
Minor doc fix to awslambda tool notebook.
Add missing import for initialize_agent to awslambda agent example
Co-authored-by: Josh Hart <josharj@amazon.com>
Description:
Fixed inaccurate import in integrations:providers:bedrock documentation
In the current version of the bedrock documentation, page
https://python.langchain.com/docs/integrations/providers/bedrock it
states that the import is from langchain import Bedrock
This has been changed to from langchain.llms.bedrock import Bedrock as
stated in https://python.langchain.com/docs/integrations/llms/bedrock
Issue:
Not applicable
Dependencies
No dependencies required
Tag maintainer
@baskaryan
Twitter handle:
Not applicable
Adds Ollama as an LLM. Ollama can run various open source models locally
e.g. Llama 2 and Vicuna, automatically configuring and GPU-optimizing
them.
@rlancemartin @hwchase17
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
## Description
I am excited to propose an integration with USearch, a lightweight
vector-search engine available for both Python and JavaScript, among
other languages.
## Dependencies
It introduces a new PyPi dependency - `usearch`. I am unsure if it must
be added to the Poetry file, as this would make the PR too clunky.
Please let me know.
## Profiles
- Maintainers: @ashvardanian @davvard
- Twitter handles: @ashvardanian @unum_cloud
---------
Co-authored-by: Davit Vardanyan <78792753+davvard@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- fix install command
- change example notebook to use Metaphor autoprompt by default
<!-- 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
-->
- Description: Adds the ChatAnyscale class with llama-2 7b, llama-2 13b,
and llama-2 70b on [Anyscale
Endpoints](https://app.endpoints.anyscale.com/)
- It inherits from ChatOpenAI and requires openai (probably unnecessary
but it made for a quick and easy implementation)
- Inspired by https://github.com/langchain-ai/langchain/pull/8434
(@kylehh and @baskaryan )
## Description
This PR adds Nebula to the available LLMs in LangChain.
Nebula is an LLM focused on conversation understanding and enables users
to extract conversation insights from video, audio, text, and chat-based
conversations. These conversations can occur between any mix of human or
AI participants.
Examples of some questions you could ask Nebula from a given
conversation are:
- What could be the customer’s pain points based on the conversation?
- What sales opportunities can be identified from this conversation?
- What best practices can be derived from this conversation for future
customer interactions?
You can read more about Nebula here:
https://symbl.ai/blog/extract-insights-symbl-ai-generative-ai-recall-ai-meetings/
#### Integration Test
An integration test is added, but it requires network access. Since
Nebula is fully managed like OpenAI, network access is required to
exercise the integration test.
#### Linting
- [x] make lint
- [x] make test (TODO: there seems to be a failure in another
non-related test??? Need to check on this.)
- [x] make format
### Dependencies
No new dependencies were introduced.
### Twitter handle
[@symbldotai](https://twitter.com/symbldotai)
[@dvonthenen](https://twitter.com/dvonthenen)
If you have any questions, please let me know.
cc: @hwchase17, @baskaryan
---------
Co-authored-by: dvonthenen <david.vonthenen@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This adds support for [Xata](https://xata.io) (data platform based on
Postgres) as a vector store. We have recently added [Xata to
Langchain.js](https://github.com/hwchase17/langchainjs/pull/2125) and
would love to have the equivalent in the Python project as well.
The PR includes integration tests and a Jupyter notebook as docs. Please
let me know if anything else would be needed or helpful.
I have added the xata python SDK as an optional dependency.
## To run the integration tests
You will need to create a DB in xata (see the docs), then run something
like:
```
OPENAI_API_KEY=sk-... XATA_API_KEY=xau_... XATA_DB_URL='https://....xata.sh/db/langchain' poetry run pytest tests/integration_tests/vectorstores/test_xata.py
```
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: a description of the change,
- Issue: the issue # it fixes (if applicable),
- Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Philip Krauss <35487337+philkra@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Hello langchain maintainers,
this PR aims at integrating
[vllm](https://vllm.readthedocs.io/en/latest/#) into langchain. This PR
closes#8729.
This feature clearly depends on `vllm`, but I've seen other models
supported here depend on packages that are not included in the
pyproject.toml (e.g. `gpt4all`, `text-generation`) so I thought it was
the case for this as well.
@hwchase17, @baskaryan
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- Updated to use newer better function interaction
- Previous version had only one callback
- @hinthornw @hwchase17 Can you look into this
- Shout out to @MultiON_AI @DivGarg9 on twitter
---------
Co-authored-by: Naman Garg <ngarg3@binghamton.edu>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Description: This PR improves the function of recursive_url_loader, such
as limiting the depth of the access, and customizable extractors(from
the raw webpage to the text of the Document object), so that users can
use other tools to extract the webpage. This PR also includes the
document and test for the new loader.
Old PR closed due to project structure change. #7756
Because socket requests are not allowed, the old unit test was removed.
Issue: N/A
Dependencies: asyncio, aiohttp
Tag maintainer: @rlancemartin
Twitter handle: @ Zend_Nihility
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: docstore had two main method: add and search, however,
dealing with docstore sometimes requires deleting an entry from
docstore. So I have added a simple delete method that deletes items from
docstore. Additionally, I have added the delete method to faiss
vectorstore for the very same reason.
- Issue: NA
- Dependencies: NA
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Description: Add ScaNN vectorstore to langchain.
ScaNN is a Open Source, high performance vector similarity library
optimized for AVX2-enabled CPUs.
https://github.com/google-research/google-research/tree/master/scann
- Dependencies: scann
Python notebook to illustrate the usage:
docs/extras/integrations/vectorstores/scann.ipynb
Integration test:
libs/langchain/tests/integration_tests/vectorstores/test_scann.py
@rlancemartin, @eyurtsev for review.
Thanks!
# What
- This is to add filter option to sklearn vectore store functions
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: Add filter to sklearn vectore store functions.
- Issue: None
- Dependencies: None
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @MlopsJ
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This is to add save_local and load_local to tfidf_vectorizer and docs in
tfidf_retriever to make the vectorizer reusable.
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: add save_local and load_local to tfidf_vectorizer and
docs in tfidf_retriever
- Issue: None
- Dependencies: None
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @MlopsJ
Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Simple retriever that applies an LLM between the user input and the
query pass the to retriever.
It can be used to pre-process the user input in any way.
The default prompt:
```
DEFAULT_QUERY_PROMPT = PromptTemplate(
input_variables=["question"],
template="""You are an assistant tasked with taking a natural languge query from a user
and converting it into a query for a vectorstore. In this process, you strip out
information that is not relevant for the retrieval task. Here is the user query: {question} """
)
```
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- Description: updates to Vectara documentation with more details on how
to get started.
- Issue: NA
- Dependencies: NA
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @vectara, @ofermend
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Replace this comment with:
- Description: added a document loader for a list of RSS feeds or OPML.
It iterates through the list and uses NewsURLLoader to load each
article.
- Issue: N/A
- Dependencies: feedparser, listparser
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @ruze
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: run the poetry dependencies
- Issue: #7329
- Dependencies: any dependencies required for this change,
- Tag maintainer: @rlancemartin
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description - Integrates Fireworks within Langchain LLMs to allow users
to use Fireworks models with Langchain, mainly for summarization.
Issue - Not applicable
Dependencies - None
Tag maintainer - @rlancemartin
---------
Co-authored-by: Raj Janardhan <rajjanardhan@Rajs-Laptop.attlocal.net>
Add a StreamlitChatMessageHistory class that stores chat messages in
[Streamlit's Session
State](https://docs.streamlit.io/library/api-reference/session-state).
Note: The integration test uses a currently-experimental Streamlit
testing framework to simulate the execution of a Streamlit app. Marking
this PR as draft until I confirm with the Streamlit team that we're
comfortable supporting it.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Summary
Updates the `unstructured` install instructions. For
`unstructured>=0.9.0`, dependencies are broken out by document type and
the base `unstructured` package includes fewer dependencies. `pip
install "unstructured[local-inference]"` has been replace by `pip
install "unstructured[all-docs]"`, though the `local-inference` extra is
still supported for the time being.
### Reviewers
- @rlancemartin
- @eyurtsev
- @hwchase17
## Description
This PR implements a callback handler for SageMaker Experiments which is
similar to that of mlflow.
* When creating the callback handler, it takes the experiment's run
object as an argument. All the callback outputs are then logged to the
run object.
* The output of each callback action (e.g., `on_llm_start`) is saved to
S3 bucket as json file.
* Optionally, you can also log additional information such as the LLM
hyper-parameters to the same run object.
* Once the callback object is no more needed, you will need to call the
`flush_tracker()` method. This makes sure that any intermediate files
are deleted.
* A separate notebook example is provided to show how the callback is
used.
@3coins @agola11
---------
Co-authored-by: Tesfagabir Meharizghi <mehariz@amazon.com>
Description:
This PR adds support for loading documents from Huawei OBS (Object
Storage Service) in Langchain. OBS is a cloud-based object storage
service provided by Huawei Cloud. With this enhancement, Langchain users
can now easily access and load documents stored in Huawei OBS directly
into the system.
Key Changes:
- Added a new document loader module specifically for Huawei OBS
integration.
- Implemented the necessary logic to authenticate and connect to Huawei
OBS using access credentials.
- Enabled the loading of individual documents from a specified bucket
and object key in Huawei OBS.
- Provided the option to specify custom authentication information or
obtain security tokens from Huawei Cloud ECS for easy access.
How to Test:
1. Ensure the required package "esdk-obs-python" is installed.
2. Configure the endpoint, access key, secret key, and bucket details
for Huawei OBS in the Langchain settings.
3. Load documents from Huawei OBS using the updated document loader
module.
4. Verify that documents are successfully retrieved and loaded into
Langchain for further processing.
Please review this PR and let us know if any further improvements are
needed. Your feedback is highly appreciated!
@rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Works just like the GenericLoader but concurrently for those who choose
to optimize their workflow.
@rlancemartin @eyurtsev
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This PR makes minor improvements to our python notebook, and adds
support for `Rockset` workspaces in our vectorstore client.
@rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
