- 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>
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>
- **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: 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
- 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.
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
## 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>
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>
### 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: Minimax is a great AI startup from China, recently they
released their latest model and chat API, and the API is widely-spread
in China. As a result, I'd like to add the Minimax llm model to
Langchain.
- Tag maintainer: @hwchase17, @baskaryan
---------
Co-authored-by: the <tao.he@hulu.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- [Xorbits
Inference(Xinference)](https://github.com/xorbitsai/inference) is a
powerful and versatile library designed to serve language, speech
recognition, and multimodal models. Xinference supports a variety of
GGML-compatible models including chatglm, whisper, and vicuna, and
utilizes heterogeneous hardware and a distributed architecture for
seamless cross-device and cross-server model deployment.
- This PR integrates Xinference models and Xinference embeddings into
LangChain.
- Dependencies: To install the depenedencies for this integration, run
`pip install "xinference[all]"`
- Example Usage:
To start a local instance of Xinference, run `xinference`.
To deploy Xinference in a distributed cluster, first start an Xinference
supervisor using `xinference-supervisor`:
`xinference-supervisor -H "${supervisor_host}"`
Then, start the Xinference workers using `xinference-worker` on each
server you want to run them on.
`xinference-worker -e "http://${supervisor_host}:9997"`
To use Xinference with LangChain, you also need to launch a model. You
can use command line interface (CLI) to do so. Fo example: `xinference
launch -n vicuna-v1.3 -f ggmlv3 -q q4_0`. This launches a model named
vicuna-v1.3 with `model_format="ggmlv3"` and `quantization="q4_0"`. A
model UID is returned for you to use.
Now you can use Xinference with LangChain:
```python
from langchain.llms import Xinference
llm = Xinference(
server_url="http://0.0.0.0:9997", # suppose the supervisor_host is "0.0.0.0"
model_uid = {model_uid} # model UID returned from launching a model
)
llm(
prompt="Q: where can we visit in the capital of France? A:",
generate_config={"max_tokens": 1024},
)
```
You can also use RESTful client to launch a model:
```python
from xinference.client import RESTfulClient
client = RESTfulClient("http://0.0.0.0:9997")
model_uid = client.launch_model(model_name="vicuna-v1.3", model_size_in_billions=7, quantization="q4_0")
```
The following code block demonstrates how to use Xinference embeddings
with LangChain:
```python
from langchain.embeddings import XinferenceEmbeddings
xinference = XinferenceEmbeddings(
server_url="http://0.0.0.0:9997",
model_uid = model_uid
)
```
```python
query_result = xinference.embed_query("This is a test query")
```
```python
doc_result = xinference.embed_documents(["text A", "text B"])
```
Xinference is still under rapid development. Feel free to [join our
Slack
community](https://xorbitsio.slack.com/join/shared_invite/zt-1z3zsm9ep-87yI9YZ_B79HLB2ccTq4WA)
to get the latest updates!
- Request for review: @hwchase17, @baskaryan
- Twitter handle: https://twitter.com/Xorbitsio
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
