## Description
This PR adds integration tests to follow up on #24164.
By default, the tests use an in-memory instance.
To run the full suite of tests, with both in-memory and Qdrant server:
```
$ docker run -p 6333:6333 qdrant/qdrant
$ make test
$ make integration_test
```
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description:** Explicitly add parameters from openai API
- [X] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Added missed docstrings. Format docstrings to the consistent format
(used in the API Reference)
---------
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
Co-authored-by: Erick Friis <erick@langchain.dev>
I stumbled upon a bug that led to different similarity scores between
the async and sync similarity searches with relevance scores in Qdrant.
The reason being is that _asimilarity_search_with_relevance_scores is
missing, this makes langchain_qdrant use the method of the vectorstore
baseclass leading to drastically different results.
To illustrate the magnitude here are the results running an identical
search in a test vectorstore.
Output of asimilarity_search_with_relevance_scores:
[0.9902903374601824, 0.9472135924938804, 0.8535534011299859]
Output of similarity_search_with_relevance_scores:
[0.9805806749203648, 0.8944271849877607, 0.7071068022599718]
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for contributing to LangChain!
- [ ] **HuggingFaceEndpoint**: "Skip Login to HuggingFaceHub"
- Where: langchain, community, llm, huggingface_endpoint
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Skip login to huggingface hub when when
`huggingfacehub_api_token` is not set. This is needed when using custom
`endpoint_url` outside of HuggingFaceHub.
- **Issue:** the issue # it fixes
https://github.com/langchain-ai/langchain/issues/20342 and
https://github.com/langchain-ai/langchain/issues/19685
- **Dependencies:** None
- [ ] **Add tests and docs**:
1. Tested with locally available TGI endpoint
2. Example Usage
```python
from langchain_community.llms import HuggingFaceEndpoint
llm = HuggingFaceEndpoint(
endpoint_url='http://localhost:8080',
server_kwargs={
"headers": {"Content-Type": "application/json"}
}
)
resp = llm.invoke("Tell me a joke")
print(resp)
```
Also tested against HF Endpoints
```python
from langchain_community.llms import HuggingFaceEndpoint
huggingfacehub_api_token = "hf_xyz"
repo_id = "mistralai/Mistral-7B-Instruct-v0.2"
llm = HuggingFaceEndpoint(
huggingfacehub_api_token=huggingfacehub_api_token,
repo_id=repo_id,
)
resp = llm.invoke("Tell me a joke")
print(resp)
```
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for contributing to LangChain!
**Description:** Add support for caching (standard + semantic) LLM
responses using Couchbase
- [x] **Add tests and docs**: 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. It lives in
`docs/docs/integrations` directory.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Nithish Raghunandanan <nithishr@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
If you use `refresh_schema=False`, then the metadata constraint doesn't
exist. ATM, we used default `None` in the constraint check, but then
`any` fails because it can't iterate over None value
- **Description:** `StuffDocumentsChain` uses `LLMChain` which is
deprecated by langchain runnables. `create_stuff_documents_chain` is the
replacement, but needs support for `document_variable_name` to allow
multiple uses of the chain within a longer chain.
- **Issue:** none
- **Dependencies:** none
Thank you for contributing to LangChain!
**Description**:
This PR fixes a bug described in the issue in #24064, when using the
AzureSearch Vectorstore with the asyncronous methods to do search which
is also the method used for the retriever. The proposed change includes
just change the access of the embedding as optional because is it not
used anywhere to retrieve documents. Actually, the syncronous methods of
retrieval do not use the embedding neither.
With this PR the code given by the user in the issue works.
```python
vectorstore = AzureSearch(
azure_search_endpoint=os.getenv("AI_SEARCH_ENDPOINT_SECRET"),
azure_search_key=os.getenv("AI_SEARCH_API_KEY"),
index_name=os.getenv("AI_SEARCH_INDEX_NAME_SECRET"),
fields=fields,
embedding_function=encoder,
)
retriever = vectorstore.as_retriever(search_type="hybrid", k=2)
await vectorstore.avector_search("what is the capital of France")
await retriever.ainvoke("what is the capital of France")
```
**Issue**:
The Azure Search Vectorstore is not working when searching for documents
with asyncronous methods, as described in issue #24064
**Dependencies**:
There are no extra dependencies required for this change.
---------
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
## Description
This PR introduces a new sparse embedding provider interface to work
with the new Qdrant implementation that will follow this PR.
Additionally, an implementation of this interface is provided with
https://github.com/qdrant/fastembed.
This PR will be followed by
https://github.com/Anush008/langchain/pull/3.
Disabled by default.
```python
from langchain_core.tools import tool
@tool(parse_docstring=True)
def foo(bar: str, baz: int) -> str:
"""The foo.
Args:
bar: this is the bar
baz: this is the baz
"""
return bar
foo.args_schema.schema()
```
```json
{
"title": "fooSchema",
"description": "The foo.",
"type": "object",
"properties": {
"bar": {
"title": "Bar",
"description": "this is the bar",
"type": "string"
},
"baz": {
"title": "Baz",
"description": "this is the baz",
"type": "integer"
}
},
"required": [
"bar",
"baz"
]
}
```
Refactor the code to use the existing InMemroyVectorStore.
This change is needed for another PR that moves some of the imports
around (and messes up the mock.patch in this file)
Description: ImagePromptTemplate for Multimodal llms like llava when
using Ollama
Twitter handle: https://x.com/a7ulr
Details:
When using llava models / any ollama multimodal llms and passing images
in the prompt as urls, langchain breaks with this error.
```python
image_url_components = image_url.split(",")
^^^^^^^^^^^^^^^^^^^^
AttributeError: 'dict' object has no attribute 'split'
```
From the looks of it, there was bug where the condition did check for a
`url` field in the variable but missed to actually assign it.
This PR fixes ImagePromptTemplate for Multimodal llms like llava when
using Ollama specifically.
@hwchase17
