community: Add you.com utility, update you retriever integration docs (#17014)

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes if applicable,
  - **Dependencies:** any dependencies required for this change,
- **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 your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

- **Description: changes to you.com files** 
    - general cleanup
- adds community/utilities/you.py, moving bulk of code from retriever ->
utility
    - removes `snippet` as endpoint
    - adds `news` as endpoint
    - adds more tests

<s>**Description: update community MAKE file** 
    - adds `integration_tests`
    - adds `coverage`</s>

- **Issue:** the issue # it fixes if applicable,
- [For New Contributors: Update Integration
Documentation](https://github.com/langchain-ai/langchain/issues/15664#issuecomment-1920099868)
- **Dependencies:** n/a
- **Twitter handle:** @scottnath
- **Mastodon handle:** scottnath@mastodon.social

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
Scott Nath
2024-02-08 16:47:50 -05:00
committed by GitHub
parent 3984f6604f
commit a32798abd7
9 changed files with 881 additions and 86 deletions

View File

@@ -1,64 +1,23 @@
from typing import Any, Dict, List, Optional
from typing import Any, List
from langchain_core.callbacks import CallbackManagerForRetrieverRun
from langchain_core.documents import Document
from langchain_core.pydantic_v1 import root_validator
from langchain_core.retrievers import BaseRetriever
from langchain_core.utils import get_from_dict_or_env
from langchain_community.utilities import YouSearchAPIWrapper
class YouRetriever(BaseRetriever):
class YouRetriever(BaseRetriever, YouSearchAPIWrapper):
"""`You` retriever that uses You.com's search API.
To connect to the You.com api requires an API key which
you can get by emailing api@you.com.
You can check out our docs at https://documentation.you.com.
You need to set the environment variable `YDC_API_KEY` for retriever to operate.
It wraps results() to get_relevant_documents
It uses all YouSearchAPIWrapper arguments without any change.
"""
ydc_api_key: str
k: Optional[int] = None
n_hits: Optional[int] = None
n_snippets_per_hit: Optional[int] = None
endpoint_type: str = "web"
@root_validator(pre=True)
def validate_client(
cls,
values: Dict[str, Any],
) -> Dict[str, Any]:
values["ydc_api_key"] = get_from_dict_or_env(
values, "ydc_api_key", "YDC_API_KEY"
)
return values
def _get_relevant_documents(
self, query: str, *, run_manager: CallbackManagerForRetrieverRun
self,
query: str,
*,
run_manager: CallbackManagerForRetrieverRun,
**kwargs: Any,
) -> List[Document]:
import requests
headers = {"X-API-Key": self.ydc_api_key}
if self.endpoint_type == "web":
results = requests.get(
f"https://api.ydc-index.io/search?query={query}",
headers=headers,
).json()
docs = []
n_hits = self.n_hits or len(results["hits"])
for hit in results["hits"][:n_hits]:
n_snippets_per_hit = self.n_snippets_per_hit or len(hit["snippets"])
for snippet in hit["snippets"][:n_snippets_per_hit]:
docs.append(Document(page_content=snippet))
if self.k is not None and len(docs) >= self.k:
return docs
return docs
elif self.endpoint_type == "snippet":
results = requests.get(
f"https://api.ydc-index.io/snippet_search?query={query}",
headers=headers,
).json()
return [Document(page_content=snippet) for snippet in results]
else:
raise RuntimeError(f"Invalid endpoint type provided {self.endpoint_type}")
return self.results(query, run_manager=run_manager.get_child(), **kwargs)