Spaces:
Runtime error
Runtime error
File size: 4,861 Bytes
ed4d993 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
import os
import re
from typing import Any, Dict, List, Literal, Optional
from langchain_core.callbacks import (
AsyncCallbackManagerForRetrieverRun,
CallbackManagerForRetrieverRun,
)
from langchain_core.documents import Document
from langchain_core.retrievers import BaseRetriever
class AskNewsRetriever(BaseRetriever):
"""AskNews retriever."""
k: int = 10
offset: int = 0
start_timestamp: Optional[int] = None
end_timestamp: Optional[int] = None
method: Literal["nl", "kw"] = "nl"
categories: List[
Literal[
"All",
"Business",
"Crime",
"Politics",
"Science",
"Sports",
"Technology",
"Military",
"Health",
"Entertainment",
"Finance",
"Culture",
"Climate",
"Environment",
"World",
]
] = ["All"]
historical: bool = False
similarity_score_threshold: float = 0.5
kwargs: Optional[Dict[str, Any]] = {}
client_id: Optional[str] = None
client_secret: Optional[str] = None
def _get_relevant_documents(
self, query: str, *, run_manager: CallbackManagerForRetrieverRun
) -> List[Document]:
"""Get documents relevant to a query.
Args:
query: String to find relevant documents for
run_manager: The callbacks handler to use
Returns:
List of relevant documents
"""
try:
from asknews_sdk import AskNewsSDK
except ImportError:
raise ImportError(
"AskNews python package not found. "
"Please install it with `pip install asknews`."
)
an_client = AskNewsSDK(
client_id=self.client_id or os.environ["ASKNEWS_CLIENT_ID"],
client_secret=self.client_secret or os.environ["ASKNEWS_CLIENT_SECRET"],
scopes=["news"],
)
response = an_client.news.search_news(
query=query,
n_articles=self.k,
start_timestamp=self.start_timestamp,
end_timestamp=self.end_timestamp,
method=self.method,
categories=self.categories,
historical=self.historical,
similarity_score_threshold=self.similarity_score_threshold,
offset=self.offset,
doc_start_delimiter="<doc>",
doc_end_delimiter="</doc>",
return_type="both",
**self.kwargs,
)
return self._extract_documents(response)
async def _aget_relevant_documents(
self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
) -> List[Document]:
"""Asynchronously get documents relevant to a query.
Args:
query: String to find relevant documents for
run_manager: The callbacks handler to use
Returns:
List of relevant documents
"""
try:
from asknews_sdk import AsyncAskNewsSDK
except ImportError:
raise ImportError(
"AskNews python package not found. "
"Please install it with `pip install asknews`."
)
an_client = AsyncAskNewsSDK(
client_id=self.client_id or os.environ["ASKNEWS_CLIENT_ID"],
client_secret=self.client_secret or os.environ["ASKNEWS_CLIENT_SECRET"],
scopes=["news"],
)
response = await an_client.news.search_news(
query=query,
n_articles=self.k,
start_timestamp=self.start_timestamp,
end_timestamp=self.end_timestamp,
method=self.method,
categories=self.categories,
historical=self.historical,
similarity_score_threshold=self.similarity_score_threshold,
offset=self.offset,
return_type="both",
doc_start_delimiter="<doc>",
doc_end_delimiter="</doc>",
**self.kwargs,
)
return self._extract_documents(response)
def _extract_documents(self, response: Any) -> List[Document]:
"""Extract documents from an api response."""
from asknews_sdk.dto.news import SearchResponse
sr: SearchResponse = response
matches = re.findall(r"<doc>(.*?)</doc>", sr.as_string, re.DOTALL)
docs = [
Document(
page_content=matches[i].strip(),
metadata={
"title": sr.as_dicts[i].title,
"source": str(sr.as_dicts[i].article_url)
if sr.as_dicts[i].article_url
else None,
"images": sr.as_dicts[i].image_url,
},
)
for i in range(len(matches))
]
return docs
|