feat: add jina_search as new websearch provider

This commit is contained in:
Yash-1511 2024-06-22 20:06:15 +05:30
parent 9e4dd4b86f
commit 7c9fb9199e
3 changed files with 46 additions and 1 deletions

View File

@ -74,6 +74,7 @@ from apps.rag.search.serpstack import search_serpstack
from apps.rag.search.serply import search_serply
from apps.rag.search.duckduckgo import search_duckduckgo
from apps.rag.search.tavily import search_tavily
from apps.rag.search.jina_search import search_jina
from utils.misc import (
calculate_sha256,
@ -841,6 +842,8 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
)
else:
raise Exception("No TAVILY_API_KEY found in environment variables")
elif engine == "jina":
return search_jina(query, app.state.config.RAG_WEB_SEARCH_RESULT_COUNT)
else:
raise Exception("No search engine API key found in environment variables")

View File

@ -0,0 +1,41 @@
import logging
import requests
from yarl import URL
from apps.rag.search.main import SearchResult
from config import SRC_LOG_LEVELS
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_jina(query: str, count: int) -> list[SearchResult]:
"""
Search using Jina's Search API and return the results as a list of SearchResult objects.
Args:
query (str): The query to search for
count (int): The number of results to return
Returns:
List[SearchResult]: A list of search results
"""
jina_search_endpoint = "https://s.jina.ai/"
headers = {
"Accept": "application/json",
}
url = str(URL(jina_search_endpoint + query))
response = requests.get(url, headers=headers)
response.raise_for_status()
data = response.json()
results = []
for result in data["data"][:count]:
results.append(
SearchResult(
link=result["url"],
title=result.get("title"),
snippet=result.get("content"),
)
)
return results

View File

@ -19,7 +19,8 @@
'serper',
'serply',
'duckduckgo',
'tavily'
'tavily',
'jina'
];
let youtubeLanguage = 'en';