You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/langchain/retrievers/chatgpt_plugin_retriever.py

70 lines
2.1 KiB
Python

from __future__ import annotations
from typing import List
import aiohttp
import requests
from pydantic import BaseModel
from langchain.schema import BaseRetriever, Document
class ChatGPTPluginRetriever(BaseRetriever, BaseModel):
url: str
bearer_token: str
top_k: int = 3
filter: dict | None = None
aiosession: aiohttp.ClientSession | None = None
class Config:
"""Configuration for this pydantic object."""
arbitrary_types_allowed = True
def get_relevant_documents(self, query: str) -> List[Document]:
url, json, headers = self._create_request(query)
response = requests.post(url, json=json, headers=headers)
results = response.json()["results"][0]["results"]
docs = []
for d in results:
content = d.pop("text")
docs.append(Document(page_content=content, metadata=d))
return docs
async def aget_relevant_documents(self, query: str) -> List[Document]:
url, json, headers = self._create_request(query)
if not self.aiosession:
async with aiohttp.ClientSession() as session:
async with session.post(url, headers=headers, json=json) as response:
res = await response.json()
else:
async with self.aiosession.post(
url, headers=headers, json=json
) as response:
res = await response.json()
results = res["results"][0]["results"]
docs = []
for d in results:
content = d.pop("text")
docs.append(Document(page_content=content, metadata=d))
return docs
def _create_request(self, query: str) -> tuple[str, dict, dict]:
url = f"{self.url}/query"
json = {
"queries": [
{
"query": query,
"filter": self.filter,
"top_k": self.top_k,
}
]
}
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {self.bearer_token}",
}
return url, json, headers