mirror of https://github.com/hwchase17/langchain
Rename Databerry to Chaindesk (#7022)
--------- Co-authored-by: Bagatur <baskaryan@gmail.com>pull/7378/head
Georges Petrov
1 year ago
committed by
GitHub
parent
da5b0723d2
commit
ec033ae277
|
Before Width: | Height: | Size: 157 KiB After Width: | Height: | Size: 157 KiB |
@ -1,17 +1,17 @@
|
||||
# Databerry
|
||||
# Chaindesk
|
||||
|
||||
>[Databerry](https://databerry.ai) is an [open source](https://github.com/gmpetrov/databerry) document retrieval platform that helps to connect your personal data with Large Language Models.
|
||||
>[Chaindesk](https://chaindesk.ai) is an [open source](https://github.com/gmpetrov/databerry) document retrieval platform that helps to connect your personal data with Large Language Models.
|
||||
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
We need to sign up for Databerry, create a datastore, add some data and get your datastore api endpoint url.
|
||||
We need the [API Key](https://docs.databerry.ai/api-reference/authentication).
|
||||
We need to sign up for Chaindesk, create a datastore, add some data and get your datastore api endpoint url.
|
||||
We need the [API Key](https://docs.chaindesk.ai/api-reference/authentication).
|
||||
|
||||
## Retriever
|
||||
|
||||
See a [usage example](/docs/modules/data_connection/retrievers/integrations/databerry.html).
|
||||
See a [usage example](/docs/modules/data_connection/retrievers/integrations/chaindesk.html).
|
||||
|
||||
```python
|
||||
from langchain.retrievers import DataberryRetriever
|
||||
from langchain.retrievers import ChaindeskRetriever
|
||||
```
|
||||
@ -0,0 +1,92 @@
|
||||
from typing import Any, List, Optional
|
||||
|
||||
import aiohttp
|
||||
import requests
|
||||
|
||||
from langchain.callbacks.manager import (
|
||||
AsyncCallbackManagerForRetrieverRun,
|
||||
CallbackManagerForRetrieverRun,
|
||||
)
|
||||
from langchain.schema import BaseRetriever, Document
|
||||
|
||||
|
||||
class ChaindeskRetriever(BaseRetriever):
|
||||
"""Retriever that uses the Chaindesk API."""
|
||||
|
||||
datastore_url: str
|
||||
top_k: Optional[int]
|
||||
api_key: Optional[str]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
datastore_url: str,
|
||||
top_k: Optional[int] = None,
|
||||
api_key: Optional[str] = None,
|
||||
):
|
||||
self.datastore_url = datastore_url
|
||||
self.api_key = api_key
|
||||
self.top_k = top_k
|
||||
|
||||
def _get_relevant_documents(
|
||||
self,
|
||||
query: str,
|
||||
*,
|
||||
run_manager: CallbackManagerForRetrieverRun,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
response = requests.post(
|
||||
self.datastore_url,
|
||||
json={
|
||||
"query": query,
|
||||
**({"topK": self.top_k} if self.top_k is not None else {}),
|
||||
},
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
**(
|
||||
{"Authorization": f"Bearer {self.api_key}"}
|
||||
if self.api_key is not None
|
||||
else {}
|
||||
),
|
||||
},
|
||||
)
|
||||
data = response.json()
|
||||
return [
|
||||
Document(
|
||||
page_content=r["text"],
|
||||
metadata={"source": r["source"], "score": r["score"]},
|
||||
)
|
||||
for r in data["results"]
|
||||
]
|
||||
|
||||
async def _aget_relevant_documents(
|
||||
self,
|
||||
query: str,
|
||||
*,
|
||||
run_manager: AsyncCallbackManagerForRetrieverRun,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.request(
|
||||
"POST",
|
||||
self.datastore_url,
|
||||
json={
|
||||
"query": query,
|
||||
**({"topK": self.top_k} if self.top_k is not None else {}),
|
||||
},
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
**(
|
||||
{"Authorization": f"Bearer {self.api_key}"}
|
||||
if self.api_key is not None
|
||||
else {}
|
||||
),
|
||||
},
|
||||
) as response:
|
||||
data = await response.json()
|
||||
return [
|
||||
Document(
|
||||
page_content=r["text"],
|
||||
metadata={"source": r["source"], "score": r["score"]},
|
||||
)
|
||||
for r in data["results"]
|
||||
]
|
||||
Loading…
Reference in New Issue