Spaces:
Runtime error
Runtime error
File size: 4,642 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 |
from __future__ import annotations
import json
import logging
from typing import (
TYPE_CHECKING,
Any,
AsyncIterator,
Callable,
Dict,
Iterator,
List,
Optional,
)
from langchain_core._api.deprecation import deprecated
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
from langchain_community.utilities.astradb import _AstraDBEnvironment
if TYPE_CHECKING:
from astrapy.db import AstraDB, AsyncAstraDB
logger = logging.getLogger(__name__)
@deprecated(
since="0.0.29",
removal="0.3.0",
alternative_import="langchain_astradb.AstraDBLoader",
)
class AstraDBLoader(BaseLoader):
def __init__(
self,
collection_name: str,
*,
token: Optional[str] = None,
api_endpoint: Optional[str] = None,
astra_db_client: Optional[AstraDB] = None,
async_astra_db_client: Optional[AsyncAstraDB] = None,
namespace: Optional[str] = None,
filter_criteria: Optional[Dict[str, Any]] = None,
projection: Optional[Dict[str, Any]] = None,
find_options: Optional[Dict[str, Any]] = None,
nb_prefetched: int = 1000,
extraction_function: Callable[[Dict], str] = json.dumps,
) -> None:
"""Load DataStax Astra DB documents.
Args:
collection_name: name of the Astra DB collection to use.
token: API token for Astra DB usage.
api_endpoint: full URL to the API endpoint,
such as `https://<DB-ID>-us-east1.apps.astra.datastax.com`.
astra_db_client: *alternative to token+api_endpoint*,
you can pass an already-created 'astrapy.db.AstraDB' instance.
async_astra_db_client: *alternative to token+api_endpoint*,
you can pass an already-created 'astrapy.db.AsyncAstraDB' instance.
namespace: namespace (aka keyspace) where the
collection is. Defaults to the database's "default namespace".
filter_criteria: Criteria to filter documents.
projection: Specifies the fields to return.
find_options: Additional options for the query.
nb_prefetched: Max number of documents to pre-fetch. Defaults to 1000.
extraction_function: Function applied to collection documents to create
the `page_content` of the LangChain Document. Defaults to `json.dumps`.
"""
astra_env = _AstraDBEnvironment(
token=token,
api_endpoint=api_endpoint,
astra_db_client=astra_db_client,
async_astra_db_client=async_astra_db_client,
namespace=namespace,
)
self.astra_env = astra_env
self.collection = astra_env.astra_db.collection(collection_name)
self.collection_name = collection_name
self.filter = filter_criteria
self.projection = projection
self.find_options = find_options or {}
self.nb_prefetched = nb_prefetched
self.extraction_function = extraction_function
def lazy_load(self) -> Iterator[Document]:
for doc in self.collection.paginated_find(
filter=self.filter,
options=self.find_options,
projection=self.projection,
sort=None,
prefetched=self.nb_prefetched,
):
yield Document(
page_content=self.extraction_function(doc),
metadata={
"namespace": self.collection.astra_db.namespace,
"api_endpoint": self.collection.astra_db.base_url,
"collection": self.collection_name,
},
)
async def aload(self) -> List[Document]:
"""Load data into Document objects."""
return [doc async for doc in self.alazy_load()]
async def alazy_load(self) -> AsyncIterator[Document]:
async_collection = await self.astra_env.async_astra_db.collection(
self.collection_name
)
async for doc in async_collection.paginated_find(
filter=self.filter,
options=self.find_options,
projection=self.projection,
sort=None,
prefetched=self.nb_prefetched,
):
yield Document(
page_content=self.extraction_function(doc),
metadata={
"namespace": async_collection.astra_db.namespace,
"api_endpoint": async_collection.astra_db.base_url,
"collection": self.collection_name,
},
)
|