Spaces:
Runtime error
Runtime error
File size: 2,814 Bytes
6628fd9 |
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 |
from llama_index import StorageContext
from typing import List
from abc import abstractmethod, ABC
from llama_index import Document
from core.lifecycle import Lifecycle
from llama.data_loader import DirectoryLoader
from llama.service_context import ServiceContextManager
class StorageContextManager(Lifecycle, ABC):
_storage_context: StorageContext
@property
def storage_context(self) -> StorageContext:
return self._storage_context
@storage_context.setter
def storage_context(self, value: StorageContext) -> None:
self._storage_context = value
@abstractmethod
def _is_embedding_ready(self) -> bool:
pass
@abstractmethod
def _load_data(self) -> List[Document]:
pass
@abstractmethod
def _indexing_embedding(self, docs: List[Document]) -> StorageContext:
pass
@abstractmethod
def _load_storage_context(self) -> StorageContext:
pass
@abstractmethod
def _persist(self) -> None:
pass
def do_init(self) -> None:
if self._is_embedding_ready():
self.storage_context = self._load_storage_context()
else:
self.storage_context = self._indexing_embedding(self._load_data())
self._persist()
def do_dispose(self) -> None:
if self._is_embedding_ready():
self._persist()
def do_start(self) -> None:
# self.logger.info("[do_start]%", self.storage_context.__str__())
pass
def do_stop(self) -> None:
# self.logger.info("[do_stop]%", self.storage_context.__str__())
pass
class LocalStorageContextManager(StorageContextManager):
def __init__(
self,
service_context_manager: ServiceContextManager,
dataset_path: str = "./dataset",
) -> None:
super().__init__()
self._dataset_path = dataset_path
self._service_context_manager = service_context_manager
def _is_embedding_ready(self) -> bool:
from llama.utils import is_local_storage_files_ready
return is_local_storage_files_ready(self._dataset_path)
def _load_data(self) -> List[Document]:
return DirectoryLoader(
dir_path="./docs/faq", required_exts=[".pdf"], exclude_glob=[]
).load()
def _indexing_embedding(self, docs: List[Document]) -> StorageContext:
from llama_index import GPTVectorStoreIndex
index = GPTVectorStoreIndex.from_documents(
docs, service_context=self._service_context_manager.get_service_context()
)
return index.storage_context
def _load_storage_context(self) -> StorageContext:
return StorageContext.from_defaults(persist_dir=self._dataset_path)
def _persist(self) -> None:
self.storage_context.persist(self._dataset_path)
|