Spaces:
Sleeping
Sleeping
File size: 3,648 Bytes
47b5f0c |
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 |
from fastapi import Depends, Request
from transformers import AutoModel, AutoModelForMaskedLM, AutoTokenizer
from app.infrastructure.repository.document_handeler_repository import (
DocumentHandelerRepository,
)
from app.modules.denseEmbeddings.denseEmbeddings import DenseEmbeddings
from app.modules.documentHandeler.controllers.document_handeler_controller import (
DocumentHandelerController,
)
from app.modules.documentHandeler.features.createEmbeddings_feature import (
CreateEmbeddingsFeature,
)
from app.modules.documentHandeler.features.deleteDocument_feature import (
DeleteDocumentFeature,
)
from app.modules.documentHandeler.features.getAllChunkedText_feature import (
GetAllChunkedTextFeature,
)
from app.qdrant import QdrantConnectionDb
def get_qdrant_connection_db() -> QdrantConnectionDb:
return QdrantConnectionDb()
def get_document_handeler_repository(
qdrant_connection_db: QdrantConnectionDb = Depends(get_qdrant_connection_db),
):
return DocumentHandelerRepository(qdrant_connection_db)
def get_dense_model(request: Request) -> AutoModel:
return request.scope["state"]["dense_model"]
def get_sparse_model(request: Request) -> AutoModelForMaskedLM:
return request.scope["state"]["sparse_model"]
def get_dense_tokenizer(request: Request) -> AutoTokenizer:
return request.scope["state"]["dense_tokenizer"]
def get_sparse_tokenizer(request: Request) -> AutoTokenizer:
return request.scope["state"]["sparse_tokenizer"]
def get_dense_embeddings(
dense_model: AutoModel = Depends(get_dense_model),
dense_tokenizer: AutoTokenizer = Depends(get_dense_tokenizer),
sparse_model: AutoModelForMaskedLM = Depends(get_sparse_model),
sparse_tokenizer: AutoTokenizer = Depends(get_sparse_tokenizer),
):
return DenseEmbeddings(
dense_model=dense_model,
dense_tokenizer=dense_tokenizer,
sparse_model=sparse_model,
sparse_tokenizer=sparse_tokenizer,
)
def get_all_chunked_text_feature(
document_handeler_repository: DocumentHandelerRepository = Depends(
get_document_handeler_repository
),
):
return GetAllChunkedTextFeature(document_handeler_repository)
def get_create_embeddings_feature(
dense_embeddings: DenseEmbeddings = Depends(get_dense_embeddings),
document_handeler_repository: DocumentHandelerRepository = Depends(
get_document_handeler_repository
),
):
return CreateEmbeddingsFeature(dense_embeddings, document_handeler_repository)
def get_delete_document_feature(
document_handeler_repository: DocumentHandelerRepository = Depends(
get_document_handeler_repository
),
):
return DeleteDocumentFeature(document_handeler_repository)
def get_document_handeler_controller(
delete_document_feature: DeleteDocumentFeature = Depends(
get_delete_document_feature
),
create_embeddings_feature: CreateEmbeddingsFeature = Depends(
get_create_embeddings_feature
),
get_all_chunked_text_feature: GetAllChunkedTextFeature = Depends(
get_all_chunked_text_feature
),
):
return DocumentHandelerController(
delete_document_feature=delete_document_feature,
create_embeddings_feature=create_embeddings_feature,
get_all_chunked_text_feature=get_all_chunked_text_feature,
)
def get_create_embeddings_feature(
dense_embeddings: DenseEmbeddings = Depends(get_dense_embeddings),
document_handeler_repository: DocumentHandelerRepository = Depends(
get_document_handeler_repository
),
):
return CreateEmbeddingsFeature(dense_embeddings, document_handeler_repository)
|