estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

improve: generalize vector factory classes and vector type (#5033)

Browse Source
This commit is contained in:
Bowen Liang
2024-06-08 22:29:24 +08:00
committed by GitHub
parent 3b62ab564a
commit bdad993901
12 changed files with 343 additions and 233 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
api/controllers/console/datasets/datasets.py
View File

@@ -15,6 +15,7 @@ from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
from core.indexing_runner import IndexingRunner
from core.model_runtime.entities.model_entities import ModelType
from core.provider_manager import ProviderManager
from core.rag.datasource.vdb.vector_type import VectorType
from core.rag.extractor.entity.extract_setting import ExtractSetting
from extensions.ext_database import db
from fields.app_fields import related_app_list
@@ -476,20 +477,22 @@ class DatasetRetrievalSettingApi(Resource):
@account_initialization_required
def get(self):
vector_type = current_app.config['VECTOR_STORE']
if vector_type in {"milvus", "relyt", "pgvector", "pgvecto_rs", 'tidb_vector'}:
return {
'retrieval_method': [
'semantic_search'
]
}
elif vector_type in {"qdrant", "weaviate"}:
return {
'retrieval_method': [
'semantic_search', 'full_text_search', 'hybrid_search'
]
}
else:
raise ValueError("Unsupported vector db type.")
match vector_type:
case VectorType.MILVUS | VectorType.RELYT | VectorType.PGVECTOR | VectorType.TIDB_VECTOR:
return {
'retrieval_method': [
'semantic_search'
]
}
case VectorType.QDRANT | VectorType.WEAVIATE:
return {
'retrieval_method': [
'semantic_search', 'full_text_search', 'hybrid_search'
]
}
case _:
raise ValueError(f"Unsupported vector db type {vector_type}.")
class DatasetRetrievalSettingMockApi(Resource):
@@ -497,20 +500,22 @@ class DatasetRetrievalSettingMockApi(Resource):
@login_required
@account_initialization_required
def get(self, vector_type):
if vector_type in {'milvus', 'relyt', 'pgvector', 'tidb_vector'}:
return {
'retrieval_method': [
'semantic_search'
]
}
elif vector_type in {'qdrant', 'weaviate'}:
return {
'retrieval_method': [
'semantic_search', 'full_text_search', 'hybrid_search'
]
}
else:
raise ValueError("Unsupported vector db type.")
match vector_type:
case VectorType.MILVUS | VectorType.RELYT | VectorType.PGVECTOR | VectorType.TIDB_VECTOR:
return {
'retrieval_method': [
'semantic_search'
]
}
case VectorType.QDRANT | VectorType.WEAVIATE:
return {
'retrieval_method': [
'semantic_search', 'full_text_search', 'hybrid_search'
]
}
case _:
raise ValueError(f"Unsupported vector db type {vector_type}.")
class DatasetErrorDocs(Resource):
@setup_required