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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279 | class DashScopeCloudIndex(BaseManagedIndex):
"""云平台指数。"""
def __init__(
self,
name: str,
nodes: Optional[List[BaseNode]] = None,
transformations: Optional[List[TransformComponent]] = None,
timeout: int = 60,
workspace_id: Optional[str] = None,
api_key: Optional[str] = None,
base_url: Optional[str] = DASHSCOPE_DEFAULT_BASE_URL,
show_progress: bool = False,
callback_manager: Optional[CallbackManager] = None,
**kwargs: Any,
) -> None:
"""初始化平台索引。"""
self.name = name
self.transformations = transformations or []
if nodes is not None:
raise ValueError(
"DashScopeCloudIndex does not support nodes on initialization"
)
self.workspace_id = workspace_id or os.environ.get("DASHSCOPE_WORKSPACE_ID")
self._api_key = api_key or os.environ.get("DASHSCOPE_API_KEY")
self._base_url = os.environ.get("DASHSCOPE_BASE_URL", None) or base_url
self._headers = {
"Content-Type": "application/json",
"Accept-Encoding": "utf-8",
"X-DashScope-WorkSpace": self.workspace_id,
"Authorization": "Bearer " + self._api_key,
"X-DashScope-OpenAPISource": "CloudSDK",
}
self._timeout = timeout
self._show_progress = show_progress
self._service_context = None
self._callback_manager = callback_manager or Settings.callback_manager
@classmethod
def from_documents( # type: ignore
cls: Type["DashScopeCloudIndex"],
documents: List[Document],
name: str,
transformations: Optional[List[TransformComponent]] = None,
workspace_id: Optional[str] = None,
api_key: Optional[str] = None,
base_url: Optional[str] = None,
timeout: int = 60,
verbose: bool = True,
**kwargs: Any,
) -> "DashScopeCloudIndex":
"""从一系列文档中构建一个DashScope索引。"""
pipeline_create = get_pipeline_create(
name, transformations or default_transformations(), documents
)
workspace_id = workspace_id or os.environ.get("DASHSCOPE_WORKSPACE_ID")
api_key = api_key or os.environ.get("DASHSCOPE_API_KEY")
base_url = (
base_url
or os.environ.get("DASHSCOPE_BASE_URL", None)
or DASHSCOPE_DEFAULT_BASE_URL
)
headers = {
"Content-Type": "application/json",
"Accept-Encoding": "utf-8",
"X-DashScope-WorkSpace": workspace_id,
"Authorization": "Bearer " + api_key,
"X-DashScope-OpenAPISource": "CloudSDK",
}
response = requests.put(
base_url + UPSERT_PIPELINE_ENDPOINT,
data=json.dumps(pipeline_create),
headers=headers,
)
response_text = response.json()
pipeline_id = response_text.get("id", None)
if response_text.get("code", "") != Status.SUCCESS.value or pipeline_id is None:
raise ValueError(
f"Failed to create index: {response_text.get('message', '')}\n{response_text}"
)
if verbose:
print(f"Starting creating index {name}, pipeline_id: {pipeline_id}")
response = requests.post(
base_url + START_PIPELINE_ENDPOINT.format(pipeline_id=pipeline_id),
headers=headers,
)
response_text = response.json()
ingestion_id = response_text.get("ingestionId", None)
if (
response_text.get("code", "") != Status.SUCCESS.value
or ingestion_id is None
):
raise ValueError(
f"Failed to start ingestion: {response_text.get('message', '')}\n{response_text}"
)
if verbose:
print(f"Starting ingestion for index {name}, ingestion_id: {ingestion_id}")
ingestion_status, failed_docs = run_ingestion(
base_url
+ CHECK_INGESTION_ENDPOINT.format(
pipeline_id=pipeline_id, ingestion_id=ingestion_id
),
headers,
verbose,
)
if verbose:
print(f"ingestion_status {ingestion_status}")
print(f"failed_docs: {failed_docs}")
if ingestion_status == "FAILED":
print("Index {name} created failed!")
return None
if verbose:
print(f"Index {name} created successfully!")
return cls(
name,
transformations=transformations,
workspace_id=workspace_id,
api_key=api_key,
base_url=base_url,
timeout=timeout,
**kwargs,
)
def as_retriever(self, **kwargs: Any) -> BaseRetriever:
"""返回此托管索引的Retriever。"""
from llama_index.indices.managed.dashscope.retriever import (
DashScopeCloudRetriever,
)
return DashScopeCloudRetriever(
self.name,
**kwargs,
)
def as_query_engine(self, **kwargs: Any) -> BaseQueryEngine:
from llama_index.core.query_engine.retriever_query_engine import (
RetrieverQueryEngine,
)
kwargs["retriever"] = self.as_retriever(**kwargs)
return RetrieverQueryEngine.from_args(**kwargs)
def _insert(
self,
documents: List[Document],
transformations: Optional[List[TransformComponent]] = None,
verbose: bool = True,
**insert_kwargs: Any,
) -> None:
"""插入一组文档（每个文档都是一个节点）。"""
pipeline_id = get_pipeline_id(
self._base_url + PIPELINE_SIMPLE_ENDPOINT,
self._headers,
{"pipeline_name": self.name},
)
doc_insert = get_doc_insert(
transformations or default_transformations(),
documents,
)
response = requests.put(
self._base_url + INSERT_DOC_ENDPOINT.format(pipeline_id=pipeline_id),
data=json.dumps(doc_insert),
headers=self._headers,
)
response_text = response.json()
ingestion_id = response_text.get("ingestionId", None)
if (
response_text.get("code", "") != Status.SUCCESS.value
or ingestion_id is None
):
raise ValueError(
f"Failed to insert documents: {response_text.get('message', '')}\n{response_text}"
)
ingestion_status, failed_docs = run_ingestion(
self._base_url
+ CHECK_INGESTION_ENDPOINT.format(
pipeline_id=pipeline_id, ingestion_id=ingestion_id
),
self._headers,
verbose,
)
if verbose:
print(f"ingestion_status {ingestion_status}")
print(f"failed_docs: {failed_docs}")
def delete_ref_doc(
self,
ref_doc_ids: Union[str, List[str]],
verbose: bool = True,
**delete_kwargs: Any,
) -> None:
"""删除索引中的文档。"""
if isinstance(ref_doc_ids, str):
ref_doc_ids = [ref_doc_ids]
pipeline_id = get_pipeline_id(
self._base_url + PIPELINE_SIMPLE_ENDPOINT,
self._headers,
{"pipeline_name": self.name},
)
doc_delete = get_doc_delete(ref_doc_ids)
response = requests.post(
self._base_url + DELETE_DOC_ENDPOINT.format(pipeline_id=pipeline_id),
json=doc_delete,
headers=self._headers,
)
response_text = response.json()
if response_text.get("code", "") != Status.SUCCESS.value:
raise ValueError(
f"Failed to delete documents: {response_text.get('message', '')}\n{response_text}"
)
if verbose:
print(f"Delete documents {ref_doc_ids} successfully!")
def update_ref_doc(self, document: Document, **update_kwargs: Any) -> None:
"""更新文档及其对应的节点。"""
raise NotImplementedError("update_ref_doc not implemented.")
|