davidkhala.ai 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- davidkhala/ai/agent/dify/__init__.py +0 -9
- davidkhala/ai/agent/dify/knowledge.py +42 -3
- {davidkhala_ai-0.1.2.dist-info → davidkhala_ai-0.1.4.dist-info}/METADATA +1 -1
- {davidkhala_ai-0.1.2.dist-info → davidkhala_ai-0.1.4.dist-info}/RECORD +5 -5
- {davidkhala_ai-0.1.2.dist-info → davidkhala_ai-0.1.4.dist-info}/WHEEL +0 -0
|
@@ -141,13 +141,40 @@ class Dataset(API):
|
|
|
141
141
|
'limit': size
|
|
142
142
|
})
|
|
143
143
|
|
|
144
|
-
def list_documents(self) -> Iterable[
|
|
145
|
-
|
|
144
|
+
def list_documents(self) -> Iterable[DocumentDict]:
|
|
145
|
+
for document_batch in Iterator(self.paginate_documents, None):
|
|
146
|
+
for document in document_batch:
|
|
147
|
+
yield document
|
|
146
148
|
|
|
147
149
|
def has_document(self, name) -> bool:
|
|
148
150
|
return any(name == item['name'] for row in self.list_documents() for item in row)
|
|
149
151
|
|
|
150
152
|
|
|
153
|
+
class ChunkDict(TypedDict):
|
|
154
|
+
id: str
|
|
155
|
+
position: int
|
|
156
|
+
document_id: str
|
|
157
|
+
content: str
|
|
158
|
+
sign_content: str # trimmed version of content
|
|
159
|
+
answer: Optional[str] # only used in QA chunk
|
|
160
|
+
word_count: int
|
|
161
|
+
tokens: int
|
|
162
|
+
keywords: Optional[list[str]]
|
|
163
|
+
index_node_id: str # chunk 在向量索引中的节点 ID
|
|
164
|
+
index_node_hash: str # hash of sign_content
|
|
165
|
+
hit_count: int
|
|
166
|
+
enabled: bool
|
|
167
|
+
status: str # 'completed'
|
|
168
|
+
created_at: int # timestamp
|
|
169
|
+
updated_at: int # timestamp
|
|
170
|
+
completed_at: int # timestamp
|
|
171
|
+
created_by: str # user id
|
|
172
|
+
child_chunks: list
|
|
173
|
+
error: Optional
|
|
174
|
+
stopped_at: Optional[int] # timestamp
|
|
175
|
+
disabled_at: Optional[int] # timestamp
|
|
176
|
+
|
|
177
|
+
|
|
151
178
|
class Document(API):
|
|
152
179
|
def __init__(self, d: Dataset.Instance, document_id: str):
|
|
153
180
|
super().__init__(d.api_key, f"{d.base_url}/documents/{document_id}")
|
|
@@ -157,7 +184,19 @@ class Document(API):
|
|
|
157
184
|
except requests.exceptions.HTTPError as e:
|
|
158
185
|
if e.response.status_code == 404:
|
|
159
186
|
self.exist = False
|
|
160
|
-
|
|
187
|
+
else:
|
|
188
|
+
raise e
|
|
161
189
|
|
|
162
190
|
def get(self):
|
|
163
191
|
return self.request(self.base_url, "GET")
|
|
192
|
+
|
|
193
|
+
def paginate_chunks(self, page=1, size=20):
|
|
194
|
+
return self.request(f"{self.base_url}/segments", "GET", params={
|
|
195
|
+
'page': page,
|
|
196
|
+
'limit': size
|
|
197
|
+
})
|
|
198
|
+
|
|
199
|
+
def list_chunks(self) -> Iterable[ChunkDict]:
|
|
200
|
+
for chunk_batch in Iterator(self.paginate_chunks, None):
|
|
201
|
+
for chunk in chunk_batch:
|
|
202
|
+
yield chunk
|
|
@@ -5,9 +5,9 @@ davidkhala/ai/agent/README.md,sha256=kIPsx3gOjrpOw7w2qhNEALuCEQkuh4nYp6uBnijdvHE
|
|
|
5
5
|
davidkhala/ai/agent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
6
6
|
davidkhala/ai/agent/langgraph.py,sha256=jrc_Yvgo7eJjd3y5UJn0t1FzpnObDGYscwgsuVl2O_I,1052
|
|
7
7
|
davidkhala/ai/agent/ragflow.py,sha256=UaK31us6V0NhAPCthGo07rQsm72vlR-McmihC_NDe1g,273
|
|
8
|
-
davidkhala/ai/agent/dify/__init__.py,sha256=
|
|
8
|
+
davidkhala/ai/agent/dify/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
9
9
|
davidkhala/ai/agent/dify/base.py,sha256=V4BIhG9oTg9ayPZnYVxxA1Yobl2C4ukSWEOu2U_l0Tw,259
|
|
10
|
-
davidkhala/ai/agent/dify/knowledge.py,sha256=
|
|
10
|
+
davidkhala/ai/agent/dify/knowledge.py,sha256=GFRKbudSoTR6BX7FiMg6a0uTepkm1X1N7kwqowDyRg4,6214
|
|
11
11
|
davidkhala/ai/ali/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
12
12
|
davidkhala/ai/ali/dashscope.py,sha256=SZIzRhVHlLx3s5I2RNUh2-u8OoSdrbvoN5e1k8Mh8N0,1943
|
|
13
13
|
davidkhala/ai/api/__init__.py,sha256=q2Ro5nhW5kJx2CYR1MRVamjTT5tTexPZwhrS2hwAvFM,1319
|
|
@@ -22,6 +22,6 @@ davidkhala/ai/huggingface/inference.py,sha256=bYN0PtLF2CaIHzdTP4LaTALJhcawvuLnLR
|
|
|
22
22
|
davidkhala/ai/openai/__init__.py,sha256=GXzWaw2ER3YFGHG6TPD9SmAHV6Tpsnqxj6tXlaWsrko,1897
|
|
23
23
|
davidkhala/ai/openai/azure.py,sha256=QR1uZj8qAyhpCjo3Ks5zNV8GfOp3-enyZs6fBvV-MkA,1110
|
|
24
24
|
davidkhala/ai/openai/native.py,sha256=MB0nDnzCOj_M42RMhdK3HTMVnxGnwpLT2GeLwSrepwI,704
|
|
25
|
-
davidkhala_ai-0.1.
|
|
26
|
-
davidkhala_ai-0.1.
|
|
27
|
-
davidkhala_ai-0.1.
|
|
25
|
+
davidkhala_ai-0.1.4.dist-info/METADATA,sha256=RvHa05xsA2__WejkH8lp5vYqPThvI2Ymj1iqk_5KK4M,1098
|
|
26
|
+
davidkhala_ai-0.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
|
27
|
+
davidkhala_ai-0.1.4.dist-info/RECORD,,
|
|
File without changes
|