davidkhala.ai 0.1.1__tar.gz → 0.1.3__tar.gz

{davidkhala_ai-0.1.1 → davidkhala_ai-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: davidkhala.ai
-Version: 0.1.1
+Version: 0.1.3
 Summary: misc AI modules
 Requires-Python: >=3.13
 Provides-Extra: ali

{davidkhala_ai-0.1.1 → davidkhala_ai-0.1.3}/davidkhala/ai/agent/dify/knowledge.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import os
 from pathlib import Path
-from typing import Iterable, TypedDict, Callable
+from typing import Iterable, TypedDict, Callable, Any, Optional
 from urllib.parse import urlparse
 
 import requests
@@ -41,14 +41,16 @@ class Iterator(Iterable):
     def __iter__(self):
         return self
 
-    def __init__(self, get_fn: Callable, r):
+    def __init__(self, get_fn: Callable[[int, int], Any], r: Optional[dict]):
         self.response = r
         self.fn = get_fn
 
     def __next__(self):
         if self.response and not self.response['has_more']:
             raise StopIteration
-        self.response = self.fn()
+        page = 1 if not self.response else self.response['page'] + 1
+        limit = None if not self.response else self.response['limit']
+        self.response = self.fn(page, limit)
         return self.response['data']
 
 
@@ -81,15 +83,19 @@ class Dataset(API):
     def __init__(self, api_key: str, base_url="https://api.dify.ai/v1"):
         super().__init__(api_key, f"{base_url}/datasets")
 
-    def list(self):
-        return self.request(self.base_url, "GET")
+    def paginate_datasets(self, page=1, size=20):
+        r = self.request(self.base_url, "GET", params={
+            'page': page,
+            'limit': size,
+        })
+        return r
 
-    def list_all(self) -> Iterable[DatasetDict]:
-        return Iterator(self.list, None)
+    def list_datasets(self) -> Iterable[list[DatasetDict]]:
+        return Iterator(self.paginate_datasets, None)
 
     @property
     def ids(self):
-        for sub_list in self.list_all():
+        for sub_list in self.list_datasets():
             for dataset in sub_list:
                 yield dataset['id']
 
@@ -129,11 +135,14 @@ class Dataset(API):
             r = self.on_response(r)
             return r['document']
 
-        def list(self):
-            return self.request(f"{self.base_url}/documents", "GET")
+        def paginate_documents(self, page=1, size=20):
+            return self.request(f"{self.base_url}/documents", "GET", params={
+                'page': page,
+                'limit': size
+            })
 
-        def list_documents(self) -> Iterable[DocumentDict]:
-            return Iterator(self.list, None)
+        def list_documents(self) -> Iterable[list[DocumentDict]]:
+            return Iterator(self.paginate_documents, None)
 
         def has_document(self, name) -> bool:
             return any(name == item['name'] for row in self.list_documents() for item in row)
@@ -142,15 +151,21 @@ class Dataset(API):
 class Document(API):
     def __init__(self, d: Dataset.Instance, document_id: str):
         super().__init__(d.api_key, f"{d.base_url}/documents/{document_id}")
-
-    def get(self):
-        return self.request(self.base_url, "GET")
-
-    def exist(self):
         try:
             self.get()
-            return True
+            self.exist = True
         except requests.exceptions.HTTPError as e:
             if e.response.status_code == 404:
-                return False
-            raise e
+                self.exist = False
+            else:
+                raise e
+
+    def get(self):
+        return self.request(self.base_url, "GET")
+    def paginate_chunks(self, page=1, size=20):
+        return self.request(f"{self.base_url}/segments", "GET", params={
+            'page':page,
+            'limit':size
+        })
+    def list_chunks(self)->Iterable[list]: # TODO ChunkDict
+        return Iterator(self.paginate_chunks, None)

{davidkhala_ai-0.1.1 → davidkhala_ai-0.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "davidkhala.ai"
-version = "0.1.1"
+version = "0.1.3"
 description = "misc AI modules"
 readme = "README.md"
 requires-python = ">=3.13"

davidkhala_ai-0.1.1/davidkhala/ai/agent/dify/__init__.py

@@ -1,9 +0,0 @@
-from datetime import datetime
-
-
-def with_datetime(filename:str):
-    if ' ' in filename:
-        raise ValueError(f"Filename '{filename}' should not contain spaces.")
-    return f"{datetime.now().strftime("%Y%m%d_%H%M%S")}.{filename}"
-
-