indexify 0.0.24__tar.gz → 0.0.26__tar.gz

{indexify-0.0.24 → indexify-0.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: indexify
-Version: 0.0.24
+Version: 0.0.26
 Summary: Python Client for Indexify
 Home-page: https://github.com/tensorlakeai/indexify
 License: Apache 2.0

{indexify-0.0.24 → indexify-0.0.26}/indexify/client.py

@@ -4,7 +4,7 @@ import uuid
 import hashlib
 import json
 from collections import namedtuple
-from .settings import DEFAULT_SERVICE_URL
+from .settings import DEFAULT_SERVICE_URL, DEFAULT_SERVICE_URL_HTTPS
 from .extractor import Extractor
 from .extraction_policy import ExtractionPolicy, ExtractionGraph
 from .index import Index
@@ -108,7 +108,7 @@ class IndexifyClient:
         cert_path: str,
         key_path: str,
         ca_bundle_path: Optional[str] = None,
-        service_url: str = DEFAULT_SERVICE_URL,
+        service_url: str = DEFAULT_SERVICE_URL_HTTPS,
         *args,
         **kwargs,
     ) -> "IndexifyClient":
@@ -535,7 +535,7 @@ class IndexifyClient:
             response = self.post(
                 f"namespaces/{self.namespace}/upload_file",
                 files={"file": f},
-                data=labels,
+                data={"labels": json.dumps(labels)},
                 params=params,
             )
             response_json = response.json()
@@ -560,7 +560,7 @@ class IndexifyClient:
         )
         return response.json()
 
-    def get_extracted_content(self, content_id: str, level: int = 0):
+    def get_extracted_content(self, content_id: str, graph_name: str, policy_name: str):
         """
         Get list of child for a given content id and their content up to the specified level.
 
@@ -570,20 +570,13 @@ class IndexifyClient:
         """
         content_tree = self.get_content_tree(content_id)
         child_list = []
-
-        def traverse_content(parent_id, current_level):
-            if current_level > level:
-                return
-
-            for item in content_tree["content_tree_metadata"]:
-                if item["parent_id"] == parent_id:
-                    child_id = item["id"]
-                    content = self.download_content(child_id)
-                    child_list.append({"id": child_id, "content": content})
-
-                    traverse_content(child_id, current_level + 1)
-
-        traverse_content(content_id, 0)
+        for item in content_tree["content_tree_metadata"]:
+            if (
+                graph_name in item["extraction_graph_names"]
+                and item["source"] == policy_name
+            ):
+                content = self.download_content(item["id"])
+                child_list.append({"id": item["id"], "content": content})
 
         return child_list
 

{indexify-0.0.24 → indexify-0.0.26}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "indexify"
-version = "0.0.24"
+version = "0.0.26"
 description = "Python Client for Indexify"
 authors = ["Diptanu Gon Choudhury <diptanuc@gmail.com>", "Lucas Jackson <lucas@tensorlake.ai>", "Vijay Parthasarathy <vijay2win@gmail.com>"]
 license = "Apache 2.0"