indexify 0.0.28__py3-none-any.whl → 0.0.29__py3-none-any.whl

indexify/__init__.py

@@ -2,10 +2,12 @@ from .index import Index
 from .client import IndexifyClient
 from .extraction_policy import ExtractionGraph
 from .client import IndexifyClient, Document, generate_hash_from_string, generate_unique_hex_id
+from .data_containers import Content
 from .settings import DEFAULT_SERVICE_URL
 
 __all__ = [
     "Index",
+    "Content",
     "Document",
     "IndexifyClient",
     "ExtractionGraph",

indexify/client.py

@@ -10,7 +10,7 @@ from .extraction_policy import ExtractionPolicy, ExtractionGraph
 from .index import Index
 from .utils import json_set_default
 from .error import Error
-from .data_containers import TextChunk
+from .data_containers import TextChunk, Content
 from indexify.exceptions import ApiException
 from dataclasses import dataclass
 from typing import List, Optional, Union, Dict
@@ -153,7 +153,9 @@ class IndexifyClient:
         try:
             response = self._client.request(method, timeout=self._timeout, **kwargs)
             status_code = str(response.status_code)
-            if status_code.startswith("4") or status_code.startswith("5"):
+            if status_code.startswith("4"):
+                raise ApiException("status code: " + status_code + " request args: " + str(kwargs))
+            if status_code.startswith("5"):
                 raise ApiException(response.text)
                 # error = Error.from_tonic_error_string(str(response.url), response.text)
                 # self.__print_additional_error_context(error)
@@ -511,6 +513,30 @@ class IndexifyClient:
             headers={"Content-Type": "application/json"},
         )
         return response.json()["results"]
+    
+    def list_content(self, extraction_graph: str, extraction_policy: str = "", start_id: str="", limit: int=10) -> List[Content]:
+        """
+        List content in the current namespace.
+
+        Args:
+            - extraction_graph (str): extraction graph name
+            - start_index (str): start index for pagination
+            - limit (int): number of items to return
+        """
+        params = {"graph": extraction_graph, "start_id": start_id, "limit": limit}
+        if extraction_policy:
+            params["source"] = extraction_policy
+        else:
+            params["source"] = "ingestion"
+        response = self.get(
+            f"namespaces/{self.namespace}/content",
+            params=params,
+        )
+        content_list = response.json()["content_list"]
+        content = []
+        for item in content_list:
+            content.append(Content.from_dict(item))
+        return content
 
     def upload_file(
         self,

indexify/data_containers.py

@@ -2,6 +2,25 @@ from enum import Enum
 from typing import List
 from dataclasses import dataclass, field
 
+@dataclass
+class Content:
+    id: str
+    parent_id: str
+    labels: dict[str, any]
+    extraction_graph_names: List[str]
+    extraction_policy: str
+    mime_type: str
+
+    @classmethod
+    def from_dict(cls, json: dict):
+        return Content(
+            id=json["id"],
+            parent_id=json["parent_id"],
+            labels=json["labels"],
+            extraction_graph_names=json["extraction_graph_names"],
+            extraction_policy=json["source"],
+            mime_type=json["mime_type"],
+        )
 
 @dataclass
 class TextChunk:

{indexify-0.0.28.dist-info → indexify-0.0.29.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: indexify
-Version: 0.0.28
+Version: 0.0.29
 Summary: Python Client for Indexify
 Home-page: https://github.com/tensorlakeai/indexify
 License: Apache 2.0

{indexify-0.0.28.dist-info → indexify-0.0.29.dist-info}/RECORD

@@ -1,6 +1,6 @@
-indexify/__init__.py,sha256=Y40-Ur_tL7kGGs-reh9BTfEYGe-KyGxgdg-CmoFsXRQ,473
-indexify/client.py,sha256=qECQvvVPvzMDra8OQ-94u7J5ABFWSEmEx_uIEdJ3RiU,22159
-indexify/data_containers.py,sha256=r1wxJPtsmXbyKvb17fqxm-dPjKz51oZ62f8A8Zxls1c,361
+indexify/__init__.py,sha256=xqymbwqaiHiWXFpm7Cll2j-_V1lNQH2EEGlevtCTZK4,525
+indexify/client.py,sha256=14O63O_D1xatnRItS6ecs9juREooYQKelDz0Zc9TSrY,23197
+indexify/data_containers.py,sha256=fIX_rghpojrCUtmZ0grywoq_HWniDgN1mnR7yXDej-Y,874
 indexify/error.py,sha256=3umTeYb0ugtUyehV1ibfvaeACxAONPyWPc-1HRN4d1M,856
 indexify/exceptions.py,sha256=vjd5SPPNFIEW35GorSIodsqvm9RKHQm9kdp8t9gv-WM,111
 indexify/extraction_policy.py,sha256=POluredrBw6DzTN0OyfPLaLFP5-2DoWGRK0V6w68R28,2080
@@ -8,7 +8,7 @@ indexify/extractor.py,sha256=sWFLlXHgEfWlmiKAXN6ytUt_uG7th-XGNHqz-TG39gs,1216
 indexify/index.py,sha256=RvxYhJXEth-GKvqzlMiz5PuN1eIbZk84pt20piA1Gsw,504
 indexify/settings.py,sha256=LSaWZ0ADIVmUv6o6dHWRC3-Ry5uLbCw2sBSg1e_U7UM,99
 indexify/utils.py,sha256=rDN2lrsAs9noJEIjfx6ukmC2SAIyrlUt7QU-kaBjujM,125
-indexify-0.0.28.dist-info/LICENSE.txt,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-indexify-0.0.28.dist-info/METADATA,sha256=3r9wATECrfXFfmI68yU2cUOtrOBR4nT_ajPnag8IdZg,1798
-indexify-0.0.28.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-indexify-0.0.28.dist-info/RECORD,,
+indexify-0.0.29.dist-info/LICENSE.txt,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+indexify-0.0.29.dist-info/METADATA,sha256=c-2NDf8ayGuboLyMkc0tVXACfp9L30QbxQTCARfuFeA,1798
+indexify-0.0.29.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+indexify-0.0.29.dist-info/RECORD,,