indexify 0.0.27__tar.gz → 0.0.29__tar.gz

{indexify-0.0.27 → indexify-0.0.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: indexify
-Version: 0.0.27
+Version: 0.0.29
 Summary: Python Client for Indexify
 Home-page: https://github.com/tensorlakeai/indexify
 License: Apache 2.0

{indexify-0.0.27 → indexify-0.0.29}/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-0.0.27 → indexify-0.0.29}/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,
@@ -622,7 +648,8 @@ class IndexifyClient:
             json=req,
             headers={"Content-Type": "application/json"},
         )
-        return response.json()
+        response.raise_for_status()
+        return response.json()["content_id"]
 
     def wait_for_extraction(self, content_ids: Union[str, List[str]]):
         """

indexify-0.0.29/indexify/data_containers.py

@@ -0,0 +1,37 @@
+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:
+    text: str
+    metadata: dict[str, any] = field(default_factory=dict)
+    score: float = 0.0
+
+    def to_dict(self):
+        return {"text": self.text, "metadata": self.metadata}
+
+
+@dataclass
+class SearchResult:
+    results: List[TextChunk]

{indexify-0.0.27 → indexify-0.0.29}/indexify/extraction_policy.py

@@ -33,11 +33,13 @@ class ExtractionPolicy:
 class ExtractionGraph:
     id: str
     name: str
+    description: str
     extraction_policies: List[ExtractionPolicy]
 
     @classmethod
     def from_dict(cls, json: dict):
         json["id"] = json.get("id", None)
+        json["description"] = json.get("description", None)
         if "namespace" in json.keys():
             json.pop("namespace")
         return ExtractionGraph(**json)
@@ -47,6 +49,11 @@ class ExtractionGraph:
         import yaml
 
         return ExtractionGraph.from_dict(yaml.load(spec, Loader=yaml.FullLoader))
+    
+    @staticmethod
+    def from_yaml_file(path: str):
+        with open(path, "r") as f:
+            return ExtractionGraph.from_yaml(f.read())
 
     def to_dict(self) -> dict:
         filtered_dict = {k: v for k, v in asdict(self).items() if v is not None}

{indexify-0.0.27 → indexify-0.0.29}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "indexify"
-version = "0.0.27"
+version = "0.0.29"
 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"

indexify-0.0.27/indexify/data_containers.py

@@ -1,18 +0,0 @@
-from enum import Enum
-from typing import List
-from dataclasses import dataclass, field
-
-
-@dataclass
-class TextChunk:
-    text: str
-    metadata: dict[str, any] = field(default_factory=dict)
-    score: float = 0.0
-
-    def to_dict(self):
-        return {"text": self.text, "metadata": self.metadata}
-
-
-@dataclass
-class SearchResult:
-    results: List[TextChunk]