indexify 0.0.8__tar.gz → 0.0.10__tar.gz

{indexify-0.0.8 → indexify-0.0.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: indexify
-Version: 0.0.8
+Version: 0.0.10
 Summary: Python Client for Indexify
 Home-page: https://github.com/tensorlakeai/indexify
 License: Apache 2.0

{indexify-0.0.8 → indexify-0.0.10}/indexify/__init__.py

@@ -1,12 +1,13 @@
 from .index import Index
 from .client import IndexifyClient
-from .extractor_binding import ExtractorBinding
-from .data_containers import TextChunk
+from .extraction_policy import ExtractionPolicy
+from .client import IndexifyClient, Document
 from .settings import DEFAULT_SERVICE_URL
 
 __all__ = [
     "Index",
+    "Document",
     "IndexifyClient",
-    "ExtractorBinding",
+    "ExtractionPolicy",
     "DEFAULT_SERVICE_URL",
 ]

{indexify-0.0.8 → indexify-0.0.10}/indexify/client.py

@@ -3,7 +3,7 @@ import json
 from collections import namedtuple
 from .settings import DEFAULT_SERVICE_URL
 from .extractor import Extractor
-from .extractor_binding import ExtractorBinding
+from .extraction_policy import ExtractionPolicy
 from .index import Index
 from .utils import json_set_default
 from .data_containers import TextChunk
@@ -41,7 +41,7 @@ class IndexifyClient:
         **kwargs,
     ):
         self.namespace: str = namespace
-        self.extractor_bindings: List[ExtractorBinding] = []
+        self.extraction_policies: List[ExtractionPolicy] = []
         self.labels: dict = {}
         self._service_url = service_url
         self._client = httpx.Client(*args, **kwargs)
@@ -50,9 +50,9 @@ class IndexifyClient:
         response = self.get(f"namespaces/{self.namespace}")
         response.raise_for_status()
         resp_json = response.json()
-        # initialize extractor_bindings
-        for eb in resp_json["namespace"]["extractor_bindings"]:
-            self.extractor_bindings.append(ExtractorBinding.from_dict(eb))
+        # initialize extraction_policies
+        for eb in resp_json["namespace"]["extraction_policies"]:
+            self.extraction_policies.append(ExtractionPolicy.from_dict(eb))
 
     @classmethod
     def with_mtls(
@@ -189,7 +189,7 @@ class IndexifyClient:
     def create_namespace(
         self,
         namespace: str,
-        extractor_bindings: list = [],
+        extraction_policies: list = [],
         labels: dict = {},
     ) -> "IndexifyClient":
         """
@@ -198,15 +198,15 @@ class IndexifyClient:
         Returns:
             IndexifyClient: a new client with the given namespace
         """
-        bindings = []
-        for bd in extractor_bindings:
-            if isinstance(bd, ExtractorBinding):
-                bindings.append(bd.to_dict())
+        extraction_policies = []
+        for bd in extraction_policies:
+            if isinstance(bd, ExtractionPolicy):
+                extraction_policies.append(bd.to_dict())
             else:
-                bindings.append(bd)
+                extraction_policies.append(bd)
         req = {
             "name": namespace,
-            "extractor_bindings": bindings,
+            "extraction_policies": extraction_policies,
             "labels": labels,
         }
 
@@ -239,19 +239,19 @@ class IndexifyClient:
             extractors.append(Extractor.from_dict(ed))
         return extractors
 
-    def get_extractor_bindings(self):
+    def get_extraction_policies(self):
         """
-        Retrieve and update the list of extractor bindings for the current namespace.
+        Retrieve and update the list of extraction policies for the current namespace.
         """
         response = self.get(f"namespaces/{self.namespace}")
         response.raise_for_status()
 
-        self.extractor_bindings = []
-        for eb in response.json()["namespace"]["extractor_bindings"]:
-            self.extractor_bindings.append(ExtractorBinding.from_dict(eb))
-        return self.extractor_bindings
+        self.extraction_policies = []
+        for eb in response.json()["namespace"]["extraction_policies"]:
+            self.extraction_policies.append(ExtractionPolicy.from_dict(eb))
+        return self.extraction_policies
 
-    def bind_extractor(
+    def add_extraction_policy(
         self,
         extractor: str,
         name: str,
@@ -259,7 +259,7 @@ class IndexifyClient:
         labels_eq: str = None,
         content_source="ingestion",
     ) -> dict:
-        """Bind an extractor.
+        """Add a new extraction policy.
 
         Args:
             - extractor (str): Name of the extractor
@@ -271,9 +271,9 @@ class IndexifyClient:
             dict: response payload
 
         Examples:
-            >>> repo.bind_extractor("EfficientNet", "efficientnet")
+            >>> repo.add_extraction_policy("EfficientNet", "efficientnet")
 
-            >>> repo.bind_extractor("MiniLML6", "minilm")
+            >>> repo.add_extraction_policy("MiniLML6", "minilm")
 
         """
         req = {
@@ -288,13 +288,13 @@ class IndexifyClient:
 
         request_body = json.dumps(req, default=json_set_default)
         response = self.post(
-            f"namespaces/{self.namespace}/extractor_bindings",
+            f"namespaces/{self.namespace}/extraction_policies",
             data=request_body,
             headers={"Content-Type": "application/json"},
         )
 
         # update self.extractor_bindings
-        self.get_extractor_bindings()
+        self.get_extraction_policies()
 
         try:
             response.raise_for_status()
@@ -404,5 +404,6 @@ class IndexifyClient:
             response = self.post(
                 f"namespaces/{self.namespace}/upload_file",
                 files={"file": f},
+                timeout=None,
             )
             response.raise_for_status()

{indexify-0.0.8 → indexify-0.0.10}/indexify/data_containers.py

@@ -3,15 +3,6 @@ from typing import List
 from dataclasses import dataclass, field
 
 
-class TextSplitter(str, Enum):
-    NEWLINE = "new_line"
-    REGEX = "regex"
-    NOOP = "noop"
-
-    def __str__(self) -> str:
-        return self.value.lower()
-
-
 @dataclass
 class TextChunk:
     text: str
@@ -22,16 +13,6 @@ class TextChunk:
         return {"text": self.text, "metadata": self.metadata}
 
 
-@dataclass
-class SearchChunk:
-    index: str
-    query: str
-    k: int
-
-    def to_dict(self):
-        return {"index": self.index, "query": self.query, "k": self.k}
-
-
 @dataclass
 class SearchResult:
     results: List[TextChunk]

indexify-0.0.8/indexify/extractor_binding.py → indexify-0.0.10/indexify/extraction_policy.py

@@ -3,7 +3,7 @@ from typing import Optional
 
 
 @dataclass
-class ExtractorBinding:
+class ExtractionPolicy:
     extractor: str
     name: str
     content_source: str
@@ -11,7 +11,7 @@ class ExtractorBinding:
     labels_eq: Optional[str] = None
 
     def __repr__(self) -> str:
-        return f"ExtractorBinding(name={self.name} extractor={self.extractor})"
+        return f"ExtractionPolicy(name={self.name} extractor={self.extractor})"
 
     def __str__(self) -> str:
         return self.__repr__()
@@ -24,4 +24,4 @@ class ExtractorBinding:
     def from_dict(cls, json: dict):
         if "filters_eq" in json:
             json["labels_eq"] = json.pop("filters_eq")
-        return ExtractorBinding(**json)
+        return ExtractionPolicy(**json)

{indexify-0.0.8 → indexify-0.0.10}/indexify/extractor.py

@@ -16,22 +16,15 @@ class ExtractorSchema:
     outputs: dict[str, Union[EmbeddingSchema, dict]]
 
 
-@dataclass
-class Extractor:
-    name: str
-    description: str
-    input_params: dict
-    outputs: ExtractorSchema
-
-
 class Extractor:
     def __init__(
-        self, name: str, description: str, input_params: dict, outputs: ExtractorSchema
+        self, name: str, description: str, input_params: dict, outputs: ExtractorSchema, input_mime_types: list[str]
     ):
         self.name = name
         self.description = description
         self.input_params = input_params
         self.outputs = outputs
+        self.input_mime_types = input_mime_types
 
     @classmethod
     def from_dict(cls, data):
@@ -39,11 +32,12 @@ class Extractor:
             name=data["name"],
             description=data["description"],
             input_params=data["input_params"],
+            input_mime_types=data["input_mime_types"],
             outputs=data["outputs"],
         )
 
     def __repr__(self) -> str:
-        return f"Extractor(name={self.name}, description={self.description}, input_params={self.input_params}, outputs={self.outputs})"
+        return f"Extractor(name={self.name}, description={self.description}, input_params={self.input_params}, input_mime_types={self.input_mime_types}, outputs={self.outputs})"
 
     def __str__(self) -> str:
         return self.__repr__()

{indexify-0.0.8 → indexify-0.0.10}/indexify/index.py

@@ -1,6 +1,6 @@
 import httpx
 
-from .data_containers import SearchChunk, TextChunk
+from .data_containers import TextChunk
 
 
 class Index:

indexify-0.0.10/indexify/utils.py

@@ -0,0 +1,7 @@
+from enum import Enum
+
+
+def json_set_default(obj):
+    if isinstance(obj, set):
+        return list(obj)
+    raise TypeError

{indexify-0.0.8 → indexify-0.0.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "indexify"
-version = "0.0.8"
+version = "0.0.10"
 description = "Python Client for Indexify"
 authors = ["Diptanu Gon Choudhury <diptanuc@gmail.com>", "Vijay Parthasarathy <vijay2win@gmail.com>"]
 license = "Apache 2.0"

indexify-0.0.8/indexify/utils.py

@@ -1,16 +0,0 @@
-from enum import Enum
-
-
-def json_set_default(obj):
-    if isinstance(obj, set):
-        return list(obj)
-    raise TypeError
-
-
-class Metric(str, Enum):
-    COSINE = "cosine"
-    DOT = "dot"
-    EUCLIDEAN = "euclidean"
-
-    def __str__(self) -> str:
-        return self.name.lower()