indexify 0.0.14__py3-none-any.whl → 0.0.16__py3-none-any.whl

indexify/client.py

@@ -1,4 +1,7 @@
+import yaml
 import httpx
+import uuid
+import hashlib
 import json
 from collections import namedtuple
 from .settings import DEFAULT_SERVICE_URL
@@ -12,7 +15,7 @@ from dataclasses import dataclass
 
 from typing import List, Optional, Union, Dict
 
-Document = namedtuple("Document", ["text", "labels"])
+Document = namedtuple("Document", ["text", "labels", "id"])
 
 SQLQueryRow = namedtuple("SQLQueryRow", ["content_id", "data"])
 
@@ -44,14 +47,30 @@ class IndexifyClient:
         self,
         service_url: str = DEFAULT_SERVICE_URL,
         namespace: str = "default",
+        config_path: Optional[str] = None,
         *args,
         **kwargs,
     ):
+        if config_path:
+            with open(config_path, 'r') as file:
+                config = yaml.safe_load(file)
+                
+            if config.get('use_tls', False):
+                tls_config = config['tls_config']
+                self._client = httpx.Client(
+                    http2=True,
+                    cert=(tls_config['cert_path'], tls_config['key_path']),
+                    verify=tls_config.get('ca_bundle_path', True)
+                )
+            else:
+                self._client = httpx.Client(*args, **kwargs)
+        else:
+            self._client = httpx.Client(*args, **kwargs)
+
         self.namespace: str = namespace
         self.extraction_policies: List[ExtractionPolicy] = []
         self.labels: dict = {}
         self._service_url = service_url
-        self._client = httpx.Client(*args, **kwargs)
 
         # get namespace data
         response = self.get(f"namespaces/{self.namespace}")
@@ -349,11 +368,21 @@ class IndexifyClient:
         except httpx.HTTPStatusError as exc:
             raise ApiException(exc.response.text)
         return
+    
+    def get_content_metadata(self, content_id: str) -> dict:
+        """
+        Get metadata for a specific content ID in a given index.
 
-    def get_content(
+        Args:
+            - content_id (str): content id to query
+        """
+        response = self.get(f"namespaces/{self.namespace}/content/{content_id}")
+        response.raise_for_status()
+        return response.json()
+
+    def get_extracted_content(
         self,
-        parent_id: str = None,
-        labels_eq: str = None,
+        content_id: str = None,
     ):
         """
         Get list of content from current namespace.
@@ -362,11 +391,7 @@ class IndexifyClient:
             - parent_id (str): Optional filter for parent id
             - labels_eq (str): Optional filter for labels
         """
-        params = {}
-        if parent_id:
-            params.update({"parent_id": parent_id})
-        if labels_eq:
-            params.update({"labels_eq": labels_eq})
+        params = {"parent_id": content_id}
 
         response = self.get(f"namespaces/{self.namespace}/content", params=params)
         response.raise_for_status()
@@ -390,7 +415,7 @@ class IndexifyClient:
             raise ApiException(exc.response.text)
 
     def add_documents(
-        self, documents: Union[Document, str, List[Union[Document, str]]]
+        self, documents: Union[Document, str, List[Union[Document, str]]], doc_id=None
     ) -> None:
         """
         Add documents to current namespace.
@@ -401,14 +426,14 @@ class IndexifyClient:
         if isinstance(documents, Document):
             documents = [documents]
         elif isinstance(documents, str):
-            documents = [Document(documents, {})]
+            documents = [Document(documents, {}, id=doc_id)]
         elif isinstance(documents, list):
             new_documents = []
             for item in documents:
                 if isinstance(item, Document):
                     new_documents.append(item)
                 elif isinstance(item, str):
-                    new_documents.append(Document(item, {}))
+                    new_documents.append(Document(item, {}, id=None)) # don't pass in id for a string content because doesn't make sense to have same content id for all strings
                 else:
                     raise ValueError(
                         "List items must be either Document instances or strings."
@@ -419,7 +444,7 @@ class IndexifyClient:
                 "Invalid type for documents. Expected Document, str, or list of these."
             )
 
-        req = {"documents": documents}
+        req = {"documents": [doc._asdict() for doc in documents]}
         response = self.post(
             f"namespaces/{self.namespace}/add_texts",
             json=req,
@@ -453,7 +478,7 @@ class IndexifyClient:
             response = self.put(f"namespaces/{self.namespace}/content/{document_id}", files={"file": f}, timeout=None)
             response.raise_for_status()
 
-    def get_metadata(self, content_id: str) -> dict:
+    def get_structured_data(self, content_id: str) -> dict:
         """
         Query metadata for a specific content ID in a given index.
 
@@ -464,7 +489,7 @@ class IndexifyClient:
         response.raise_for_status()
         return response.json().get("metadata",[])
 
-    def search_index(self, name: str, query: str, top_k: int) -> list[TextChunk]:
+    def search_index(self, name: str, query: str, top_k: int, filters: List[str] = None) -> list[TextChunk]:
         """
         Search index in the current namespace.
 
@@ -472,8 +497,11 @@ class IndexifyClient:
             - name (str): name of index to search
             - query (str): query string
             - top_k (int): top k nearest neighbors to be returned
+            - filters (List[str]): list of filters to apply
         """
-        req = {"index": name, "query": query, "k": top_k}
+        if filters is None:
+            filters = []
+        req = {"index": name, "query": query, "k": top_k, "filters": filters}
         response = self.post(
             f"namespaces/{self.namespace}/search",
             json=req,
@@ -482,17 +510,23 @@ class IndexifyClient:
         response.raise_for_status()
         return response.json()["results"]
 
-    def upload_file(self, path: str):
+    def upload_file(self, path: str, id=None, labels: dict = {}):
         """
         Upload a file.
 
         Args:
             - path (str): relative path to the file to be uploaded
+            - labels (dict): labels to be associated with the file
         """
+        params={}
+        if id is not None:
+            params['id'] = id
         with open(path, "rb") as f:
             response = self.post(
                 f"namespaces/{self.namespace}/upload_file",
                 files={"file": f},
+                data=labels,
+                params=params,
                 timeout=None,
             )
             response.raise_for_status()
@@ -535,4 +569,27 @@ class IndexifyClient:
         )
         response.raise_for_status()
         return response.json()
+    
+    def generate_unique_hex_id(self):
+        """
+        Generate a unique hexadecimal identifier
+
+        Returns:
+            str: a unique hexadecimal string
+        """
+        return uuid.uuid4().hex[:16]
+    
+    def generate_hash_from_string(self, input_string: str):
+        """
+        Generate a hash for the given string and return it as a hexadecimal string.
+        
+        Args:
+            input_string (str): The input string to hash.
+        
+        Returns:
+            str: The hexadecimal hash of the input string.
+        """
+        hash_object = hashlib.sha256(input_string.encode())
+        return hash_object.hexdigest()[:16]
+
 

{indexify-0.0.14.dist-info → indexify-0.0.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: indexify
-Version: 0.0.14
+Version: 0.0.16
 Summary: Python Client for Indexify
 Home-page: https://github.com/tensorlakeai/indexify
 License: Apache 2.0

{indexify-0.0.14.dist-info → indexify-0.0.16.dist-info}/RECORD

@@ -1,5 +1,5 @@
 indexify/__init__.py,sha256=Sz6zkAIHsPOi0rG5RM7dVkXGDa0fO2uurD6vS4Qo15E,312
-indexify/client.py,sha256=sT4tcSuR3wQBF0yYStBRva3xUfe15X6GjZaViiRX2sA,16944
+indexify/client.py,sha256=ZDirw1O46nRx0WBgB95jvpkd4LdAjgZnlQ_2A673_cI,19047
 indexify/data_containers.py,sha256=r1wxJPtsmXbyKvb17fqxm-dPjKz51oZ62f8A8Zxls1c,361
 indexify/exceptions.py,sha256=vjd5SPPNFIEW35GorSIodsqvm9RKHQm9kdp8t9gv-WM,111
 indexify/extraction_policy.py,sha256=vKVHT8jSjzhUaKqWpewOGkYojMBplvGdSm9zoSN9Pcg,750
@@ -7,7 +7,7 @@ indexify/extractor.py,sha256=KMcP9xopHJRBzeSxalztGGTBvOzVKRFEsJynV-hLRSc,1175
 indexify/index.py,sha256=RvxYhJXEth-GKvqzlMiz5PuN1eIbZk84pt20piA1Gsw,504
 indexify/settings.py,sha256=yzWAEZkrTjykSMj3hrFU7l_jUoUCOUsgPVW1nU-qzJQ,46
 indexify/utils.py,sha256=rDN2lrsAs9noJEIjfx6ukmC2SAIyrlUt7QU-kaBjujM,125
-indexify-0.0.14.dist-info/LICENSE.txt,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-indexify-0.0.14.dist-info/METADATA,sha256=ANdIdnRnC6ISLYc1oTUb-BE-NjdgUg0iEu0dHRmonnI,1714
-indexify-0.0.14.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-indexify-0.0.14.dist-info/RECORD,,
+indexify-0.0.16.dist-info/LICENSE.txt,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+indexify-0.0.16.dist-info/METADATA,sha256=h_tYmLlbYT0g_9SJnec9hgey8AYP0VTKascytOt0_jE,1714
+indexify-0.0.16.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+indexify-0.0.16.dist-info/RECORD,,