usecortex-ai 0.5.0__tar.gz → 0.5.1__tar.gz

{usecortex_ai-0.5.0 → usecortex_ai-0.5.1}/LICENSE

@@ -1,22 +1,22 @@
-Copyright (c) 2024 Cortex AI
-
-All Rights Reserved.
-
-PROPRIETARY AND CONFIDENTIAL
-
-This software is the proprietary and confidential property of Cortex AI ("the Company").
-Permission is hereby granted to users to install and use this software as part of the Cortex AI service, subject to the terms and conditions of the service agreement entered into with the Company.
-
-You may not, without the express written permission of the Company:
-
-1. Copy, modify, or create derivative works of the software.
-2. Distribute, sell, rent, lease, sublicense, or otherwise transfer the software to any third party.
-3. Reverse engineer, decompile, or disassemble the software, except and only to the extent that such activity is expressly permitted by applicable law notwithstanding this limitation.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+Copyright (c) 2024 Cortex AI
+
+All Rights Reserved.
+
+PROPRIETARY AND CONFIDENTIAL
+
+This software is the proprietary and confidential property of Cortex AI ("the Company").
+Permission is hereby granted to users to install and use this software as part of the Cortex AI service, subject to the terms and conditions of the service agreement entered into with the Company.
+
+You may not, without the express written permission of the Company:
+
+1. Copy, modify, or create derivative works of the software.
+2. Distribute, sell, rent, lease, sublicense, or otherwise transfer the software to any third party.
+3. Reverse engineer, decompile, or disassemble the software, except and only to the extent that such activity is expressly permitted by applicable law notwithstanding this limitation.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.

{usecortex_ai-0.5.0/src/usecortex_ai.egg-info → usecortex_ai-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: usecortex-ai
-Version: 0.5.0
+Version: 0.5.1
 Summary: The official Python SDK for the Cortex AI platform.
 Author-email: Soham Ratnaparkhi <soham@usecortex.ai>
 License: Copyright (c) 2024 Cortex AI

{usecortex_ai-0.5.0 → usecortex_ai-0.5.1}/README.md

@@ -1,135 +1,135 @@
-# Cortex AI Python SDK - [usecortex.ai](https://www.usecortex.ai/)
-
-The official Python SDK for the Cortex AI platform. Build powerful, context-aware AI applications in your Python applications.
-
-**Cortex** is your plug-and-play memory infrastructure. It powers intelligent, context-aware retrieval for any AI app or agent. Whether you’re building a customer support bot, research copilot, or internal knowledge assistant.
-
-[Learn more about the SDK from our docs](https://docs.usecortex.ai/)
-
-## Core features
-
-* **Dynamic retrieval and querying** that always retrieve the most relevant context
-* **Built-in long-term memory** that evolves with every user interaction
-* **Personalization hooks** for user preferences, intent, and history
-* **Developer-first SDK** with the most flexible APIs and fine-grained controls
-
-## Getting started
-
-### Installation
-
-```bash
-pip install usecortex-ai
-```
-
-### Client setup
-
-We provide both synchronous and asynchronous clients. Use **`AsyncCortexAI`** when working with async/await patterns, and **`CortexAI`** for traditional synchronous workflows. Client initialization does not trigger any network requests, so you can safely create as many client instances as needed. Both clients expose the exact same set of methods.
-
-```python
-import os
-from usecortex_ai import CortexAI, AsyncCortexAI
-
-api_key = os.environ["CORTEX_API_KEY"]  # Set your Cortex API key in the environment variable CORTEX_API_KEY. Optional, but recommended.
-
-# Sync client
-client = CortexAI(token=api_key)
-
-# Async client (for async/await usage)
-async_client = AsyncCortexAI(token=api_key)
-```
-
-### Create a Tenant
-
-You can consider a `tenant` as a single database that can have internal isolated collections called `sub-tenants`. [Know more about the concept of tenant here](https://docs.usecortex.ai/essentials/multi-tenant)
-
-```python
-def create_tenant():
-    return client.user.create_tenant(tenant_id="my-company")
-```
-
-### Index Your Data
-
-When you index your data, you make it ready for retrieval from Cortex using natural language.
-
-```python
-# Upload text content
-def upload_text():
-    return client.upload.upload_text(
-        tenant_id="my-company-py-sync",
-        sub_tenant_id="engineering",
-        content="Our API rate limits are 1000 requests per minute for premium accounts.",
-        file_id="api-docs-rate-limits",
-        tenant_metadata={"sub_tenant_id": "engineering"}
-    )
-
-# Upload document file
-def upload_file():
-    with open("company-handbook.pdf", 'rb') as file_obj:
-        file_data = ("company-handbook.pdf", file_obj)
-        return client.upload.upload_document(
-            tenant_id="my-company",
-            file=file_data,
-            file_id="company-handbook.pdf"
-        )
-```
-
-**For a more detailed explanation** of document upload, including supported file formats, processing pipeline, metadata handling, and advanced configuration options, refer to the [Upload Document endpoint documentation](https://docs.usecortex.ai/api-reference/endpoint/upload-document).
-
-### Search and retrieval
-
-```python
-# Semantic search with retrieval
-results = client.search.retrieve(
-    query="What are the API rate limits?",
-    tenant_id="my-company",
-    sub_tenant_id="engineering",
-    max_chunks=10
-)
-
-# List all sources
-all_sources = client.sources.get_all(
-    tenant_id="my-company",
-    sub_tenant_id="engineering",
-)
-
-# Get specific sources by ID
-specific_sources = client.sources.get_by_ids(
-    tenant_id="my-company",
-    sub_tenant_id="engineering",
-    source_ids=["api-docs-rate-limits", "company-handbook"]
-)
-```
-
-**For a more detailed explanation** of search and retrieval, including query parameters, scoring mechanisms, result structure, and advanced search features, refer to the [Search endpoint documentation](https://docs.usecortex.ai/api-reference/endpoint/search).
-
-## SDK Method Structure & Type Safety
-
-Our SDKs follow a predictable pattern that mirrors the API structure while providing full type safety.
-
-> **Method Mapping** : `client.<group>.<function_name>` mirrors  `api.usecortex.ai/<group>/<function_name>`
->
-> For example: `client.upload.upload_text()` corresponds to `POST /upload/upload_text`
-
-The SDKs provide exact type parity with the API specification:
-
-- **Request Parameters** : Every field documented in the API reference (required, optional, types, validation rules) is reflected in the SDK method signatures
-- **Response Objects** : Return types match the exact JSON schema documented for each endpoint
-- **Error Types** : Exception structures mirror the error response formats from the API
-- **Nested Objects** : Complex nested parameters and responses maintain their full structure and typing
-
-> This means you can rely on your IDE’s autocomplete and type checking. If a parameter is optional in the API docs, it’s optional in the SDK. If a response contains a specific field, your IDE will know about it. Our SDKs are built in such a way that your IDE will automatically provide **autocompletion, type-checking, inline documentation with examples, and compile time validation** for each and every method.
->
-> Just hit **Cmd+Space/Ctrl+Space!**
-
-## Links
-
-- **Homepage:** [usecortex.ai](https://www.usecortex.ai/)
-- **Documentation:** [docs.usecortex.ai](https://docs.usecortex.ai/)
-
-## Our docs
-
-Please refer to our [API reference](https://docs.usecortex.ai/api-reference/introduction) for detailed explanations of every API endpoint, parameter options, and advanced use cases.
-
-## Support
-
-If you have any questions or need help, please reach out to our support team at [founders@usecortex.ai](mailto:founders@usecortex.ai).
+# Cortex AI Python SDK - [usecortex.ai](https://www.usecortex.ai/)
+
+The official Python SDK for the Cortex AI platform. Build powerful, context-aware AI applications in your Python applications.
+
+**Cortex** is your plug-and-play memory infrastructure. It powers intelligent, context-aware retrieval for any AI app or agent. Whether you’re building a customer support bot, research copilot, or internal knowledge assistant.
+
+[Learn more about the SDK from our docs](https://docs.usecortex.ai/)
+
+## Core features
+
+* **Dynamic retrieval and querying** that always retrieve the most relevant context
+* **Built-in long-term memory** that evolves with every user interaction
+* **Personalization hooks** for user preferences, intent, and history
+* **Developer-first SDK** with the most flexible APIs and fine-grained controls
+
+## Getting started
+
+### Installation
+
+```bash
+pip install usecortex-ai
+```
+
+### Client setup
+
+We provide both synchronous and asynchronous clients. Use **`AsyncCortexAI`** when working with async/await patterns, and **`CortexAI`** for traditional synchronous workflows. Client initialization does not trigger any network requests, so you can safely create as many client instances as needed. Both clients expose the exact same set of methods.
+
+```python
+import os
+from usecortex_ai import CortexAI, AsyncCortexAI
+
+api_key = os.environ["CORTEX_API_KEY"]  # Set your Cortex API key in the environment variable CORTEX_API_KEY. Optional, but recommended.
+
+# Sync client
+client = CortexAI(token=api_key)
+
+# Async client (for async/await usage)
+async_client = AsyncCortexAI(token=api_key)
+```
+
+### Create a Tenant
+
+You can consider a `tenant` as a single database that can have internal isolated collections called `sub-tenants`. [Know more about the concept of tenant here](https://docs.usecortex.ai/essentials/multi-tenant)
+
+```python
+def create_tenant():
+    return client.user.create_tenant(tenant_id="my-company")
+```
+
+### Index Your Data
+
+When you index your data, you make it ready for retrieval from Cortex using natural language.
+
+```python
+# Upload text content
+def upload_text():
+    return client.upload.upload_text(
+        tenant_id="my-company-py-sync",
+        sub_tenant_id="engineering",
+        content="Our API rate limits are 1000 requests per minute for premium accounts.",
+        file_id="api-docs-rate-limits",
+        tenant_metadata={"sub_tenant_id": "engineering"}
+    )
+
+# Upload document file
+def upload_file():
+    with open("company-handbook.pdf", 'rb') as file_obj:
+        file_data = ("company-handbook.pdf", file_obj)
+        return client.upload.upload_document(
+            tenant_id="my-company",
+            file=file_data,
+            file_id="company-handbook.pdf"
+        )
+```
+
+**For a more detailed explanation** of document upload, including supported file formats, processing pipeline, metadata handling, and advanced configuration options, refer to the [Upload Document endpoint documentation](https://docs.usecortex.ai/api-reference/endpoint/upload-document).
+
+### Search and retrieval
+
+```python
+# Semantic search with retrieval
+results = client.search.retrieve(
+    query="What are the API rate limits?",
+    tenant_id="my-company",
+    sub_tenant_id="engineering",
+    max_chunks=10
+)
+
+# List all sources
+all_sources = client.sources.get_all(
+    tenant_id="my-company",
+    sub_tenant_id="engineering",
+)
+
+# Get specific sources by ID
+specific_sources = client.sources.get_by_ids(
+    tenant_id="my-company",
+    sub_tenant_id="engineering",
+    source_ids=["api-docs-rate-limits", "company-handbook"]
+)
+```
+
+**For a more detailed explanation** of search and retrieval, including query parameters, scoring mechanisms, result structure, and advanced search features, refer to the [Search endpoint documentation](https://docs.usecortex.ai/api-reference/endpoint/search).
+
+## SDK Method Structure & Type Safety
+
+Our SDKs follow a predictable pattern that mirrors the API structure while providing full type safety.
+
+> **Method Mapping** : `client.<group>.<function_name>` mirrors  `api.usecortex.ai/<group>/<function_name>`
+>
+> For example: `client.upload.upload_text()` corresponds to `POST /upload/upload_text`
+
+The SDKs provide exact type parity with the API specification:
+
+- **Request Parameters** : Every field documented in the API reference (required, optional, types, validation rules) is reflected in the SDK method signatures
+- **Response Objects** : Return types match the exact JSON schema documented for each endpoint
+- **Error Types** : Exception structures mirror the error response formats from the API
+- **Nested Objects** : Complex nested parameters and responses maintain their full structure and typing
+
+> This means you can rely on your IDE’s autocomplete and type checking. If a parameter is optional in the API docs, it’s optional in the SDK. If a response contains a specific field, your IDE will know about it. Our SDKs are built in such a way that your IDE will automatically provide **autocompletion, type-checking, inline documentation with examples, and compile time validation** for each and every method.
+>
+> Just hit **Cmd+Space/Ctrl+Space!**
+
+## Links
+
+- **Homepage:** [usecortex.ai](https://www.usecortex.ai/)
+- **Documentation:** [docs.usecortex.ai](https://docs.usecortex.ai/)
+
+## Our docs
+
+Please refer to our [API reference](https://docs.usecortex.ai/api-reference/introduction) for detailed explanations of every API endpoint, parameter options, and advanced use cases.
+
+## Support
+
+If you have any questions or need help, please reach out to our support team at [founders@usecortex.ai](mailto:founders@usecortex.ai).

{usecortex_ai-0.5.0 → usecortex_ai-0.5.1}/pyproject.toml

@@ -1,40 +1,40 @@
-[build-system]
-requires = ["setuptools>=61.0"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "usecortex-ai"
-
-version = "0.5.0"
-
-authors = [
-  { name = "Soham Ratnaparkhi", email = "soham@usecortex.ai" },
-]
-description = "The official Python SDK for the Cortex AI platform."
-readme = "README.md"
-requires-python = ">=3.10"
-license = { file = "LICENSE" }
-keywords = ["cortex", "ai", "sdk", "api", "generative ai", "rag"]
-
-# Add classifiers to help users find your package on PyPI
-classifiers = [
-    # See https://pypi.org/classifiers/
-    "Development Status :: 5 - Production/Stable",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Intended Audience :: Developers",
-    "Topic :: Software Development :: Libraries :: Python Modules",
-    "Typing :: Typed",
-]
-
-dependencies = [
-  "httpx>=0.24",
-  "pydantic>=1.10,<3",
-]
-
-[project.urls]
-Homepage = "https://www.usecortex.ai/"
-Documentation = "https://docs.usecortex.ai/"
-
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "usecortex-ai"
+
+version = "0.5.1"
+
+authors = [
+  { name = "Soham Ratnaparkhi", email = "soham@usecortex.ai" },
+]
+description = "The official Python SDK for the Cortex AI platform."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { file = "LICENSE" }
+keywords = ["cortex", "ai", "sdk", "api", "generative ai", "rag"]
+
+# Add classifiers to help users find your package on PyPI
+classifiers = [
+    # See https://pypi.org/classifiers/
+    "Development Status :: 5 - Production/Stable",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Intended Audience :: Developers",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Typing :: Typed",
+]
+
+dependencies = [
+  "httpx>=0.24",
+  "pydantic>=1.10,<3",
+]
+
+[project.urls]
+Homepage = "https://www.usecortex.ai/"
+Documentation = "https://docs.usecortex.ai/"
+

{usecortex_ai-0.5.0 → usecortex_ai-0.5.1}/src/usecortex_ai/__init__.py

@@ -6,7 +6,6 @@ from .types import (
     ActualErrorResponse,
     AddMemoryResponse,
     ApiKeyInfo,
-    AppSourcesUploadData,
     AttachmentModel,
     Bm25OperatorType,
     CollectionStats,
@@ -25,6 +24,8 @@ from .types import (
     HttpValidationError,
     Infra,
     InsertResult,
+    ListContentKind,
+    ListUserMemoriesResponse,
     MemoryItem,
     MemoryResultItem,
     MilvusDataType,
@@ -56,6 +57,7 @@ from .types import (
     TenantStatsResponse,
     TripletWithEvidence,
     UserAssistantPair,
+    UserMemory,
     ValidationError,
     ValidationErrorLocItem,
     VectorStoreChunk,
@@ -73,20 +75,18 @@ from .errors import (
 from . import dashboard, embeddings, fetch, search, sources, tenant, upload
 from .client import AsyncCortexAI, CortexAI
 from .environment import CortexAIEnvironment
+from .fetch import FetchListKnowledgeResponse
 from .search import Alpha
-from .upload import BodyUploadAppIngestionUploadAppPostAppSources
 
 __all__ = [
     "ActualErrorResponse",
     "AddMemoryResponse",
     "Alpha",
     "ApiKeyInfo",
-    "AppSourcesUploadData",
     "AsyncCortexAI",
     "AttachmentModel",
     "BadRequestError",
     "Bm25OperatorType",
-    "BodyUploadAppIngestionUploadAppPostAppSources",
     "CollectionStats",
     "ContentModel",
     "CortexAI",
@@ -99,6 +99,7 @@ __all__ = [
     "DeleteUserMemoryResponse",
     "Entity",
     "ErrorResponse",
+    "FetchListKnowledgeResponse",
     "FetchMode",
     "ForbiddenError",
     "ForcefulRelationsPayload",
@@ -107,6 +108,8 @@ __all__ = [
     "Infra",
     "InsertResult",
     "InternalServerError",
+    "ListContentKind",
+    "ListUserMemoriesResponse",
     "MemoryItem",
     "MemoryResultItem",
     "MilvusDataType",
@@ -143,6 +146,7 @@ __all__ = [
     "UnauthorizedError",
     "UnprocessableEntityError",
     "UserAssistantPair",
+    "UserMemory",
     "ValidationError",
     "ValidationErrorLocItem",
     "VectorStoreChunk",

{usecortex_ai-0.5.0 → usecortex_ai-0.5.1}/src/usecortex_ai/client.py

@@ -103,8 +103,6 @@ class CortexAI:
         self, *, request_options: typing.Optional[RequestOptions] = None
     ) -> typing.Optional[typing.Any]:
         """
-        Endpoint that serves Prometheus metrics.
-
         Parameters
         ----------
         request_options : typing.Optional[RequestOptions]
@@ -213,8 +211,6 @@ class AsyncCortexAI:
         self, *, request_options: typing.Optional[RequestOptions] = None
     ) -> typing.Optional[typing.Any]:
         """
-        Endpoint that serves Prometheus metrics.
-
         Parameters
         ----------
         request_options : typing.Optional[RequestOptions]

{usecortex_ai-0.5.0 → usecortex_ai-0.5.1}/src/usecortex_ai/dashboard/client.py

@@ -27,11 +27,6 @@ class DashboardClient:
 
     def list_apis(self, *, request_options: typing.Optional[RequestOptions] = None) -> DashboardApisResponse:
         """
-        List all API keys for dashboard view.
-
-        Uses Firebase authentication to identify the user and returns API keys
-        associated with that user.
-
         Parameters
         ----------
         request_options : typing.Optional[RequestOptions]
@@ -56,10 +51,6 @@ class DashboardClient:
         self, *, tenant_id: str, sub_tenant_id: str, request_options: typing.Optional[RequestOptions] = None
     ) -> DashboardSourcesResponse:
         """
-        List all sources for a tenant/sub-tenant combination.
-
-        Uses the same logic as the existing get_sources function.
-
         Parameters
         ----------
         tenant_id : str
@@ -81,7 +72,7 @@ class DashboardClient:
         from usecortex-ai import CortexAI
 
         client = CortexAI(token="YOUR_TOKEN", )
-        client.dashboard.list_sources(tenant_id='tenant_id', sub_tenant_id='sub_tenant_id', )
+        client.dashboard.list_sources(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
         """
         _response = self._raw_client.list_sources(
             tenant_id=tenant_id, sub_tenant_id=sub_tenant_id, request_options=request_options
@@ -90,11 +81,6 @@ class DashboardClient:
 
     def list_tenants(self, *, request_options: typing.Optional[RequestOptions] = None) -> DashboardTenantsResponse:
         """
-        List all tenants for dashboard view.
-
-        Uses Firebase authentication to identify the user and returns tenant
-        mappings associated with that user's organization.
-
         Parameters
         ----------
         request_options : typing.Optional[RequestOptions]
@@ -231,11 +217,6 @@ class AsyncDashboardClient:
 
     async def list_apis(self, *, request_options: typing.Optional[RequestOptions] = None) -> DashboardApisResponse:
         """
-        List all API keys for dashboard view.
-
-        Uses Firebase authentication to identify the user and returns API keys
-        associated with that user.
-
         Parameters
         ----------
         request_options : typing.Optional[RequestOptions]
@@ -264,10 +245,6 @@ class AsyncDashboardClient:
         self, *, tenant_id: str, sub_tenant_id: str, request_options: typing.Optional[RequestOptions] = None
     ) -> DashboardSourcesResponse:
         """
-        List all sources for a tenant/sub-tenant combination.
-
-        Uses the same logic as the existing get_sources function.
-
         Parameters
         ----------
         tenant_id : str
@@ -292,7 +269,7 @@ class AsyncDashboardClient:
 
         client = AsyncCortexAI(token="YOUR_TOKEN", )
         async def main() -> None:
-            await client.dashboard.list_sources(tenant_id='tenant_id', sub_tenant_id='sub_tenant_id', )
+            await client.dashboard.list_sources(tenant_id='tenant_1234', sub_tenant_id='sub_tenant_4567', )
         asyncio.run(main())
         """
         _response = await self._raw_client.list_sources(
@@ -304,11 +281,6 @@ class AsyncDashboardClient:
         self, *, request_options: typing.Optional[RequestOptions] = None
     ) -> DashboardTenantsResponse:
         """
-        List all tenants for dashboard view.
-
-        Uses Firebase authentication to identify the user and returns tenant
-        mappings associated with that user's organization.
-
         Parameters
         ----------
         request_options : typing.Optional[RequestOptions]