usecortex-ai 0.1.0__tar.gz

usecortex_ai-0.1.0/LICENSE

@@ -0,0 +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 authorized 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-0.1.0/PKG-INFO

@@ -0,0 +1,136 @@
+Metadata-Version: 2.4
+Name: usecortex-ai
+Version: 0.1.0
+Summary: The official Python SDK for the Cortex AI platform.
+Author-email: Nishkarsh Shrivastava <nishkarsh@usecortex.ai>
+License: 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 authorized 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.
+Project-URL: Homepage, https://www.usecortex.ai/
+Project-URL: Documentation, https://docs.usecortex.ai/
+Keywords: cortex,ai,sdk,api,generative ai,rag
+Classifier: Development Status :: 4 - Beta
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: httpx>=0.24
+Requires-Dist: pydantic<3,>=1.10
+Dynamic: license-file
+
+```
+# Introduction
+
+> You can generate and manage API keys from your Cortex Dashboard. All endpoints require an API key sent as a Bearer token in the Authorization header.
+
+Welcome to the Cortex SDK API Reference. This section documents every available endpoint and how to interact with them to power AI apps and agents with intelligent memory and retrieval.
+
+> Base URL: `https://api.usecortex.ai`
+>
+> Contact us to get your API key at [founders@usecortex.ai](mailto:founders@usecortex.ai)
+
+```mdx
+Authorization: Bearer <your_api_key>
+```
+
+### **Data Ingestion**
+
+Upload and import content into Cortex from various sources.
+
+* `/upload/upload_document` — Upload single documents
+* `/upload/upload_text` — Upload text/markdown content
+* `/upload/upload_app_sources` — Import from workplace apps (Gmail, Slack, etc.)
+* `/upload/scrape_webpage` — Scrape and index web content
+* `/upload/verify_processing` — Check upload processing status
+* `/upload/batch_upload` — Upload multiple files at once
+
+### **Search & Query**
+
+Retrieve answers and information from your knowledge base.
+
+* `/search/qna` — Main search endpoint with AI-powered responses. Supports optional `metadata` parameter to filter sources by `source_title` or `source_type`.
+* `/search/retrieve` — Hybrid search without AI generation. Returns structured search results for custom processing.
+  – `/search/full-text-search` – Perform a full text search without AI generation. Allows you to use operators like logical `AND`, `OR`
+
+### **Knowledge Management**
+
+Browse, fetch, and manage your knowledge base.
+
+* `/list/sources` — Browse all indexed sources
+* `/list/sources_by_id` — Get specific sources by ID
+* `/fetch/fetch_content` — Retrieve file content and download URLs
+* `/delete_source` — Remove sources from knowledge base
+
+### **Update & Upsert**
+
+Update existing content and embeddings. If a `source_id` does not exist, these endpoints upsert (create or update).
+
+* `/upload/update_text` — Upsert markdown/text content by `source_id`
+* `/upload/update_document` — Upsert a file/document by `source_id`
+* `/upload/update_webpage` — Re-scrape and upsert a webpage by `source_id` and `web_url`
+* `/upload/update_embeddings` — Update existing embeddings by `chunk_id` within a batch/source
+
+### **Embeddings**
+
+Manage and query pre-computed embeddings.
+
+* `/upload/upload_embeddings` — Upload embeddings and get generated `chunk_ids`
+* `/embeddings/search` — Vector similarity search; returns nearest `chunk_ids` and scores
+* `/embeddings/by-chunk-ids` — Retrieve embedding vectors for specific `chunk_ids`
+* `/embeddings/delete` — Delete embeddings by `chunk_id`
+
+### **Tenant Management**
+
+Create and monitor tenants for multi-tenant setups.
+
+* `/user/create_tenant` — Create a tenant (optionally provide `tenant_id`, or auto-generate)
+* `/embeddings/create_embeddings_tenant` — Create an embeddings-only tenant (sets `sub_tenant_id = tenant_id`); use when directly uploading/searching embeddings
+* `/tenant/stats` — Get tenant stats (object count, vector dimension, identifiers)
+
+### **User Memory**
+
+Personalize, retrieve, and manage user-specific AI memories for advanced agentic workflows.
+
+* `/user_memory/list_user_memories` — Browse user memories
+* `/user_memory/retrieve_user_memory` — Get specific user memories
+* `/user_memory/add_user_memory` — Manually add user-specific memories
+* `/user_memory/generate_user_memory` — AI-generated personalized memories
+* `/user_memory/delete_user_memory` — Remove user memories
+
+## 💡 Best Practices
+
+* Use **sub-tenants** to support multi-user isolation in B2B use cases.
+* Leverage **metadata** (e.g., `source_title`, `source_type` in the QnA API) for fine-grained filtering and agentic retrieval.
+* Tune **search\_alpha** and **recency\_bias** to control relevance.
+* Enable **highlight\_chunks** for chunk-level citations.
+
+---
+
+```
+
+```

usecortex_ai-0.1.0/README.md

@@ -0,0 +1,91 @@
+```
+# Introduction
+
+> You can generate and manage API keys from your Cortex Dashboard. All endpoints require an API key sent as a Bearer token in the Authorization header.
+
+Welcome to the Cortex SDK API Reference. This section documents every available endpoint and how to interact with them to power AI apps and agents with intelligent memory and retrieval.
+
+> Base URL: `https://api.usecortex.ai`
+>
+> Contact us to get your API key at [founders@usecortex.ai](mailto:founders@usecortex.ai)
+
+```mdx
+Authorization: Bearer <your_api_key>
+```
+
+### **Data Ingestion**
+
+Upload and import content into Cortex from various sources.
+
+* `/upload/upload_document` — Upload single documents
+* `/upload/upload_text` — Upload text/markdown content
+* `/upload/upload_app_sources` — Import from workplace apps (Gmail, Slack, etc.)
+* `/upload/scrape_webpage` — Scrape and index web content
+* `/upload/verify_processing` — Check upload processing status
+* `/upload/batch_upload` — Upload multiple files at once
+
+### **Search & Query**
+
+Retrieve answers and information from your knowledge base.
+
+* `/search/qna` — Main search endpoint with AI-powered responses. Supports optional `metadata` parameter to filter sources by `source_title` or `source_type`.
+* `/search/retrieve` — Hybrid search without AI generation. Returns structured search results for custom processing.
+  – `/search/full-text-search` – Perform a full text search without AI generation. Allows you to use operators like logical `AND`, `OR`
+
+### **Knowledge Management**
+
+Browse, fetch, and manage your knowledge base.
+
+* `/list/sources` — Browse all indexed sources
+* `/list/sources_by_id` — Get specific sources by ID
+* `/fetch/fetch_content` — Retrieve file content and download URLs
+* `/delete_source` — Remove sources from knowledge base
+
+### **Update & Upsert**
+
+Update existing content and embeddings. If a `source_id` does not exist, these endpoints upsert (create or update).
+
+* `/upload/update_text` — Upsert markdown/text content by `source_id`
+* `/upload/update_document` — Upsert a file/document by `source_id`
+* `/upload/update_webpage` — Re-scrape and upsert a webpage by `source_id` and `web_url`
+* `/upload/update_embeddings` — Update existing embeddings by `chunk_id` within a batch/source
+
+### **Embeddings**
+
+Manage and query pre-computed embeddings.
+
+* `/upload/upload_embeddings` — Upload embeddings and get generated `chunk_ids`
+* `/embeddings/search` — Vector similarity search; returns nearest `chunk_ids` and scores
+* `/embeddings/by-chunk-ids` — Retrieve embedding vectors for specific `chunk_ids`
+* `/embeddings/delete` — Delete embeddings by `chunk_id`
+
+### **Tenant Management**
+
+Create and monitor tenants for multi-tenant setups.
+
+* `/user/create_tenant` — Create a tenant (optionally provide `tenant_id`, or auto-generate)
+* `/embeddings/create_embeddings_tenant` — Create an embeddings-only tenant (sets `sub_tenant_id = tenant_id`); use when directly uploading/searching embeddings
+* `/tenant/stats` — Get tenant stats (object count, vector dimension, identifiers)
+
+### **User Memory**
+
+Personalize, retrieve, and manage user-specific AI memories for advanced agentic workflows.
+
+* `/user_memory/list_user_memories` — Browse user memories
+* `/user_memory/retrieve_user_memory` — Get specific user memories
+* `/user_memory/add_user_memory` — Manually add user-specific memories
+* `/user_memory/generate_user_memory` — AI-generated personalized memories
+* `/user_memory/delete_user_memory` — Remove user memories
+
+## 💡 Best Practices
+
+* Use **sub-tenants** to support multi-user isolation in B2B use cases.
+* Leverage **metadata** (e.g., `source_title`, `source_type` in the QnA API) for fine-grained filtering and agentic retrieval.
+* Tune **search\_alpha** and **recency\_bias** to control relevance.
+* Enable **highlight\_chunks** for chunk-level citations.
+
+---
+
+```
+
+```

usecortex_ai-0.1.0/pyproject.toml

@@ -0,0 +1,46 @@
+# pyproject.toml
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+# This is the name used for 'pip install usecortex-ai'
+name = "usecortex-ai"
+
+# Start with an initial version
+version = "0.1.0"
+
+authors = [
+  { name = "Nishkarsh Shrivastava", email = "nishkarsh@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 :: 4 - Beta",
+    "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/"
+# Add this if you have a public issue tracker
+# "Bug Tracker" = "https://github.com/your-org/your-repo/issues"
+

usecortex_ai-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

usecortex_ai-0.1.0/src/cortex_ai/__init__.py

@@ -0,0 +1,103 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+
+from .types import (
+    ActualErrorResponse,
+    AppSourcesUploadData,
+    AttachmentModel,
+    BatchUploadData,
+    Bm25OperatorType,
+    ContentModel,
+    DeleteMemoryRequest,
+    EmbeddingsCreateCollectionData,
+    EmbeddingsDeleteData,
+    EmbeddingsGetData,
+    EmbeddingsSearchData,
+    ErrorResponse,
+    ExtendedContext,
+    FetchContentData,
+    FileUploadResult,
+    FullTextSearchData,
+    HttpValidationError,
+    ListSourcesResponse,
+    MarkdownUploadRequest,
+    ProcessingStatus,
+    RelatedChunk,
+    SearchChunk,
+    SearchData,
+    SingleUploadData,
+    Source,
+    SourceContent,
+    SourceModel,
+    TenantCreateData,
+    TenantStats,
+    ValidationError,
+    ValidationErrorLocItem,
+)
+from .errors import (
+    BadRequestError,
+    ForbiddenError,
+    InternalServerError,
+    NotFoundError,
+    ServiceUnavailableError,
+    UnauthorizedError,
+    UnprocessableEntityError,
+)
+from . import embeddings, fetch, search, sources, tenant, upload, user, user_memory
+from .client import AsyncCortexAI, CortexAI
+from .environment import CortexAIEnvironment
+from .search import Alpha
+
+__all__ = [
+    "ActualErrorResponse",
+    "Alpha",
+    "AppSourcesUploadData",
+    "AsyncCortexAI",
+    "AttachmentModel",
+    "BadRequestError",
+    "BatchUploadData",
+    "Bm25OperatorType",
+    "ContentModel",
+    "CortexAI",
+    "CortexAIEnvironment",
+    "DeleteMemoryRequest",
+    "EmbeddingsCreateCollectionData",
+    "EmbeddingsDeleteData",
+    "EmbeddingsGetData",
+    "EmbeddingsSearchData",
+    "ErrorResponse",
+    "ExtendedContext",
+    "FetchContentData",
+    "FileUploadResult",
+    "ForbiddenError",
+    "FullTextSearchData",
+    "HttpValidationError",
+    "InternalServerError",
+    "ListSourcesResponse",
+    "MarkdownUploadRequest",
+    "NotFoundError",
+    "ProcessingStatus",
+    "RelatedChunk",
+    "SearchChunk",
+    "SearchData",
+    "ServiceUnavailableError",
+    "SingleUploadData",
+    "Source",
+    "SourceContent",
+    "SourceModel",
+    "TenantCreateData",
+    "TenantStats",
+    "UnauthorizedError",
+    "UnprocessableEntityError",
+    "ValidationError",
+    "ValidationErrorLocItem",
+    "embeddings",
+    "fetch",
+    "search",
+    "sources",
+    "tenant",
+    "upload",
+    "user",
+    "user_memory",
+]

usecortex_ai-0.1.0/src/cortex_ai/client.py

@@ -0,0 +1,244 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import httpx
+from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from .core.request_options import RequestOptions
+from .embeddings.client import AsyncEmbeddingsClient, EmbeddingsClient
+from .environment import CortexAIEnvironment
+from .fetch.client import AsyncFetchClient, FetchClient
+from .raw_client import AsyncRawCortexAI, RawCortexAI
+from .search.client import AsyncSearchClient, SearchClient
+from .sources.client import AsyncSourcesClient, SourcesClient
+from .tenant.client import AsyncTenantClient, TenantClient
+from .upload.client import AsyncUploadClient, UploadClient
+from .user.client import AsyncUserClient, UserClient
+from .user_memory.client import AsyncUserMemoryClient, UserMemoryClient
+
+
+class CortexAI:
+    """
+    Use this class to access the different functions within the SDK. You can instantiate any number of clients with different configuration that will propagate to these functions.
+
+    Parameters
+    ----------
+    base_url : typing.Optional[str]
+        The base url to use for requests from the client.
+
+    environment : CortexAIEnvironment
+        The environment to use for requests from the client. from .environment import CortexAIEnvironment
+
+
+
+        Defaults to CortexAIEnvironment.CORTEX_PROD
+
+
+
+    token : typing.Optional[typing.Union[str, typing.Callable[[], str]]]
+    headers : typing.Optional[typing.Dict[str, str]]
+        Additional headers to send with every request.
+
+    timeout : typing.Optional[float]
+        The timeout to be used, in seconds, for requests. By default the timeout is 60 seconds, unless a custom httpx client is used, in which case this default is not enforced.
+
+    follow_redirects : typing.Optional[bool]
+        Whether the default httpx client follows redirects or not, this is irrelevant if a custom httpx client is passed in.
+
+    httpx_client : typing.Optional[httpx.Client]
+        The httpx client to use for making requests, a preconfigured client is used by default, however this is useful should you want to pass in any custom httpx configuration.
+
+    Examples
+    --------
+    from cortex-ai import CortexAI
+
+    client = CortexAI(token="YOUR_TOKEN", )
+    """
+
+    def __init__(
+        self,
+        *,
+        base_url: typing.Optional[str] = None,
+        environment: CortexAIEnvironment = CortexAIEnvironment.CORTEX_PROD,
+        token: typing.Optional[typing.Union[str, typing.Callable[[], str]]] = None,
+        headers: typing.Optional[typing.Dict[str, str]] = None,
+        timeout: typing.Optional[float] = None,
+        follow_redirects: typing.Optional[bool] = True,
+        httpx_client: typing.Optional[httpx.Client] = None,
+    ):
+        _defaulted_timeout = (
+            timeout if timeout is not None else 60 if httpx_client is None else httpx_client.timeout.read
+        )
+        self._client_wrapper = SyncClientWrapper(
+            base_url=_get_base_url(base_url=base_url, environment=environment),
+            token=token,
+            headers=headers,
+            httpx_client=httpx_client
+            if httpx_client is not None
+            else httpx.Client(timeout=_defaulted_timeout, follow_redirects=follow_redirects)
+            if follow_redirects is not None
+            else httpx.Client(timeout=_defaulted_timeout),
+            timeout=_defaulted_timeout,
+        )
+        self._raw_client = RawCortexAI(client_wrapper=self._client_wrapper)
+        self.search = SearchClient(client_wrapper=self._client_wrapper)
+        self.sources = SourcesClient(client_wrapper=self._client_wrapper)
+        self.user_memory = UserMemoryClient(client_wrapper=self._client_wrapper)
+        self.fetch = FetchClient(client_wrapper=self._client_wrapper)
+        self.upload = UploadClient(client_wrapper=self._client_wrapper)
+        self.embeddings = EmbeddingsClient(client_wrapper=self._client_wrapper)
+        self.user = UserClient(client_wrapper=self._client_wrapper)
+        self.tenant = TenantClient(client_wrapper=self._client_wrapper)
+
+    @property
+    def with_raw_response(self) -> RawCortexAI:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        RawCortexAI
+        """
+        return self._raw_client
+
+    def root_get(self, *, request_options: typing.Optional[RequestOptions] = None) -> typing.Optional[typing.Any]:
+        """
+        Parameters
+        ----------
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        typing.Optional[typing.Any]
+            Successful Response
+
+        Examples
+        --------
+        from cortex-ai import CortexAI
+
+        client = CortexAI(token="YOUR_TOKEN", )
+        client.root_get()
+        """
+        _response = self._raw_client.root_get(request_options=request_options)
+        return _response.data
+
+
+class AsyncCortexAI:
+    """
+    Use this class to access the different functions within the SDK. You can instantiate any number of clients with different configuration that will propagate to these functions.
+
+    Parameters
+    ----------
+    base_url : typing.Optional[str]
+        The base url to use for requests from the client.
+
+    environment : CortexAIEnvironment
+        The environment to use for requests from the client. from .environment import CortexAIEnvironment
+
+
+
+        Defaults to CortexAIEnvironment.CORTEX_PROD
+
+
+
+    token : typing.Optional[typing.Union[str, typing.Callable[[], str]]]
+    headers : typing.Optional[typing.Dict[str, str]]
+        Additional headers to send with every request.
+
+    timeout : typing.Optional[float]
+        The timeout to be used, in seconds, for requests. By default the timeout is 60 seconds, unless a custom httpx client is used, in which case this default is not enforced.
+
+    follow_redirects : typing.Optional[bool]
+        Whether the default httpx client follows redirects or not, this is irrelevant if a custom httpx client is passed in.
+
+    httpx_client : typing.Optional[httpx.AsyncClient]
+        The httpx client to use for making requests, a preconfigured client is used by default, however this is useful should you want to pass in any custom httpx configuration.
+
+    Examples
+    --------
+    from cortex-ai import AsyncCortexAI
+
+    client = AsyncCortexAI(token="YOUR_TOKEN", )
+    """
+
+    def __init__(
+        self,
+        *,
+        base_url: typing.Optional[str] = None,
+        environment: CortexAIEnvironment = CortexAIEnvironment.CORTEX_PROD,
+        token: typing.Optional[typing.Union[str, typing.Callable[[], str]]] = None,
+        headers: typing.Optional[typing.Dict[str, str]] = None,
+        timeout: typing.Optional[float] = None,
+        follow_redirects: typing.Optional[bool] = True,
+        httpx_client: typing.Optional[httpx.AsyncClient] = None,
+    ):
+        _defaulted_timeout = (
+            timeout if timeout is not None else 60 if httpx_client is None else httpx_client.timeout.read
+        )
+        self._client_wrapper = AsyncClientWrapper(
+            base_url=_get_base_url(base_url=base_url, environment=environment),
+            token=token,
+            headers=headers,
+            httpx_client=httpx_client
+            if httpx_client is not None
+            else httpx.AsyncClient(timeout=_defaulted_timeout, follow_redirects=follow_redirects)
+            if follow_redirects is not None
+            else httpx.AsyncClient(timeout=_defaulted_timeout),
+            timeout=_defaulted_timeout,
+        )
+        self._raw_client = AsyncRawCortexAI(client_wrapper=self._client_wrapper)
+        self.search = AsyncSearchClient(client_wrapper=self._client_wrapper)
+        self.sources = AsyncSourcesClient(client_wrapper=self._client_wrapper)
+        self.user_memory = AsyncUserMemoryClient(client_wrapper=self._client_wrapper)
+        self.fetch = AsyncFetchClient(client_wrapper=self._client_wrapper)
+        self.upload = AsyncUploadClient(client_wrapper=self._client_wrapper)
+        self.embeddings = AsyncEmbeddingsClient(client_wrapper=self._client_wrapper)
+        self.user = AsyncUserClient(client_wrapper=self._client_wrapper)
+        self.tenant = AsyncTenantClient(client_wrapper=self._client_wrapper)
+
+    @property
+    def with_raw_response(self) -> AsyncRawCortexAI:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        AsyncRawCortexAI
+        """
+        return self._raw_client
+
+    async def root_get(self, *, request_options: typing.Optional[RequestOptions] = None) -> typing.Optional[typing.Any]:
+        """
+        Parameters
+        ----------
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        typing.Optional[typing.Any]
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from cortex-ai import AsyncCortexAI
+
+        client = AsyncCortexAI(token="YOUR_TOKEN", )
+        async def main() -> None:
+            await client.root_get()
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.root_get(request_options=request_options)
+        return _response.data
+
+
+def _get_base_url(*, base_url: typing.Optional[str] = None, environment: CortexAIEnvironment) -> str:
+    if base_url is not None:
+        return base_url
+    elif environment is not None:
+        return environment.value
+    else:
+        raise Exception("Please pass in either base_url or environment to construct the client")