nfinitmonkeys-cortex-sdk 1.0.0__tar.gz

nfinitmonkeys_cortex_sdk-1.0.0/.gitignore

@@ -0,0 +1,16 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+dist/
+build/
+.eggs/
+*.egg
+.venv/
+venv/
+.env
+.pytest_cache/
+.coverage
+htmlcov/
+.mypy_cache/
+.ruff_cache/

nfinitmonkeys_cortex_sdk-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 InfiniteMonkeys
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+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.

nfinitmonkeys_cortex_sdk-1.0.0/PKG-INFO

@@ -0,0 +1,274 @@
+Metadata-Version: 2.4
+Name: nfinitmonkeys-cortex-sdk
+Version: 1.0.0
+Summary: Official Python SDK for the Cortex LLM Gateway API by InfiniteMonkeys
+Author: InfiniteMonkeys
+License-Expression: MIT
+License-File: LICENSE
+Keywords: ai,cortex,gateway,llm,sdk
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Requires-Dist: httpx>=0.24.0
+Requires-Dist: pydantic>=2.0
+Provides-Extra: dev
+Requires-Dist: coverage>=7.0; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.21; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: respx>=0.20; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Cortex Python SDK
+
+Python client for the Cortex LLM Gateway and Admin API.
+
+## Installation
+
+```bash
+pip install cortex-sdk
+```
+
+## Quick Start
+
+```python
+from cortex_sdk import CortexClient
+
+client = CortexClient(api_key="sk-cortex-...")
+
+# Chat completions
+response = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Hello!"}],
+)
+print(response.choices[0].message.content)
+
+client.close()
+```
+
+## Async Usage
+
+```python
+import asyncio
+from cortex_sdk import AsyncCortexClient
+
+async def main():
+    async with AsyncCortexClient(api_key="sk-cortex-...") as client:
+        response = await client.chat.completions.create(
+            model="default",
+            messages=[{"role": "user", "content": "Hello!"}],
+        )
+        print(response.choices[0].message.content)
+
+asyncio.run(main())
+```
+
+## Streaming
+
+```python
+# Sync streaming
+stream = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Tell me a story"}],
+    stream=True,
+)
+for chunk in stream:
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content, end="")
+
+# Async streaming
+stream = await async_client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Tell me a story"}],
+    stream=True,
+)
+async for chunk in stream:
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content, end="")
+```
+
+## Configuration
+
+```python
+client = CortexClient(
+    api_key="sk-cortex-...",
+    llm_base_url="https://cortexapi.nfinitmonkeys.com/v1",   # LLM gateway
+    admin_base_url="https://admin.nfinitmonkeys.com",         # Admin API
+    timeout=30.0,               # Request timeout (seconds)
+    streaming_timeout=300.0,    # Streaming timeout (seconds)
+    max_retries=3,              # Retry count for transient errors
+    extra_headers={"X-Custom": "value"},
+)
+```
+
+## LLM Gateway
+
+### Chat Completions
+
+```python
+response = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "What is Python?"},
+    ],
+    temperature=0.7,
+    max_tokens=500,
+)
+```
+
+### Text Completions
+
+```python
+response = client.completions.create(
+    model="gpt-3.5-turbo-instruct",
+    prompt="Once upon a time",
+    max_tokens=100,
+)
+print(response.choices[0].text)
+```
+
+### Embeddings
+
+```python
+response = client.embeddings.create(
+    model="text-embedding-ada-002",
+    input="Hello world",
+)
+print(response.data[0].embedding)
+```
+
+### Models
+
+```python
+models = client.models.list()
+for model in models.data:
+    print(model.id)
+```
+
+## Admin API
+
+### API Keys
+
+```python
+# List keys
+keys = client.keys.list()
+
+# Create key
+key = client.keys.create(name="Production", scopes=["chat", "embeddings"])
+
+# Delete key
+client.keys.delete("key-id")
+```
+
+### Teams
+
+```python
+# List / create / get / delete teams
+teams = client.teams.list()
+team = client.teams.create(name="Engineering")
+team = client.teams.get("team-id")
+client.teams.delete("team-id")
+
+# Members
+member = client.teams.add_member("team-id", email="alice@example.com", role="admin")
+client.teams.update_member("team-id", "member-id", role="viewer")
+client.teams.remove_member("team-id", "member-id")
+```
+
+### Usage & Performance
+
+```python
+stats = client.usage.get(params={"start_date": "2024-01-01"})
+limits = client.usage.limits()
+metrics = client.performance.get()
+```
+
+### Conversations
+
+```python
+convos = client.conversations.list()
+convo = client.conversations.create(title="My Chat", model="gpt-4")
+convo = client.conversations.get("conv-id")
+convo = client.conversations.update("conv-id", title="New Title")
+client.conversations.delete("conv-id")
+
+# Stream messages (SSE)
+for msg in client.conversations.messages("conv-id"):
+    print(msg.content)
+```
+
+### Iris (Document Extraction)
+
+```python
+job = client.iris.extract(
+    document_url="https://example.com/invoice.pdf",
+    schema_id="invoice-schema",
+)
+jobs = client.iris.list_jobs(limit=10)
+schemas = client.iris.list_schemas()
+```
+
+### Other Resources
+
+```python
+# Plugins & Optimizations
+plugins = client.plugins.list()
+opts = client.optimizations.get()
+
+# Admin models config
+models = client.admin_models.list()
+
+# PDF generation
+pdf = client.pdf.generate(content="# Report", template="default")
+
+# Web search
+results = client.web_search.search(query="Python programming", num_results=5)
+```
+
+## Error Handling
+
+```python
+from cortex_sdk import (
+    CortexError,
+    AuthenticationError,
+    RateLimitError,
+    NotFoundError,
+    InternalServerError,
+)
+
+try:
+    response = client.chat.completions.create(...)
+except AuthenticationError:
+    print("Invalid API key")
+except RateLimitError as e:
+    print(f"Rate limited. Retry after {e.retry_after}s")
+except NotFoundError:
+    print("Resource not found")
+except InternalServerError:
+    print("Server error — will be retried automatically")
+except CortexError as e:
+    print(f"SDK error: {e.message}")
+```
+
+## Retry Behavior
+
+The SDK automatically retries on HTTP 429, 500, 502, 503, and 504 with exponential backoff and jitter. The `Retry-After` header is respected when present. Configure with `max_retries` (default: 3).
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+## License
+
+MIT

nfinitmonkeys_cortex_sdk-1.0.0/README.md

@@ -0,0 +1,246 @@
+# Cortex Python SDK
+
+Python client for the Cortex LLM Gateway and Admin API.
+
+## Installation
+
+```bash
+pip install cortex-sdk
+```
+
+## Quick Start
+
+```python
+from cortex_sdk import CortexClient
+
+client = CortexClient(api_key="sk-cortex-...")
+
+# Chat completions
+response = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Hello!"}],
+)
+print(response.choices[0].message.content)
+
+client.close()
+```
+
+## Async Usage
+
+```python
+import asyncio
+from cortex_sdk import AsyncCortexClient
+
+async def main():
+    async with AsyncCortexClient(api_key="sk-cortex-...") as client:
+        response = await client.chat.completions.create(
+            model="default",
+            messages=[{"role": "user", "content": "Hello!"}],
+        )
+        print(response.choices[0].message.content)
+
+asyncio.run(main())
+```
+
+## Streaming
+
+```python
+# Sync streaming
+stream = client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Tell me a story"}],
+    stream=True,
+)
+for chunk in stream:
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content, end="")
+
+# Async streaming
+stream = await async_client.chat.completions.create(
+    model="default",
+    messages=[{"role": "user", "content": "Tell me a story"}],
+    stream=True,
+)
+async for chunk in stream:
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content, end="")
+```
+
+## Configuration
+
+```python
+client = CortexClient(
+    api_key="sk-cortex-...",
+    llm_base_url="https://cortexapi.nfinitmonkeys.com/v1",   # LLM gateway
+    admin_base_url="https://admin.nfinitmonkeys.com",         # Admin API
+    timeout=30.0,               # Request timeout (seconds)
+    streaming_timeout=300.0,    # Streaming timeout (seconds)
+    max_retries=3,              # Retry count for transient errors
+    extra_headers={"X-Custom": "value"},
+)
+```
+
+## LLM Gateway
+
+### Chat Completions
+
+```python
+response = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "What is Python?"},
+    ],
+    temperature=0.7,
+    max_tokens=500,
+)
+```
+
+### Text Completions
+
+```python
+response = client.completions.create(
+    model="gpt-3.5-turbo-instruct",
+    prompt="Once upon a time",
+    max_tokens=100,
+)
+print(response.choices[0].text)
+```
+
+### Embeddings
+
+```python
+response = client.embeddings.create(
+    model="text-embedding-ada-002",
+    input="Hello world",
+)
+print(response.data[0].embedding)
+```
+
+### Models
+
+```python
+models = client.models.list()
+for model in models.data:
+    print(model.id)
+```
+
+## Admin API
+
+### API Keys
+
+```python
+# List keys
+keys = client.keys.list()
+
+# Create key
+key = client.keys.create(name="Production", scopes=["chat", "embeddings"])
+
+# Delete key
+client.keys.delete("key-id")
+```
+
+### Teams
+
+```python
+# List / create / get / delete teams
+teams = client.teams.list()
+team = client.teams.create(name="Engineering")
+team = client.teams.get("team-id")
+client.teams.delete("team-id")
+
+# Members
+member = client.teams.add_member("team-id", email="alice@example.com", role="admin")
+client.teams.update_member("team-id", "member-id", role="viewer")
+client.teams.remove_member("team-id", "member-id")
+```
+
+### Usage & Performance
+
+```python
+stats = client.usage.get(params={"start_date": "2024-01-01"})
+limits = client.usage.limits()
+metrics = client.performance.get()
+```
+
+### Conversations
+
+```python
+convos = client.conversations.list()
+convo = client.conversations.create(title="My Chat", model="gpt-4")
+convo = client.conversations.get("conv-id")
+convo = client.conversations.update("conv-id", title="New Title")
+client.conversations.delete("conv-id")
+
+# Stream messages (SSE)
+for msg in client.conversations.messages("conv-id"):
+    print(msg.content)
+```
+
+### Iris (Document Extraction)
+
+```python
+job = client.iris.extract(
+    document_url="https://example.com/invoice.pdf",
+    schema_id="invoice-schema",
+)
+jobs = client.iris.list_jobs(limit=10)
+schemas = client.iris.list_schemas()
+```
+
+### Other Resources
+
+```python
+# Plugins & Optimizations
+plugins = client.plugins.list()
+opts = client.optimizations.get()
+
+# Admin models config
+models = client.admin_models.list()
+
+# PDF generation
+pdf = client.pdf.generate(content="# Report", template="default")
+
+# Web search
+results = client.web_search.search(query="Python programming", num_results=5)
+```
+
+## Error Handling
+
+```python
+from cortex_sdk import (
+    CortexError,
+    AuthenticationError,
+    RateLimitError,
+    NotFoundError,
+    InternalServerError,
+)
+
+try:
+    response = client.chat.completions.create(...)
+except AuthenticationError:
+    print("Invalid API key")
+except RateLimitError as e:
+    print(f"Rate limited. Retry after {e.retry_after}s")
+except NotFoundError:
+    print("Resource not found")
+except InternalServerError:
+    print("Server error — will be retried automatically")
+except CortexError as e:
+    print(f"SDK error: {e.message}")
+```
+
+## Retry Behavior
+
+The SDK automatically retries on HTTP 429, 500, 502, 503, and 504 with exponential backoff and jitter. The `Retry-After` header is respected when present. Configure with `max_retries` (default: 3).
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+## License
+
+MIT

nfinitmonkeys_cortex_sdk-1.0.0/cortex_sdk/__init__.py

@@ -0,0 +1,155 @@
+"""Cortex SDK — Python client for the Cortex LLM Gateway API."""
+
+from cortex_sdk.client import AsyncCortexClient, CortexClient
+from cortex_sdk.errors import (
+    APIError,
+    AuthenticationError,
+    ConnectionError,
+    CortexError,
+    InternalServerError,
+    NotFoundError,
+    PermissionDeniedError,
+    RateLimitError,
+    StreamError,
+    TimeoutError,
+    ValidationError,
+)
+from cortex_sdk.streaming import AsyncStream, Stream
+from cortex_sdk.types import (
+    APIKey,
+    APIKeyCreate,
+    APIKeyList,
+    ChatCompletion,
+    ChatCompletionChunk,
+    ChatCompletionRequest,
+    ChatMessage,
+    Choice,
+    ChoiceDelta,
+    ChoiceMessage,
+    Completion,
+    CompletionChoice,
+    CompletionChunk,
+    CompletionRequest,
+    Conversation,
+    ConversationCreate,
+    ConversationList,
+    ConversationMessage,
+    ConversationUpdate,
+    DeleteResponse,
+    EmbeddingData,
+    EmbeddingRequest,
+    EmbeddingResponse,
+    FunctionDefinition,
+    IrisExtractionRequest,
+    IrisJob,
+    IrisJobList,
+    IrisSchema,
+    IrisSchemaList,
+    Model,
+    ModelConfig,
+    ModelConfigList,
+    ModelList,
+    ModelPermission,
+    OptimizationSettings,
+    PDFGenerateRequest,
+    PDFGenerateResponse,
+    PerformanceMetrics,
+    Plugin,
+    PluginList,
+    ResponseFormat,
+    StreamChoice,
+    Team,
+    TeamCreate,
+    TeamList,
+    TeamMember,
+    TeamMemberAdd,
+    TeamMemberUpdate,
+    ToolDefinition,
+    Usage,
+    UsageLimits,
+    UsageRecord,
+    UsageStats,
+    WebSearchRequest,
+    WebSearchResponse,
+    WebSearchResult,
+)
+
+__all__ = [
+    # Clients
+    "CortexClient",
+    "AsyncCortexClient",
+    # Streams
+    "Stream",
+    "AsyncStream",
+    # Errors
+    "CortexError",
+    "APIError",
+    "AuthenticationError",
+    "PermissionDeniedError",
+    "NotFoundError",
+    "RateLimitError",
+    "InternalServerError",
+    "ConnectionError",
+    "TimeoutError",
+    "StreamError",
+    "ValidationError",
+    # Types
+    "ChatMessage",
+    "FunctionDefinition",
+    "ToolDefinition",
+    "ResponseFormat",
+    "ChatCompletionRequest",
+    "ChoiceDelta",
+    "ChoiceMessage",
+    "Choice",
+    "StreamChoice",
+    "Usage",
+    "ChatCompletion",
+    "ChatCompletionChunk",
+    "CompletionRequest",
+    "CompletionChoice",
+    "Completion",
+    "CompletionChunk",
+    "EmbeddingRequest",
+    "EmbeddingData",
+    "EmbeddingResponse",
+    "Model",
+    "ModelPermission",
+    "ModelList",
+    "APIKey",
+    "APIKeyCreate",
+    "APIKeyList",
+    "TeamMember",
+    "Team",
+    "TeamCreate",
+    "TeamMemberAdd",
+    "TeamMemberUpdate",
+    "TeamList",
+    "UsageRecord",
+    "UsageStats",
+    "UsageLimits",
+    "PerformanceMetrics",
+    "ConversationMessage",
+    "Conversation",
+    "ConversationCreate",
+    "ConversationUpdate",
+    "ConversationList",
+    "IrisExtractionRequest",
+    "IrisJob",
+    "IrisJobList",
+    "IrisSchema",
+    "IrisSchemaList",
+    "Plugin",
+    "PluginList",
+    "OptimizationSettings",
+    "ModelConfig",
+    "ModelConfigList",
+    "PDFGenerateRequest",
+    "PDFGenerateResponse",
+    "WebSearchRequest",
+    "WebSearchResult",
+    "WebSearchResponse",
+    "DeleteResponse",
+]
+
+__version__ = "0.1.0"