stratifyai 0.1.0__tar.gz

stratifyai-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Scott Jones
+
+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.

stratifyai-0.1.0/MANIFEST.in

@@ -0,0 +1,16 @@
+include README.md
+include LICENSE
+include requirements.txt
+include WARP.md
+
+recursive-include docs *.md
+recursive-include examples *.py *.md
+recursive-include llm_abstraction *.py
+recursive-include cli *.py
+recursive-include tests *.py
+
+global-exclude __pycache__
+global-exclude *.py[co]
+global-exclude .DS_Store
+global-exclude *.so
+global-exclude .gitignore

stratifyai-0.1.0/PKG-INFO

@@ -0,0 +1,263 @@
+Metadata-Version: 2.4
+Name: stratifyai
+Version: 0.1.0
+Summary: Unified multi-provider LLM abstraction module with intelligent routing, cost tracking, and caching
+Author-email: Steven Cotton <cototnbytes@gmail.com>
+Maintainer-email: Steven Cotton <cototnbytes@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/Bytes0211/stratifyai
+Project-URL: Repository, https://github.com/Bytes0211/stratifyai
+Project-URL: Documentation, https://github.com/Bytes0211/stratifyai#readme
+Project-URL: Bug Tracker, https://github.com/Bytes0211/stratifyai/issues
+Keywords: llm,openai,anthropic,google,gemini,ai,chatgpt,claude,deepseek,groq,grok,ollama,multi-provider,abstraction,routing,cost-tracking,caching
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=1.12.0
+Requires-Dist: anthropic>=0.18.0
+Requires-Dist: google-genai>=1.0.0
+Requires-Dist: aioboto3>=12.0.0
+Requires-Dist: boto3>=1.34.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: typing-extensions>=4.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=9.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Provides-Extra: cli
+Requires-Dist: typer>=0.9.0; extra == "cli"
+Requires-Dist: rich>=13.0.0; extra == "cli"
+Provides-Extra: web
+Requires-Dist: fastapi>=0.115.0; extra == "web"
+Requires-Dist: uvicorn[standard]>=0.34.0; extra == "web"
+Requires-Dist: websockets>=14.0; extra == "web"
+Provides-Extra: rag
+Requires-Dist: chromadb>=0.5.0; extra == "rag"
+Provides-Extra: all
+Requires-Dist: stratifyai[cli,dev,rag,web]; extra == "all"
+Dynamic: license-file
+
+![StratifyAI](stratifyai_trans_logo.png)
+
+
+# StratifyAI — Unified Multi‑Provider LLM Interface
+
+![Python](https://img.shields.io/badge/python-3.10%2B-blue) ![License](https://img.shields.io/badge/license-MIT-green) ![Tests](https://img.shields.io/badge/tests-300%2B%20passing-brightgreen) ![Providers](https://img.shields.io/badge/providers-9-orange)
+
+**Status:** Phase 7.8 Complete  
+**Providers:** 9 Operational  
+**Features:** Routing • RAG • Caching • Streaming • CLI • Web UI • Builder Pattern
+
+StratifyAI is a production‑ready Python framework that provides a unified interface for 9+ LLM providers, including OpenAI, Anthropic, Google, DeepSeek, Groq, Grok, OpenRouter, Ollama, and AWS Bedrock. It eliminates vendor lock‑in, simplifies multi‑model development, and enables intelligent routing, cost tracking, caching, streaming, and RAG workflows.
+
+---
+
+## Features
+
+### Core
+
+- Unified API for 9+ LLM providers
+- Async-first architecture with sync wrappers
+- Automatic provider detection
+- Cost tracking and budget enforcement
+- Latency tracking on all responses
+- Retry logic with fallback models
+- Streaming support for all providers
+- Response caching + provider prompt caching
+- Intelligent routing (cost, quality, latency, hybrid)
+- Capability filtering (vision, tools, reasoning)
+- Model metadata and context window awareness
+- **Builder pattern** for fluent configuration
+
+### Advanced
+
+- Large‑file handling with chunking and progressive summarization
+- File extraction (CSV schema, JSON schema, logs, code structure)
+- Auto model selection for extraction tasks
+- RAG pipeline with embeddings + vector DB (ChromaDB)
+- Semantic search and citation tracking
+- Rich/Typer CLI with interactive mode
+- Optional FastAPI web interface
+
+---
+
+## Installation
+
+```bash
+git clone https://github.com/Bytes0211/stratifyai.git
+cd stratifyai
+pip install -e .
+```
+
+Or using `uv`:
+
+```bash
+uv sync
+```
+
+---
+
+## Configuration
+
+```bash
+cp .env.example .env
+# Add your API keys
+```
+
+Check configured providers:
+
+```bash
+stratifyai check-keys
+```
+
+---
+
+## Quick Start
+
+### CLI Usage
+
+```bash
+stratifyai chat -p openai -m gpt-4o-mini -t "Hello"
+stratifyai route "Explain relativity" --strategy hybrid
+stratifyai interactive
+stratifyai cache-stats
+```
+
+### Python Example (LLMClient)
+
+```python
+from stratifyai import LLMClient
+from stratifyai.models import Message, ChatRequest, ChatResponse
+
+client: LLMClient = LLMClient()
+request: ChatRequest = ChatRequest(
+    model="gpt-4o-mini",
+    messages=[Message(role="user", content="Explain quantum computing")]
+)
+
+# Async (recommended)
+response: ChatResponse = await client.chat_completion(request)
+
+# Sync wrapper for scripts/CLI
+response: ChatResponse = client.chat_completion_sync(request)
+
+print(response.content)
+print(f"Cost: ${response.usage.cost_usd:.6f}")
+print(f"Latency: {response.latency_ms:.0f}ms")
+```
+
+### Python Example (Chat Package - Simplified)
+
+```python
+from stratifyai.chat import anthropic, openai
+from stratifyai.models import ChatResponse
+
+# Quick usage - model is always required
+response: ChatResponse = await anthropic.chat("Hello!", model="claude-sonnet-4-5")
+print(response.content)
+
+# With options
+response: ChatResponse = await openai.chat(
+    "Explain quantum computing",
+    model="gpt-4o-mini",
+    system="Be concise",
+    temperature=0.5
+)
+```
+
+### Builder Pattern (Fluent Configuration)
+
+```python
+from stratifyai.chat import anthropic
+from stratifyai.chat.builder import ChatBuilder
+from stratifyai.models import ChatResponse
+
+# Configure once, use multiple times
+client: ChatBuilder = (
+    anthropic
+    .with_model("claude-sonnet-4-5")
+    .with_system("You are a helpful assistant")
+    .with_temperature(0.7)
+)
+
+# All subsequent calls use the configured settings
+response: ChatResponse = await client.chat("Hello!")
+response: ChatResponse = await client.chat("Tell me more")
+
+# Stream with builder
+async for chunk in client.chat_stream("Write a story"):
+    print(chunk.content, end="", flush=True)
+```
+
+---
+
+## Routing
+
+- **Cost**: choose cheapest model
+- **Quality**: choose highest‑quality model
+- **Latency**: choose fastest model
+- **Hybrid (default)**: dynamic weighting based on complexity
+
+---
+
+## RAG
+
+- Embeddings (OpenAI)
+- ChromaDB vector storage
+- Semantic search
+- Document indexing
+- Retrieval‑augmented generation
+- Citation tracking
+
+---
+
+## Project Structure
+
+```
+stratifyai/
+├── llm_abstraction/      # Core package
+│   ├── providers/        # Provider implementations (9 providers)
+│   ├── router.py         # Intelligent routing
+│   ├── models.py         # Data models
+│   └── utils/            # Utilities (token counting, extraction)
+├── chat/                 # Simplified chat modules with builder pattern
+│   ├── builder.py        # ChatBuilder class
+│   └── stratifyai_*.py    # Provider-specific modules
+├── cli/                  # Typer CLI
+├── api/                  # Optional FastAPI server
+├── examples/             # Usage examples
+└── docs/                 # Technical documentation
+```
+
+---
+
+## Testing
+
+```bash
+pytest           # Run all tests
+pytest -v        # Verbose output
+```
+
+**Test Coverage:** 300+ tests across all modules
+
+---
+
+## License
+
+Internal project — All rights reserved.
+

stratifyai-0.1.0/README.md

@@ -0,0 +1,209 @@
+![StratifyAI](stratifyai_trans_logo.png)
+
+
+# StratifyAI — Unified Multi‑Provider LLM Interface
+
+![Python](https://img.shields.io/badge/python-3.10%2B-blue) ![License](https://img.shields.io/badge/license-MIT-green) ![Tests](https://img.shields.io/badge/tests-300%2B%20passing-brightgreen) ![Providers](https://img.shields.io/badge/providers-9-orange)
+
+**Status:** Phase 7.8 Complete  
+**Providers:** 9 Operational  
+**Features:** Routing • RAG • Caching • Streaming • CLI • Web UI • Builder Pattern
+
+StratifyAI is a production‑ready Python framework that provides a unified interface for 9+ LLM providers, including OpenAI, Anthropic, Google, DeepSeek, Groq, Grok, OpenRouter, Ollama, and AWS Bedrock. It eliminates vendor lock‑in, simplifies multi‑model development, and enables intelligent routing, cost tracking, caching, streaming, and RAG workflows.
+
+---
+
+## Features
+
+### Core
+
+- Unified API for 9+ LLM providers
+- Async-first architecture with sync wrappers
+- Automatic provider detection
+- Cost tracking and budget enforcement
+- Latency tracking on all responses
+- Retry logic with fallback models
+- Streaming support for all providers
+- Response caching + provider prompt caching
+- Intelligent routing (cost, quality, latency, hybrid)
+- Capability filtering (vision, tools, reasoning)
+- Model metadata and context window awareness
+- **Builder pattern** for fluent configuration
+
+### Advanced
+
+- Large‑file handling with chunking and progressive summarization
+- File extraction (CSV schema, JSON schema, logs, code structure)
+- Auto model selection for extraction tasks
+- RAG pipeline with embeddings + vector DB (ChromaDB)
+- Semantic search and citation tracking
+- Rich/Typer CLI with interactive mode
+- Optional FastAPI web interface
+
+---
+
+## Installation
+
+```bash
+git clone https://github.com/Bytes0211/stratifyai.git
+cd stratifyai
+pip install -e .
+```
+
+Or using `uv`:
+
+```bash
+uv sync
+```
+
+---
+
+## Configuration
+
+```bash
+cp .env.example .env
+# Add your API keys
+```
+
+Check configured providers:
+
+```bash
+stratifyai check-keys
+```
+
+---
+
+## Quick Start
+
+### CLI Usage
+
+```bash
+stratifyai chat -p openai -m gpt-4o-mini -t "Hello"
+stratifyai route "Explain relativity" --strategy hybrid
+stratifyai interactive
+stratifyai cache-stats
+```
+
+### Python Example (LLMClient)
+
+```python
+from stratifyai import LLMClient
+from stratifyai.models import Message, ChatRequest, ChatResponse
+
+client: LLMClient = LLMClient()
+request: ChatRequest = ChatRequest(
+    model="gpt-4o-mini",
+    messages=[Message(role="user", content="Explain quantum computing")]
+)
+
+# Async (recommended)
+response: ChatResponse = await client.chat_completion(request)
+
+# Sync wrapper for scripts/CLI
+response: ChatResponse = client.chat_completion_sync(request)
+
+print(response.content)
+print(f"Cost: ${response.usage.cost_usd:.6f}")
+print(f"Latency: {response.latency_ms:.0f}ms")
+```
+
+### Python Example (Chat Package - Simplified)
+
+```python
+from stratifyai.chat import anthropic, openai
+from stratifyai.models import ChatResponse
+
+# Quick usage - model is always required
+response: ChatResponse = await anthropic.chat("Hello!", model="claude-sonnet-4-5")
+print(response.content)
+
+# With options
+response: ChatResponse = await openai.chat(
+    "Explain quantum computing",
+    model="gpt-4o-mini",
+    system="Be concise",
+    temperature=0.5
+)
+```
+
+### Builder Pattern (Fluent Configuration)
+
+```python
+from stratifyai.chat import anthropic
+from stratifyai.chat.builder import ChatBuilder
+from stratifyai.models import ChatResponse
+
+# Configure once, use multiple times
+client: ChatBuilder = (
+    anthropic
+    .with_model("claude-sonnet-4-5")
+    .with_system("You are a helpful assistant")
+    .with_temperature(0.7)
+)
+
+# All subsequent calls use the configured settings
+response: ChatResponse = await client.chat("Hello!")
+response: ChatResponse = await client.chat("Tell me more")
+
+# Stream with builder
+async for chunk in client.chat_stream("Write a story"):
+    print(chunk.content, end="", flush=True)
+```
+
+---
+
+## Routing
+
+- **Cost**: choose cheapest model
+- **Quality**: choose highest‑quality model
+- **Latency**: choose fastest model
+- **Hybrid (default)**: dynamic weighting based on complexity
+
+---
+
+## RAG
+
+- Embeddings (OpenAI)
+- ChromaDB vector storage
+- Semantic search
+- Document indexing
+- Retrieval‑augmented generation
+- Citation tracking
+
+---
+
+## Project Structure
+
+```
+stratifyai/
+├── llm_abstraction/      # Core package
+│   ├── providers/        # Provider implementations (9 providers)
+│   ├── router.py         # Intelligent routing
+│   ├── models.py         # Data models
+│   └── utils/            # Utilities (token counting, extraction)
+├── chat/                 # Simplified chat modules with builder pattern
+│   ├── builder.py        # ChatBuilder class
+│   └── stratifyai_*.py    # Provider-specific modules
+├── cli/                  # Typer CLI
+├── api/                  # Optional FastAPI server
+├── examples/             # Usage examples
+└── docs/                 # Technical documentation
+```
+
+---
+
+## Testing
+
+```bash
+pytest           # Run all tests
+pytest -v        # Verbose output
+```
+
+**Test Coverage:** 300+ tests across all modules
+
+---
+
+## License
+
+Internal project — All rights reserved.
+