1 line
48 KiB
JSON
1 line
48 KiB
JSON
{"repo": "anannas-ai/anannas-pipecat-integration", "files": {"README.md": {"dc70d914f33670f7ccadb9f8cf8eb80b8f3597f2": {"t": 1785746478.0328667, "n": 5607, "h": "66b35cf867f3905e", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 1B+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-5-codex, gpt-5-pro, gpt-5-chat, and more\n- **Anthropic**: claude-opus-4.1, claude-opus-4, claude-sonnet-4.5\n- **Mistral**: magistral-medium-2506, codestral-2508, devstral-medium\n- **Google**: gemini-2.5-flash-image-preview, gemma-2-27b-it\n- **DeepSeek**: deepseek-chat, deepseek-r1\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "b4824ebc91caecaa8c5635f1ffb72a7c07870c96": {"t": 1785764760.046124, "n": 5607, "h": "66b35cf867f3905e", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 1B+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-5-codex, gpt-5-pro, gpt-5-chat, and more\n- **Anthropic**: claude-opus-4.1, claude-opus-4, claude-sonnet-4.5\n- **Mistral**: magistral-medium-2506, codestral-2508, devstral-medium\n- **Google**: gemini-2.5-flash-image-preview, gemma-2-27b-it\n- **DeepSeek**: deepseek-chat, deepseek-r1\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "37236231635bac2e7819ff5324a73f3a4d63cdcc": {"t": 1785764761.4505074, "n": 5589, "h": "16bc7ab6e0ae7180", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 1B+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more\n- **Anthropic**: claude-3-5-sonnet-20241022, claude-3-opus, claude-3-sonnet\n- **Mistral**: mistral-large, mistral-medium, mistral-small\n- **Google**: gemini-pro, gemini-1.5-pro\n- **DeepSeek**: deepseek-chat, deepseek-coder\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "18612908b99a900c133d175b1b7a8953c9c4e0fa": {"t": 1785764763.173361, "n": 5591, "h": "20efa28884407953", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 100M+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more\n- **Anthropic**: claude-3-5-sonnet-20241022, claude-3-opus, claude-3-sonnet\n- **Mistral**: mistral-large, mistral-medium, mistral-small\n- **Google**: gemini-pro, gemini-1.5-pro\n- **DeepSeek**: deepseek-chat, deepseek-coder\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "7d9b740ca3a821724bc8ad2137d9923fbf3e7bb4": {"t": 1785764764.8767014, "n": 5710, "h": "659767e6ddcc5785", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 100M+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more\n- **Anthropic**: claude-3-5-sonnet-20241022, claude-3-opus, claude-3-sonnet\n- **Mistral**: mistral-large, mistral-medium, mistral-small\n- **Google**: gemini-pro, gemini-1.5-pro\n- **DeepSeek**: deepseek-chat, deepseek-coder\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team. We're committed to keeping this integration up-to-date with the latest Pipecat releases and providing ongoing support.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "ee96e483151578ae866d02cf2bade388162ed78d": {"t": 1785764766.1366444, "n": 5800, "h": "796b424ce93f7068", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 100M+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more\n- **Anthropic**: claude-3-5-sonnet-20241022, claude-3-opus, claude-3-sonnet\n- **Mistral**: mistral-large, mistral-medium, mistral-small\n- **Google**: gemini-pro, gemini-1.5-pro\n- **DeepSeek**: deepseek-chat, deepseek-coder\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\nThis integration extends `OpenAILLMService` and is compatible with all Pipecat features:\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team. We're committed to keeping this integration up-to-date with the latest Pipecat releases and providing ongoing support.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "2e39b39dc810263fd83b373f7a1425924484b5ca": {"t": 1785764767.4561114, "n": 5930, "h": "256d090ae0c85663", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 100M+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more\n- **Anthropic**: claude-3-5-sonnet-20241022, claude-3-opus, claude-3-sonnet\n- **Mistral**: mistral-large, mistral-medium, mistral-small\n- **Google**: gemini-pro, gemini-1.5-pro\n- **DeepSeek**: deepseek-chat, deepseek-coder\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\nThis integration extends `OpenAILLMService` and is compatible with all Pipecat features:\n\n- ✅ Streaming responses\n- ✅ Function calling / tool use\n- ✅ Context management\n- ✅ Multi-modal support\n- ✅ Interruption handling\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team. We're committed to keeping this integration up-to-date with the latest Pipecat releases and providing ongoing support.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}, "f937d4e432af953796b9932eb2f4ff112b14222a": {"t": 1785764768.9095821, "n": 6163, "h": "53553dfdc7b4f761", "c": "# Anannas AI Integration for Pipecat\n\nAn OpenAI-compatible LLM service integration for Pipecat that provides access to 500+ models through Anannas AI's unified gateway.\n\n## About Anannas AI\n\nAnannas AI is a unified inference gateway that provides access to 500+ models from OpenAI, Anthropic, Mistral, Gemini, DeepSeek, and other providers through a single OpenAI-compatible API. Key features include:\n\n- **Unified API**: Access 500+ models through one consistent interface\n- **Built-in Observability**: Cache hit rate analytics, token-level metrics, tool/function call analytics, and model efficiency scoring\n- **Smart Routing**: Automatic provider health monitoring and failover with ~0.48ms overhead\n- **Cost Optimization**: 5% markup with transparent pricing\n- **Enterprise Ready**: BYOK (Bring Your Own Key) support for secure deployments\n- **Production Proven**: Powering deployments with 100k+ requests and 100M+ tokens processed\n\n## Installation\n\nInstall the package from PyPI:\n\n```bash\npip install pipecat-anannas\n```\n\nOr install from source:\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e .\n```\n\n## Quick Start\n\n```python\nimport os\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\n\n# Initialize Anannas LLM service\nllm = AnannasLLMService(\n api_key=os.getenv(\"ANANNAS_API_KEY\"),\n model=\"gpt-4o\" # or any supported model\n)\n\n# Use in your Pipecat pipeline\npipeline = Pipeline([\n # ... your pipeline components\n llm,\n # ... more components\n])\n```\n\n## Supported Models\n\nAnannas AI provides access to models from multiple providers:\n\n- **OpenAI**: gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more\n- **Anthropic**: claude-3-5-sonnet-20241022, claude-3-opus, claude-3-sonnet\n- **Mistral**: mistral-large, mistral-medium, mistral-small\n- **Google**: gemini-pro, gemini-1.5-pro\n- **DeepSeek**: deepseek-chat, deepseek-coder\n- And 500+ more models...\n\n## Usage with Pipecat Pipeline\n\n### Basic Example\n\n```python\nimport os\nfrom dotenv import load_dotenv\n\nfrom pipecat_anannas import AnannasLLMService\nfrom pipecat.pipeline.pipeline import Pipeline\nfrom pipecat.pipeline.task import PipelineTask\nfrom pipecat.services.deepgram.stt import DeepgramSTTService\nfrom pipecat.services.azure.tts import AzureTTSService\n\nload_dotenv()\n\n# Create services\nstt = DeepgramSTTService(api_key=os.getenv(\"DEEPGRAM_API_KEY\"))\nllm = AnannasLLMService(api_key=os.getenv(\"ANANNAS_API_KEY\"), model=\"gpt-4o\")\ntts = AzureTTSService(\n api_key=os.getenv(\"AZURE_SPEECH_API_KEY\"),\n region=os.getenv(\"AZURE_SPEECH_REGION\")\n)\n\n# Build pipeline\npipeline = Pipeline([stt, llm, tts])\ntask = PipelineTask(pipeline)\n```\n\n### Function Calling Example\n\nSee the complete function calling example in `examples/function_calling_example.py`. This demonstrates:\n\n- Setting up Anannas LLM service\n- Registering function handlers\n- Using function calling in a voice conversation\n- Streaming responses\n\nTo run the example:\n\n```bash\n# Set required environment variables\nexport ANANNAS_API_KEY=your_api_key\nexport DEEPGRAM_API_KEY=your_deepgram_key\nexport AZURE_SPEECH_API_KEY=your_azure_key\nexport AZURE_SPEECH_REGION=your_azure_region\n\n# Run the example\npython examples/function_calling_example.py\n```\n\n## Configuration\n\n### Environment Variables\n\n- `ANANNAS_API_KEY`: Your Anannas AI API key (required)\n\n### Service Parameters\n\n```python\nAnannasLLMService(\n api_key: Optional[str] = None, # API key or use ANANNAS_API_KEY env var\n model: str = \"gpt-4o\", # Model to use\n base_url: str = \"https://api.anannas.ai/v1\", # API endpoint\n **kwargs # Additional OpenAI-compatible parameters\n)\n```\n\n## Observability\n\nAnannas AI provides built-in observability through its dashboard:\n\n- **Cache Analytics**: Monitor cache hit rates to optimize costs\n- **Token Metrics**: Track token usage across models and requests\n- **Function Call Analytics**: Analyze tool/function call patterns\n- **Model Efficiency**: Compare performance across different models\n- **Provider Health**: Real-time monitoring of provider availability\n\nAccess your dashboard at: https://anannas.ai/dashboard\n\n## Enterprise Features\n\n### BYOK (Bring Your Own Key)\n\nFor enterprise deployments requiring direct API keys to providers:\n\n- Use your own OpenAI, Anthropic, or other provider API keys\n- Maintain full control over credentials\n- Transparent cost tracking\n\nLearn more: https://docs.anannas.ai/UseCases/BYOK\n\n## Pipecat Compatibility\n\n**Tested with Pipecat:** v0.0.86+\n\nThis integration extends `OpenAILLMService` and is compatible with all Pipecat features:\n\n- ✅ Streaming responses\n- ✅ Function calling / tool use\n- ✅ Context management\n- ✅ Multi-modal support\n- ✅ Interruption handling\n\n## Development\n\n### Setting Up for Development\n\n```bash\ngit clone https://github.com/upsurgeio/anannas-pipecat-integration.git\ncd anannas-pipecat-integration\npip install -e \".[dev]\"\n```\n\n### Running Tests\n\n```bash\npytest tests/\n```\n\n## Links\n\n- **Anannas AI Homepage**: https://anannas.ai\n- **Documentation**: https://docs.anannas.ai\n- **Quickstart Guide**: https://docs.anannas.ai/quickstart\n- **Enterprise**: https://anannas.ai/enterprise\n- **BYOK Documentation**: https://docs.anannas.ai/UseCases/BYOK\n- **Pipecat Documentation**: https://docs.pipecat.ai\n\n## Support\n\n- **Issues**: https://github.com/upsurgeio/anannas-pipecat-integration/issues\n- **Pipecat Discord**: https://discord.gg/pipecat (#community-integrations channel)\n- **Anannas Support**: support@anannas.ai\n\n## Maintainer\n\nThis integration is maintained by the Anannas AI team. We're committed to keeping this integration up-to-date with the latest Pipecat releases and providing ongoing support.\n\n## License\n\nBSD 2-Clause License - see [LICENSE](LICENSE) file for details.\n\nThis license is compatible with Pipecat's BSD 2-Clause License, ensuring seamless integration.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit issues or pull requests.\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for version history and updates.\n\n"}}}} |