diff --git a/README.md b/README.md index 5cb3b71..e3227e3 100644 --- a/README.md +++ b/README.md @@ -2,9 +2,6 @@ **Async semantic caching for LLM API calls — reduce costs with one decorator.** -[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) -[![Python](https://img.shields.io/pypi/pyversions/semantic-llm-cache)](https://pypi.org/project/semantic-llm-cache/) - > **Fork of [karthyick/prompt-cache](https://github.com/karthyick/prompt-cache)** — fully converted to async for use with async frameworks (FastAPI, aiohttp, Starlette, etc.). ## Overview @@ -30,7 +27,7 @@ LLM API calls are expensive and slow. In production applications, **20-40% of pr | `CachedLLM` | `chat()` | adds`achat()` | | Utility functions | sync | `clear_cache`, `invalidate`, `warm_cache`, `export_cache` all async | | `StorageBackend` ABC | sync abstract methods | all abstract methods are`async def` | -| Min Python | 3.9 | 3.10 (uses`X | Y` union syntax) | +| Min Python | 3.9 | 3.10 (uses`X | ## Installation @@ -38,7 +35,7 @@ Not yet published to PyPI. Install directly from the repository: ```bash # Clone -git clone https://github.com/YOUR_ORG/prompt-cache.git +git clone https://github.com/nomyo-ai/async-semantic-llm-cache.git cd prompt-cache # Core (exact match only, SQLite backend) @@ -199,14 +196,14 @@ async def my_llm_function(prompt: str) -> str: ### Parameters -| Parameter | Type | Default | Description | -| -------------- | -------------- | ------------- | ----------------------------------------------------------- | -| `similarity` | `float` | `1.0` | Cosine similarity threshold (1.0 = exact, 0.9 = semantic) | -| `ttl` | `int | None` | `3600` | Time-to-live in seconds (None = never expires) | -| `backend` | `Backend` | `None` | Storage backend (None = in-memory) | -| `namespace` | `str` | `"default"` | Isolate different use cases | -| `enabled` | `bool` | `True` | Enable/disable caching | -| `key_func` | `Callable` | `None` | Custom cache key function | +| Parameter | Type | Default | Description | +| -------------- | ------------ | ------------- | ----------------------------------------------------------- | +| `similarity` | `float` | `1.0` | Cosine similarity threshold (1.0 = exact, 0.9 = semantic) | +| `ttl` | `int | None` | `3600` | +| `backend` | `Backend` | `None` | Storage backend (None = in-memory) | +| `namespace` | `str` | `"default"` | Isolate different use cases | +| `enabled` | `bool` | `True` | Enable/disable caching | +| `key_func` | `Callable` | `None` | Custom cache key function | ### Utility Functions