Add a simple GPTCache server (#244)

Signed-off-by: SimFG <[email protected]>

docs/release_note.md

@@ -5,6 +5,46 @@ To read the following content, you need to understand the basic use of GPTCache,
 - [Readme doc](https://github.com/zilliztech/GPTCache)
 - [Usage doc](https://github.com/zilliztech/GPTCache/blob/main/docs/usage.md)
 
+## v0.1.16 (2023.4.18)
+
+1. Add StableDiffusion adapter (**experimental**)
+
+```python
+import torch
+
+from gptcache.adapter.diffusers import StableDiffusionPipeline
+from gptcache.processor.pre import get_prompt
+from gptcache import cache
+
+cache.init(
+    pre_embedding_func=get_prompt,
+)
+model_id = "stabilityai/stable-diffusion-2-1"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe(prompt=prompt).images[0]
+```
+
+2. Add speech to text bootcamp, [link](https://github.com/zilliztech/GPTCache/tree/main/docs/bootcamp/openai/speech_to_text.ipynb)
+
+3. More convenient management of cache files
+
+```python
+from gptcache.manager.factory import manager_factory
+
+data_manager = manager_factory('sqlite,faiss', data_dir="test_cache", vector_params={"dimension": 5})
+```
+
+4. Add a simple GPTCache server (**experimental**)
+
+After starting this server, you can:
+
+- put the data to cache, like: `curl -X PUT -d "receive a hello message" "http://localhost:8000?prompt=hello"`
+- get the data from cache, like: `curl -X GET  "http://localhost:8000?prompt=hello"`
+
+Currently the service is just a map cache, more functions are still under development.
+
 ## v0.1.15 (2023.4.17)
 
 1. Add GPTCache api, makes it easier to access other different llm models and applications

gptcache_server/__init__.py

@@ -0,0 +1 @@
+from gptcache_server.server import start_server

gptcache_server/server.py

@@ -0,0 +1,52 @@
+import argparse
+import http.server
+import json
+
+from gptcache import cache
+from gptcache.adapter.api import get, put
+from gptcache.processor.pre import get_prompt
+
+
+class GPTCacheHandler(http.server.BaseHTTPRequestHandler):
+    # curl -X GET  "http://localhost:8000?prompt=hello"
+    def do_GET(self):
+        params = self.path.split("?")[1]
+        prompt = params.split("=")[1]
+
+        result = get(prompt)
+
+        response = json.dumps(result)
+
+        self.send_response(200)
+        self.send_header("Content-type", "application/json")
+        self.end_headers()
+        self.wfile.write(bytes(response, "utf-8"))
+
+    # curl -X PUT -d "receive a hello message" "http://localhost:8000?prompt=hello"
+    def do_PUT(self):
+        params = self.path.split("?")[1]
+        prompt = params.split("=")[1]
+        content_length = int(self.headers.get("Content-Length", "0"))
+        data = self.rfile.read(content_length).decode("utf-8")
+
+        put(prompt, data)
+
+        self.send_response(200)
+        self.end_headers()
+
+
+def start_server(host: str, port: int):
+    httpd = http.server.HTTPServer((host, port), GPTCacheHandler)
+    print(f"Starting server at {host}:{port}")
+    httpd.serve_forever()
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--host", default="localhost", help="the hostname to listen on")
+    parser.add_argument("--port", type=int, default=8000, help="the port to listen on")
+    args = parser.parse_args()
+
+    cache.init(pre_embedding_func=get_prompt)
+
+    start_server(args.host, args.port)

setup.py

@@ -17,7 +17,7 @@ def parse_requirements(file_name: str) -> List[str]:
 setuptools.setup(
     name="gptcache",
     packages=find_packages(),
-    version="0.1.15",
+    version="0.1.16",
     author="SimFG",
     author_email="[email protected]",
     description="GPTCache, a powerful caching library that can be used to speed up and lower the cost of chat "