forward chatgpt example (#90)

.env.chatgpt

@@ -0,0 +1,43 @@
+LOG_CHAT=true
+
+CACHE_CHAT_COMPLETION=true
+
+# `CACHE_BACKEND`: Options (MEMORY, LMDB, LevelDB)
+CACHE_BACKEND=LMDB
+
+#LOG_CACHE_DB_INFO=true
+
+OPENAI_BASE_URL='https://api.openai.com/v1'
+OPENAI_ROUTE_PREFIX='/v1'
+
+CHAT_COMPLETION_ROUTE=/chat/completions
+COMPLETION_ROUTE=/completions
+
+#OPENAI_API_KEY=
+#FORWARD_KEY=
+
+
+EXTRA_BASE_URL='http://chatgpt:7999'
+EXTRA_ROUTE_PREFIX='/'
+
+REQ_RATE_LIMIT={"/v1/chat/completions":"100/2minutes", "/v1/completions":"60/minute;600/hour"}
+
+#GLOBAL_RATE_LIMIT=100/minute
+
+#`RATE_LIMIT_STRATEGY` Options: (fixed-window, fixed-window-elastic-expiry, moving-window) :ref: https://limits.readthedocs.io/en/latest/strategies.html
+# `fixed-window`: most memory efficient strategy; `moving-window`:most effective for preventing bursts but has higher memory cost.
+RATE_LIMIT_STRATEGY=moving-window
+
+# Rate limit for returned tokens
+TOKEN_RATE_LIMIT={"/v1/chat/completions":"60/second","/v1/completions":"60/second"}
+
+# TCP connection timeout duration (in seconds)
+TIMEOUT=6
+
+ITER_CHUNK_TYPE=one-by-one
+#ITER_CHUNK_TYPE=efficiency
+
+#IP_BLACKLIST=
+
+# Set timezone
+TZ=Asia/Shanghai

.env.example

@@ -5,8 +5,8 @@ LOG_CHAT=true
 #PRINT_CHAT=true
 
 CACHE_CHAT_COMPLETION=true
-# `CACHE_BACKEND`: Options (MEMORY, LMDB, ROCKSDB, LevelDB)
-CACHE_BACKEND=MEMORY
+# `CACHE_BACKEND`: Options (MEMORY, LMDB, LevelDB)
+CACHE_BACKEND=LMDB
 
 BENCHMARK_MODE=true
 

README.md

@@ -39,7 +39,7 @@
 
 </div>
 
-**OpenAI-Forward** 是为大型语言模型设计的高效转发服务。其核心功能包括
+**OpenAI-Forward** 是为大型语言模型实现的高效转发服务。其核心功能包括
 用户请求速率控制、Token速率限制、智能预测缓存、日志管理和API密钥管理等，旨在提供高效、便捷的模型转发服务。
 无论是代理本地语言模型还是云端语言模型，如 [LocalAI](https://github.com/go-skynet/LocalAI) 或 [OpenAI](https://api.openai.com)，都可以由 OpenAI Forward 轻松实现。
 凭借  [uvicorn](https://github.com/encode/uvicorn), [aiohttp](https://github.com/aio-libs/aiohttp), 和 [asyncio](https://docs.python.org/3/library/asyncio.html)
@@ -155,8 +155,6 @@ docker run -d \
     yidadaa/chatgpt-next-web 
 ``` 
 
-#### 在代码中接入
-
 **Python**
 
 ```diff
@@ -165,29 +163,6 @@ docker run -d \
   openai.api_key = "sk-******"
 ```
 
-**JS/TS**
-
-```diff
-  import { Configuration } from "openai";
-
-  const configuration = new Configuration({
-+ basePath: "https://api.openai-forward.com/v1",
-  apiKey: "sk-******",
-  });
-```
-
-**gpt-3.5-turbo**
-
-```bash
-curl https://api.openai-forward.com/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-******" \
-  -d '{
-    "model": "gpt-3.5-turbo",
-    "messages": [{"role": "user", "content": "Hello!"}]
-  }'
-```
-
 **Image Generation (DALL-E)**
 
 ```bash
@@ -224,6 +199,10 @@ curl --location 'https://api.openai-forward.com/v1/images/generations' \
 
 (更多)
 
+### 代理ChatGPT
+参考根路径下 `docker-compose.yaml` 和 `.env.chatgpt`
+
+
 <a>
    <img src="https://raw.githubusercontent.com/KenyonY/openai-forward/main/.github/images/separators/aqua.png" height=8px width="100%">
 </a>

docker-compose.yaml

@@ -16,11 +16,12 @@ services:
       - --workers=1
     restart: unless-stopped
     depends_on:
-      - ninja
+      - chatgpt
 
-  ninja:
+  chatgpt:
+      # use project: https://github.com/gngpp/ninja
       image: ghcr.io/gngpp/ninja:latest
-      container_name: ninja
+      container_name: chatgpt
       restart: unless-stopped
       environment:
         - TZ=Asia/Shanghai