fix readme/requirements

README.md

@@ -165,7 +165,7 @@ streamlit run web_demo_streamlit.py
 export MODEL_PATH=/models/chatglm3/chatglm3-6b
 export TOKENIZER_PATH=/models/chatglm3/chatglm3-6b
 export EMBEDDING_PATH=/home/model/BAAI/bge-m3/
-# 推理(案例中修改了api_server.py 536行的端口号，项目中的端口未更新，仍为8000端口)
+# 推理(案例中修改了api_server.py 536行的端口号为9000，根据端口占用情况自行修改)
 python api_server.py
 ```
 <div align="center">
@@ -174,7 +174,7 @@ python api_server.py
 
 #### api调用案例
 ```
-curl -X POST "http://127.0.0.1:8000/v1/chat/completions" \
+curl -X POST "http://127.0.0.1:9000/v1/chat/completions" \
 -H "Content-Type: application/json" \
 -d "{\"model\": \"chatglm3-6b\", \"messages\": [{\"role\": \"system\", \"content\": \"You are ChatGLM3, a large language model trained by Zhipu.AI. Follow the user's instructions carefully. Respond using markdown.\"}, {\"role\": \"user\", \"content\": \"你好，给我讲一个故事，大概100字\"}], \"stream\": false, \"max_tokens\": 100, \"temperature\": 0.8, \"top_p\": 0.8}"
 ```

requirements.txt

@@ -17,6 +17,7 @@ latex2mathml>=3.77.0
 jupyter_client>=8.6.1
 nltk
 peft==0.10.0
+sse_starlette
 
 # for openai demo
 #openai>=1.17.1