Update neuralchat readme (#1286)

Author: VincyZhang

docker/README_chatbot.md

@@ -13,7 +13,7 @@ cd itrex
 ### Build Docker Image on CPU
 ```bash
 cd itrex
-docker build -f docker/Dockerfile_chatbot --target cpu --network=host -t chatbot:latest .
+docker build -f docker/Dockerfile_chatbot --build-arg ITREX_VER=main --target cpu --network=host -t chatbot:latest .
 ```
 If you need to use proxy, please use the following command
 ```bash
@@ -35,7 +35,7 @@ docker pull intel/ai-tools:itrex-chatbot
 ## Use Docker Image
 Utilize the docker container based on docker image.
 ```bash
-docker run -itd --net=host --ipc=host intel/ai-tools:itrex-chatbot /bin/bash
+docker run -itd --net=host --ipc=host <image_id> /bin/bash
 docker exec -it <container_id> /bin/bash
 ```
 

docs/installation.md

@@ -61,6 +61,9 @@ The following prerequisites and requirements must be satisfied for a successful
 - GCC >= version 10 (on Linux)
 - Visual Studio (on Windows)
 
+ >**Note**: If your system only have python3 or you meet error `python: command not found`, please run `ln -sf $(which python3) /usr/bin/python`.
+ 
+
 ### Install Intel Extension for Transformers
 ```Bash
 git clone https://github.com/intel/intel-extension-for-transformers.git itrex

intel_extension_for_transformers/neural_chat/README.md

@@ -24,6 +24,19 @@ NeuralChat is a powerful and flexible open framework that empowers you to effort
 
 > NeuralChat is under active development. APIs are subject to change.
 
+# System Requirements
+
+Please make sure below basic system libraries are installed. If you want to try more features, please refer to [system requirements](../../docs/installation.md#system-requirements)
+
+
+```shell
+apt-get update
+apt-get install -y python3-pip
+apt-get install -y libgl1-mesa-glx
+```
+ >**Note**: If your system only have python3 or you meet error `python: command not found`, please run `ln -sf $(which python3) /usr/bin/python`.
+
+
 # Installation
 
 NeuralChat is under Intel Extension for Transformers, so ensure the installation of Intel Extension for Transformers first by following the [installation](../../docs/installation.md). After that, install additional dependency for NeuralChat per your device:
@@ -86,7 +99,7 @@ Then, interact with the model:
 ```python
 import openai
 openai.api_key = "EMPTY"
-openai.base_url = 'http://127.0.0.1:80/v1/'
+openai.base_url = 'http://127.0.0.1:8000/v1/'
 response = openai.chat.completions.create(
       model="Intel/neural-chat-7b-v3-1",
       messages=[
@@ -96,10 +109,12 @@ response = openai.chat.completions.create(
 )
 print(response.choices[0].message.content)
 ```
+>**Note**: When intel-extension-for-transformers <= 1.3.1, please try [command](#using-curl) below
+
 
 #### Using Curl
 ```shell
-curl http://127.0.0.1:80/v1/chat/completions \
+curl http://127.0.0.1:8000/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
     "model": "Intel/neural-chat-7b-v3-1",
@@ -110,11 +125,17 @@ curl http://127.0.0.1:80/v1/chat/completions \
     }'
 ```
 
+>**Note**: When intel-extension-for-transformers <= 1.3.1, please use old command like:
+> ```shell
+> curl -X POST -H "Content-Type: application/json" -d '{"prompt": "Tell me about Intel Xeon Scalable Processors."}' http://127.0.0.1:8000/v1/chat/completions
+> ```
+
+
 #### Using Python Requests Library
 
 ```python
 import requests
-url = 'http://127.0.0.1:80/v1/chat/completions'
+url = 'http://127.0.0.1:8000/v1/chat/completions'
 headers = {'Content-Type': 'application/json'}
 data = '{"model": "Intel/neural-chat-7b-v3-1", "messages": [ \
           {"role": "system", "content": "You are a helpful assistant."}, \
@@ -124,6 +145,9 @@ response = requests.post(url, headers=headers, data=data)
 print(response.json())
 ```
 
+>**Note**: When intel-extension-for-transformers <= 1.3.1, please try [command](#using-curl) above
+
+
 ## Langchain Extension APIs
 
 Intel Extension for Transformers provides a comprehensive suite of Langchain-based extension APIs, including advanced retrievers, embedding models, and vector stores. These enhancements are carefully crafted to expand the capabilities of the original langchain API, ultimately boosting overall performance. This extension is specifically tailored to enhance the functionality and performance of RAG.

intel_extension_for_transformers/neural_chat/requirements.txt

@@ -1,11 +1,14 @@
 accelerate
 cchardet
+deepface
 einops
 evaluate
+ExifRead
 fastapi==0.103.2
 fschat==0.2.35
 git+https://github.com/EleutherAI/lm-evaluation-harness.git@cc9778fbe4fa1a709be2abed9deb6180fd40e7e2
 huggingface_hub
+intel-extension-for-transformers
 intel_extension_for_pytorch==2.1.0
 neural-compressor
 neural_speed
@@ -15,6 +18,8 @@ optimum
 optimum-intel
 peft==0.6.2
 pydantic==1.10.13
+pydub
+pymysql
 python-dotenv
 python-multipart
 rouge_score

intel_extension_for_transformers/neural_chat/requirements_cpu.txt

@@ -1,10 +1,13 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
 cchardet
+deepface
 einops
 evaluate
+ExifRead
 fastapi==0.103.2
 fschat==0.2.32
 git+https://github.com/EleutherAI/lm-evaluation-harness.git@cc9778fbe4fa1a709be2abed9deb6180fd40e7e2
+intel-extension-for-transformers
 intel_extension_for_pytorch==2.1.0
 neural-compressor
 neural_speed
@@ -13,6 +16,8 @@ optimum
 optimum-intel
 peft==0.6.2
 pydantic==1.10.13
+pydub
+pymysql
 python-dotenv
 python-multipart
 rouge_score

intel_extension_for_transformers/neural_chat/requirements_hpu.txt

@@ -1,16 +1,21 @@
 cchardet
+deepface
 einops
 evaluate
+ExifRead
 fastapi==0.103.2
 fschat==0.2.35
 git+https://github.com/EleutherAI/lm-evaluation-harness.git@cc9778fbe4fa1a709be2abed9deb6180fd40e7e2
+intel-extension-for-transformers
 intel_extension_for_pytorch
 neural-compressor
 neural_speed
 numpy==1.23.5
 optimum
 peft
 pydantic==1.10.13
+pydub
+pymysql
 python-dotenv
 python-multipart
 rouge_score

intel_extension_for_transformers/neural_chat/requirements_pc.txt

@@ -1,16 +1,21 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
 cchardet
+deepface
 einops
 evaluate
+ExifRead
 fastapi==0.103.2
 fschat==0.2.35
 git+https://github.com/EleutherAI/lm-evaluation-harness.git@cc9778fbe4fa1a709be2abed9deb6180fd40e7e2
+intel-extension-for-transformers
 neural-compressor
 numpy==1.23.5
 optimum
 optimum-intel
 peft
 pydantic==1.10.13
+pydub
+pymysql
 python-dotenv
 python-multipart
 rouge_score

intel_extension_for_transformers/neural_chat/requirements_xpu.txt

@@ -1,11 +1,16 @@
 cchardet
+deepface
 einops
 evaluate
+ExifRead
 fastapi==0.103.2
 fschat==0.2.35
+intel-extension-for-transformers
 neural-compressor
 numpy==1.23.5
 pydantic==1.10.13
+pydub
+pymysql
 python-dotenv
 python-multipart
 rouge_score