changes

Dockerfile

@@ -0,0 +1,29 @@
+FROM ubuntu:latest
+
+RUN apt update
+RUN apt-get update && \
+    apt-get install -y curl python3-pip python3-dev && \
+    rm -rf /var/lib/apt/lists/*
+
+
+COPY process_one.sh /app/process_one.sh
+COPY process_two.sh /app/process_two.sh
+COPY main.sh /app/main.sh
+
+
+COPY home.py /frontend/home.py
+COPY streaming.py /frontend/streaming.py
+COPY utils.py /frontend/utils.py
+COPY requirements.txt /frontend/requirements.txt
+
+WORKDIR /app
+
+EXPOSE 8501
+
+ 
+RUN chmod +x  /app/process_one.sh
+RUN chmod +x  /app/process_two.sh
+RUN chmod +x  /app/main.sh
+
+
+CMD ["/app/main.sh"]

Dockerfile.build

@@ -0,0 +1,31 @@
+# centos7 amd64 dependencies
+FROM --platform=linux/amd64 nvidia/cuda:11.3.1-devel-centos7 AS base-amd64
+RUN yum install -y https://repo.ius.io/ius-release-el7.rpm centos-release-scl && \
+    yum update -y && \
+    yum install -y devtoolset-10-gcc devtoolset-10-gcc-c++ git236 wget
+RUN wget "https://github.com/Kitware/CMake/releases/download/v3.27.6/cmake-3.27.6-linux-x86_64.sh" -O cmake-installer.sh && chmod +x cmake-installer.sh && ./cmake-installer.sh --skip-license --prefix=/usr/local
+ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
+
+# centos8 arm64 dependencies
+FROM --platform=linux/arm64 nvidia/cuda-arm64:11.3.1-devel-centos8 AS base-arm64
+RUN sed -i -e 's/mirrorlist/#mirrorlist/g' -e 's|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g' /etc/yum.repos.d/CentOS-*
+RUN yum install -y git cmake
+
+FROM base-${TARGETARCH}
+ARG TARGETARCH
+ARG GOFLAGS="'-ldflags -w -s'"
+
+# install go
+ADD https://dl.google.com/go/go1.21.3.linux-$TARGETARCH.tar.gz /tmp/go1.21.3.tar.gz
+RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.3.tar.gz
+
+# build the final binary
+WORKDIR /go/src/github.com/jmorganca/ollama
+COPY . .
+
+ENV GOOS=linux
+ENV GOARCH=$TARGETARCH
+ENV GOFLAGS=$GOFLAGS
+
+RUN /usr/local/go/bin/go generate ./... && \
+    /usr/local/go/bin/go build .

home.py

@@ -0,0 +1,105 @@
+import utils
+import streamlit as st
+from streaming import StreamHandler
+import torch
+# from LLM import OpenAI
+from langchain.chains import ConversationChain
+from langchain.memory import ConversationBufferMemory
+from langchain.llms import HuggingFaceHub
+from transformers import AutoConfig
+from langchain.llms import HuggingFaceHub
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from langchain.llms import HuggingFacePipeline
+from langchain.chat_models import ChatOllama
+import pandas as pd
+import requests
+import tempfile
+import os
+ 
+st.set_page_config(page_title="Chatbot", page_icon="💬")
+st.header('Ebiz Chatbot')
+st.write('Allows users to interact with the LLM')
+# st.write('[![view source code ](https://img.shields.io/badge/view_source_code-gray?logo=github)](https://github.com/shashankdeshpande/langchain-chatbot/blob/master/pages/1_%F0%9F%92%AC_basic_chatbot.py)')
+
+
+# Using "with" notation
+with st.sidebar:
+    
+    ktopVal= st.slider(
+        'K-top',
+        0.0, 1.0,step=0.1)
+     
+    ptopVal=st.slider(
+        'P-top',
+        0.0, 1.0,step=0.1)
+    tempVal=st.slider(
+        'Temperature',
+        0.0, 1.0, step=0.1)
+    
+    uploaded_file = st.file_uploader("Choose a file")
+    submit_button = st.button("Submit")
+ 
+
+    if submit_button:
+        # Display the file details
+        st.write("File Details:")
+        st.write(f"Filename: {uploaded_file.name}")
+        st.write(f"File Type: {uploaded_file.type}")
+        st.write(f"File Size: {uploaded_file.size} bytes")
+
+        # Send file to Flask server
+        url = "http://127.0.0.1:5000/upload"
+        files = {'file': (uploaded_file.name, uploaded_file, uploaded_file.type)}
+        payload = {'ktopVal':ktopVal,"ptopVal":ptopVal,"tempVal":tempVal}
+        response = requests.post(url, files=files,data=payload)
+
+        # Display the response from the server
+        st.write("Server Response:")
+        st.write(response.text)
+
+
+class Basic:
+
+    def __init__(self):
+        utils.configure_openai_api_key()
+        self.openai_model = "gpt-3.5-turbo"
+    
+    def setup_chain(self):
+        # config = AutoConfig.from_pretrained('stabilityai/stablelm-3b-4e1t', trust_remote_code=True)
+        model_name = 'stabilityai/stablelm-3b-4e1t'
+        torch_dtype = "float16" #@param ["float16", "bfloat16", "float"]
+        load_in_8bit = False #@param {type:"boolean"}
+        device_map = "auto"
+    #     tokenizer = AutoTokenizer.from_pretrained(model_name,trust_remote_code=True)
+    #     model = AutoModelForCausalLM.from_pretrained(
+    #     model_name,
+    #     torch_dtype=getattr(torch, torch_dtype),
+    #     load_in_8bit=load_in_8bit,
+    #     device_map=device_map,
+    #     trust_remote_code=True,
+    #     offload_folder="./offload",
+    # )
+        # pipe = pipeline(
+        #         "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=256
+        #     )
+        
+        llm = ChatOllama(model="llama2")
+        memory = ConversationBufferMemory()
+
+        chain = ConversationChain(llm=llm, memory=memory, verbose=True)
+        return chain
+    
+    @utils.enable_chat_history
+    def main(self):
+        chain = self.setup_chain()
+        user_query = st.chat_input(placeholder="Ask me anything!")
+        if user_query:
+            utils.display_msg(user_query, 'user')
+            with st.chat_message("assistant"):
+                st_cb = StreamHandler(st.empty())
+                response = chain(user_query, callbacks=[st_cb])
+                st.session_state.messages.append({"role": "assistant", "content": response['response']})
+
+if __name__ == "__main__":
+    obj = Basic()
+    obj.main()

main.sh

@@ -0,0 +1,3 @@
+#!/usr/bin/bash
+./process_one.sh
+./process_two.sh

output.log

@@ -0,0 +1,11 @@
+Error: could not connect to ollama server, run 'ollama serve' to startYour new public key is: 
+
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAII0AG1ceFVkI1K3NCwbqRwCxPC24WpENmLxWrEeeRLz6
+
+2023/12/22 09:57:49 images.go:737: total blobs: 0
+2023/12/22 09:57:49 images.go:744: total unused blobs removed: 0
+2023/12/22 09:57:49 routes.go:895: Listening on 127.0.0.1:11434 (version 0.1.17)
+2023/12/22 09:57:49 routes.go:915: warning: gpu support may not be enabled, check that you have installed GPU drivers: nvidia-smi command failed
+[GIN] 2023/12/22 - 09:59:35 | 404 |     273.258µs |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2023/12/22 - 10:00:15 | 404 |      48.669µs |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2023/12/22 - 10:17:22 | 404 |      77.915µs |       127.0.0.1 | POST     "/api/chat"

process_one.sh

@@ -0,0 +1,19 @@
+
+#!/usr/bin/bash
+
+echo "calling process one......!"
+
+curl https://ollama.ai/install.sh | sh
+
+echo "ollama installed here..."
+
+ollama serve &
+# nohup ollama serve > output.log 2>&1 &
+mkdir -p /etc/systemd/system/ollama.service.d
+echo "[Service]" >>/etc/systemd/system/ollama.service.d/environment.conf
+echo "ollama served"
+
+ollama run llama2 &
+# nohup ollama run llama2 > output.log 2>&1 &
+
+echo "llama2 running"

process_two.sh

@@ -0,0 +1,9 @@
+#!/usr/bin/bash
+echo "calling process two......!"
+
+# Install dependencies
+pip install --no-cache-dir --upgrade streamlit
+ls -al
+pip install --no-cache-dir --upgrade -r /frontend/requirements.txt
+
+streamlit run /frontend/home.py

requirements.txt

@@ -0,0 +1,9 @@
+fastapi==0.74.*
+sentencepiece==0.1.*
+torch==1.11.*
+uvicorn[standard]==0.17.* 
+streamlit
+langchain
+transformers
+pandas
+requests

streaming.py

@@ -0,0 +1,11 @@
+from langchain.callbacks.base import BaseCallbackHandler
+import streamlit as st
+class StreamHandler(BaseCallbackHandler):
+    
+    def __init__(self, container, initial_text=""):
+        self.container = container
+        self.text = initial_text
+
+    def on_llm_new_token(self, token: str, **kwargs):
+        self.text += token
+        self.container.markdown(self.text)

utils.py

@@ -0,0 +1,55 @@
+import os
+import random
+import streamlit as st
+
+#decorator
+def enable_chat_history(func):
+    if os.environ.get("OPENAI_API_KEY"):
+
+        # to clear chat history after swtching chatbot
+        current_page = func.__qualname__
+        if "current_page" not in st.session_state:
+            st.session_state["current_page"] = current_page
+        if st.session_state["current_page"] != current_page:
+            try:
+                st.cache_resource.clear()
+                del st.session_state["current_page"]
+                del st.session_state["messages"]
+            except:
+                pass
+
+        # to show chat history on ui
+        if "messages" not in st.session_state:
+            st.session_state["messages"] = [{"role": "assistant", "content": "How can I help you?"}]
+        for msg in st.session_state["messages"]:
+            st.chat_message(msg["role"]).write(msg["content"])
+
+    def execute(*args, **kwargs):
+        func(*args, **kwargs)
+    return execute
+
+def display_msg(msg, author):
+    """Method to display message on the UI
+
+    Args:
+        msg (str): message to display
+        author (str): author of the message -user/assistant
+    """
+    st.session_state.messages.append({"role": author, "content": msg})
+    st.chat_message(author).write(msg)
+
+def configure_openai_api_key():
+    openai_api_key = st.sidebar.text_input(
+        label="OpenAI API Key",
+        type="password",
+        value=st.session_state['OPENAI_API_KEY'] if 'OPENAI_API_KEY' in st.session_state else '',
+        placeholder="sk-..."
+        )
+    if openai_api_key:
+        st.session_state['OPENAI_API_KEY'] = openai_api_key
+        os.environ['OPENAI_API_KEY'] = openai_api_key
+    else:
+        st.error("Please add your OpenAI API key to continue.")
+        st.info("Obtain your key from this link: https://platform.openai.com/account/api-keys")
+        st.stop()
+    return openai_api_key