wxmxavier/PT_Sales_Bot_test_2

1# -*- coding: utf-8 -*-2"""SalesSupport-Chatbot-test2-AfterEmbbeding-PartB.ipynb3 4Automatically generated by Colab.5 6Original file is located at7    https://colab.research.google.com/drive/1MkbsRTVFogRG6BqsQFzcV_VZX7e7WvZ68 9Sales supporting Chatbot using10 11*   Haystack: document embedding & RAG pipeline12*   OpenAI API:   message generator, text embedder13*   Gradio : chat bot UI and temporary hosting14 15 16Retrieval source:17 181) BBR publicly accsessible English brochures only   192) BBR website20 212024051422Xiaomeng23 24#0. Setting Environment25"""26 27# Commented out IPython magic to ensure Python compatibility.28# %%bash29# 30# pip install haystack-ai31# pip install "sentence-transformers>=2.2.0"32# pip install "datasets>=2.6.1"33# pip install markdown-it-py mdit_plain pypdf34# pip install accelerate35# pip install gradio36 37import os38from getpass import getpass39from haystack import Pipeline, PredefinedPipeline40import urllib.request41from haystack.components.generators import OpenAIGenerator42 43# openai api44os.environ["OPENAI_API_KEY"] = "sk-proj-JfQx42WJcMDGG1zAVe36T3BlbkFJ2ZmLEOzRhstgod0DbHZ7"45 46 47"""# 1. Document store - dataset"""48 49embedded_document_path="document_store.pkl"50 51# Load the document store and retriever from .pkl files52import pickle53with open(embedded_document_path, "rb") as f:54    document_store = pickle.load(f)55 56"""#2. Define the RAG pipeline based on given documents, and build it as a tool function"""57 58# define the RAG pipeline59from haystack.components.embedders import SentenceTransformersTextEmbedder60from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever61from haystack.components.builders import PromptBuilder62from haystack.components.generators import OpenAIGenerator63from haystack.components.embedders import OpenAITextEmbedder, OpenAIDocumentEmbedder64 65#define the template66template = """67Answer the questions based on the given context.68 69Context:70{% for document in documents %}71    {{ document.content }}72{% endfor %}73Question: {{ question }}74Answer:75"""76 77# define each component of the pipeline and connect them78rag_pipe = Pipeline()79#rag_pipe.add_component("embedder", SentenceTransformersTextEmbedder(model="sentence-transformers/all-MiniLM-L6-v2"))80rag_pipe.add_component("embedder", OpenAITextEmbedder())81 82 83rag_pipe.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))84rag_pipe.add_component("prompt_builder", PromptBuilder(template=template))85rag_pipe.add_component("llm", OpenAIGenerator(model="gpt-3.5-turbo"))86 87rag_pipe.connect("embedder.embedding", "retriever.query_embedding")88rag_pipe.connect("retriever", "prompt_builder.documents")89rag_pipe.connect("prompt_builder", "llm")90 91# define the funcitoin92def rag_pipeline_func(query: str):93    result = rag_pipe.run({"embedder": {"text": query}, "prompt_builder": {"question": query}})94    return {"reply": result["llm"]["replies"][0]}95 96string_text = "What is the maximum size of the CMG system?"97rag_pipeline_func(string_text)98 99"""## 2.2 Websearch pipeline"""100 101pipeline_webserch = Pipeline.from_template(PredefinedPipeline.CHAT_WITH_WEBSITE)102result = pipeline_webserch.run({103    "fetcher": {"urls": ["https://www.bbrnetwork.com"]},104    "prompt": {"query": "How many network members are there in the BBR network?"}}105)106print(result["llm"]["replies"][0])107 108# define the funcitoin109def pipeline_websearch_func(query: str):110    result = pipeline_webserch.run({111        "fetcher": {"urls": ["https://www.bbrnetwork.com"]},112        "prompt": {"query": query}}113        )114    return {"reply": result["llm"]["replies"][0]}115 116string_text = "How many network members are there in the BBR network?"117pipeline_websearch_func(string_text)118 119"""# 3. Create tool list following OpenAI schema"""120 121#Create tool list following OpenAI schema122# following OpenAPI tool schema for the function123tools = [124    {125        "type": "function",126        "function": {127            "name": "rag_pipeline_func",128            #"description": "Get information about products for geotecnical applicaions, especially CMG system",129            "description": "Get information about BBR products",130            "parameters": {131                "type": "object",132                "properties": {133                    "query": {134                        "type": "string",135                        "description": "The query to use in the search. Infer this from the user's message. It should be a question or a statement",136                    }137                },138                "required": ["query"],139            },140        },141    },142    {143        "type": "function",144        "function": {145            "name": "pipeline_websearch_func",146            "description": "Get the information about BBR and BBR networks general information",147            "parameters": {148                "type": "object",149                "properties": {150                    "query": {151                        "type": "string",152                        "description": "The query to use in the search. Infer this from the user's message. It should be a question or a statement",153                    }154                },155                "required": ["query"],156            },157        },158    },159]160 161from haystack.dataclasses import ChatMessage162from haystack.components.generators.chat import OpenAIChatGenerator163from haystack.components.generators.utils import print_streaming_chunk164 165 166# define system and USER messages for the Chat with predifined tools list167messages = [168    #ChatMessage.from_system(169        #"Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."170    #),171    ChatMessage.from_user("What is the special features of CMG system?"),172]173 174chat_generator = OpenAIChatGenerator(model="gpt-3.5-turbo", streaming_callback=print_streaming_chunk)175response = chat_generator.run(messages=messages, generation_kwargs={"tools": tools})176 177import json178 179## Parse function calling information180function_call = json.loads(response["replies"][0].content)[0]181function_name = function_call["function"]["name"]182function_args = json.loads(function_call["function"]["arguments"])183print("Function Name:", function_name)184print("Function Arguments:", function_args)185 186 187## Find the correspoding function and call it with the given arguments188available_functions = {"rag_pipeline_func": rag_pipeline_func, "pipeline_websearch_func": pipeline_websearch_func}189function_to_call = available_functions[function_name]190function_response = function_to_call(**function_args)191print("Function Response:", function_response)192 193"""# 4. build chatbot by Gradio"""194 195chat_generator = OpenAIChatGenerator(model="gpt-3.5-turbo")196response = None197messages = [198    ChatMessage.from_system(199        "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."200    )201]202 203import gradio as gr204 205 206def chatbot_with_fc(message, history):207    messages.append(ChatMessage.from_user(message))208    response = chat_generator.run(messages=messages, generation_kwargs={"tools": tools})209 210    while True:211        # if OpenAI response is a tool call212        if response and response["replies"][0].meta["finish_reason"] == "tool_calls":213            function_calls = json.loads(response["replies"][0].content)214            print(response["replies"][0])215            for function_call in function_calls:216                ## Parse function calling information217                function_name = function_call["function"]["name"]218                function_args = json.loads(function_call["function"]["arguments"])219 220                ## Find the correspoding function and call it with the given arguments221                function_to_call = available_functions[function_name]222                function_response = function_to_call(**function_args)223 224                ## Append function response to the messages list using `ChatMessage.from_function`225                messages.append(ChatMessage.from_function(content=json.dumps(function_response), name=function_name))226                response = chat_generator.run(messages=messages, generation_kwargs={"tools": tools})227 228        # Regular Conversation229        else:230            messages.append(response["replies"][0])231            break232    return response["replies"][0].content233 234 235demo = gr.ChatInterface(236    fn=chatbot_with_fc,237    examples=[238        "What are BBR's main products?",239        "What is BBR Network?",240        "Is there a BBR member in New Zealand?",241        "What's the difference between BBR CMI A5 type and A1 type anchor head?",242    ],243    title="BBR Digital Assistante Demo - ",244)245 246demo.launch()