Upload salessupport_chatbot_test2_afterembbeding_partb.py

salessupport_chatbot_test2_afterembbeding_partb.py

@@ -0,0 +1,246 @@
+# -*- coding: utf-8 -*-
+"""SalesSupport-Chatbot-test2-AfterEmbbeding-PartB.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1MkbsRTVFogRG6BqsQFzcV_VZX7e7WvZ6
+
+Sales supporting Chatbot using
+
+*   Haystack: document embedding & RAG pipeline
+*   OpenAI API:   message generator, text embedder
+*   Gradio : chat bot UI and temporary hosting
+
+
+Retrieval source:
+
+1) BBR publicly accsessible English brochures only   
+2) BBR website
+
+20240514
+Xiaomeng
+
+#0. Setting Environment
+"""
+
+# Commented out IPython magic to ensure Python compatibility.
+# %%bash
+# 
+# pip install haystack-ai
+# pip install "sentence-transformers>=2.2.0"
+# pip install "datasets>=2.6.1"
+# pip install markdown-it-py mdit_plain pypdf
+# pip install accelerate
+# pip install gradio
+
+import os
+from getpass import getpass
+from haystack import Pipeline, PredefinedPipeline
+import urllib.request
+from haystack.components.generators import OpenAIGenerator
+
+# openai api
+os.environ["OPENAI_API_KEY"] = "sk-proj-JfQx42WJcMDGG1zAVe36T3BlbkFJ2ZmLEOzRhstgod0DbHZ7"
+
+
+"""# 1. Document store - dataset"""
+
+embedded_document_path="document_store.pkl"
+
+# Load the document store and retriever from .pkl files
+import pickle
+with open(embedded_document_path, "rb") as f:
+    document_store = pickle.load(f)
+
+"""#2. Define the RAG pipeline based on given documents, and build it as a tool function"""
+
+# define the RAG pipeline
+from haystack.components.embedders import SentenceTransformersTextEmbedder
+from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
+from haystack.components.builders import PromptBuilder
+from haystack.components.generators import OpenAIGenerator
+from haystack.components.embedders import OpenAITextEmbedder, OpenAIDocumentEmbedder
+
+#define the template
+template = """
+Answer the questions based on the given context.
+
+Context:
+{% for document in documents %}
+    {{ document.content }}
+{% endfor %}
+Question: {{ question }}
+Answer:
+"""
+
+# define each component of the pipeline and connect them
+rag_pipe = Pipeline()
+#rag_pipe.add_component("embedder", SentenceTransformersTextEmbedder(model="sentence-transformers/all-MiniLM-L6-v2"))
+rag_pipe.add_component("embedder", OpenAITextEmbedder())
+
+
+rag_pipe.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))
+rag_pipe.add_component("prompt_builder", PromptBuilder(template=template))
+rag_pipe.add_component("llm", OpenAIGenerator(model="gpt-3.5-turbo"))
+
+rag_pipe.connect("embedder.embedding", "retriever.query_embedding")
+rag_pipe.connect("retriever", "prompt_builder.documents")
+rag_pipe.connect("prompt_builder", "llm")
+
+# define the funcitoin
+def rag_pipeline_func(query: str):
+    result = rag_pipe.run({"embedder": {"text": query}, "prompt_builder": {"question": query}})
+    return {"reply": result["llm"]["replies"][0]}
+
+string_text = "What is the maximum size of the CMG system?"
+rag_pipeline_func(string_text)
+
+"""## 2.2 Websearch pipeline"""
+
+pipeline_webserch = Pipeline.from_template(PredefinedPipeline.CHAT_WITH_WEBSITE)
+result = pipeline_webserch.run({
+    "fetcher": {"urls": ["https://www.bbrnetwork.com"]},
+    "prompt": {"query": "How many network members are there in the BBR network?"}}
+)
+print(result["llm"]["replies"][0])
+
+# define the funcitoin
+def pipeline_websearch_func(query: str):
+    result = pipeline_webserch.run({
+        "fetcher": {"urls": ["https://www.bbrnetwork.com"]},
+        "prompt": {"query": query}}
+        )
+    return {"reply": result["llm"]["replies"][0]}
+
+string_text = "How many network members are there in the BBR network?"
+pipeline_websearch_func(string_text)
+
+"""# 3. Create tool list following OpenAI schema"""
+
+#Create tool list following OpenAI schema
+# following OpenAPI tool schema for the function
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "rag_pipeline_func",
+            #"description": "Get information about products for geotecnical applicaions, especially CMG system",
+            "description": "Get information about BBR products",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "query": {
+                        "type": "string",
+                        "description": "The query to use in the search. Infer this from the user's message. It should be a question or a statement",
+                    }
+                },
+                "required": ["query"],
+            },
+        },
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "pipeline_websearch_func",
+            "description": "Get the information about BBR and BBR networks general information",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "query": {
+                        "type": "string",
+                        "description": "The query to use in the search. Infer this from the user's message. It should be a question or a statement",
+                    }
+                },
+                "required": ["query"],
+            },
+        },
+    },
+]
+
+from haystack.dataclasses import ChatMessage
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.components.generators.utils import print_streaming_chunk
+
+
+# define system and USER messages for the Chat with predifined tools list
+messages = [
+    #ChatMessage.from_system(
+        #"Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."
+    #),
+    ChatMessage.from_user("What is the special features of CMG system?"),
+]
+
+chat_generator = OpenAIChatGenerator(model="gpt-3.5-turbo", streaming_callback=print_streaming_chunk)
+response = chat_generator.run(messages=messages, generation_kwargs={"tools": tools})
+
+import json
+
+## Parse function calling information
+function_call = json.loads(response["replies"][0].content)[0]
+function_name = function_call["function"]["name"]
+function_args = json.loads(function_call["function"]["arguments"])
+print("Function Name:", function_name)
+print("Function Arguments:", function_args)
+
+
+## Find the correspoding function and call it with the given arguments
+available_functions = {"rag_pipeline_func": rag_pipeline_func, "pipeline_websearch_func": pipeline_websearch_func}
+function_to_call = available_functions[function_name]
+function_response = function_to_call(**function_args)
+print("Function Response:", function_response)
+
+"""# 4. build chatbot by Gradio"""
+
+chat_generator = OpenAIChatGenerator(model="gpt-3.5-turbo")
+response = None
+messages = [
+    ChatMessage.from_system(
+        "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."
+    )
+]
+
+import gradio as gr
+
+
+def chatbot_with_fc(message, history):
+    messages.append(ChatMessage.from_user(message))
+    response = chat_generator.run(messages=messages, generation_kwargs={"tools": tools})
+
+    while True:
+        # if OpenAI response is a tool call
+        if response and response["replies"][0].meta["finish_reason"] == "tool_calls":
+            function_calls = json.loads(response["replies"][0].content)
+            print(response["replies"][0])
+            for function_call in function_calls:
+                ## Parse function calling information
+                function_name = function_call["function"]["name"]
+                function_args = json.loads(function_call["function"]["arguments"])
+
+                ## Find the correspoding function and call it with the given arguments
+                function_to_call = available_functions[function_name]
+                function_response = function_to_call(**function_args)
+
+                ## Append function response to the messages list using `ChatMessage.from_function`
+                messages.append(ChatMessage.from_function(content=json.dumps(function_response), name=function_name))
+                response = chat_generator.run(messages=messages, generation_kwargs={"tools": tools})
+
+        # Regular Conversation
+        else:
+            messages.append(response["replies"][0])
+            break
+    return response["replies"][0].content
+
+
+demo = gr.ChatInterface(
+    fn=chatbot_with_fc,
+    examples=[
+        "What are BBR's main products?",
+        "What is BBR Network?",
+        "Is there a BBR member in New Zealand?",
+        "What's the difference between BBR CMI A5 type and A1 type anchor head?",
+    ],
+    title="BBR Digital Assistante Demo - ",
+)
+
+demo.launch()