basic chatbot

app.py

@@ -3,16 +3,52 @@
 from flask import Flask,request
 from dotenv import load_dotenv
 
-from langchain_openai import ChatOpenAI
+from langchain.agents import tool
+
 
 # Initializing flask app
 app = Flask(__name__)
 load_dotenv()
 
+
+@tool
+def FAQ(question: str):
+    """Answers the question 1+1"""
+    return 23
+
+tools=[FAQ]
+
+
 @app.route('/', methods=['GET','POST'])
 def index():
-    llm = ChatOpenAI()
-    response=llm.invoke("how can langsmith help with testing?")
-    print(response)
 
-    return {"response":"just some junk response"}
+    input = {
+        "page_context":"home",
+        "user_summary":"The user is a first year student on BA Architecture",
+        "session_summary":"The user has introduced themselves as Mark Peace and asked how the bot is doing",
+        "user_input":"Can you remind me of my own name?"
+    }
+
+
+    from langchain_openai import ChatOpenAI
+    from langchain.agents import create_openai_functions_agent
+    from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+    from langchain.agents import AgentExecutor
+
+
+    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+
+    prompt = ChatPromptTemplate.from_messages([
+        ("system", "You are a helpful AI bot. Your name is Bob. Please do not answer if you aren't sure of the answer"),
+        ("system", "Here is a summary of the conversation so far: {session_summary}"),
+        ("human", "{user_input}"),
+        MessagesPlaceholder(variable_name="agent_scratchpad")
+    ]) 
+
+    agent = create_openai_functions_agent(llm, tools, prompt)
+
+    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+
+    response=agent_executor.invoke(input)
+
+    return response

requirements.txt

@@ -5,5 +5,10 @@ gunicorn
 python-dotenv
 
 #LLM
+bs4
 langchain
-langchain-openai
+torch
+transformers
+sentence-transformers
+datasets
+faiss-cpu

test.py

@@ -0,0 +1,105 @@
+#import json
+
+from flask import Flask,request
+from dotenv import load_dotenv
+
+from langchain.document_loaders import WebBaseLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+from transformers import AutoTokenizer, pipeline
+from langchain import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+
+# Initializing flask app
+app = Flask(__name__)
+load_dotenv()
+
+@app.route("/train/faq", methods=['GET','POST'])
+def embeddings_faqs():    
+
+    data = WebBaseLoader("https://rise.mmu.ac.uk/what-is-rise/").load()
+
+    # Create an instance of the RecursiveCharacterTextSplitter class with specific parameters.
+    # It splits text into chunks of 1000 characters each with a 150-character overlap.
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
+
+    # 'data' holds the text you want to split, split the text into documents using the text splitter.
+    docs = text_splitter.split_documents(data)
+
+    # Define the path to the pre-trained model you want to use
+    modelPath = "sentence-transformers/all-MiniLM-l6-v2"
+
+    # Create a dictionary with model configuration options, specifying to use the CPU for computations
+    model_kwargs = {'device':'cpu'}
+
+    # Create a dictionary with encoding options, specifically setting 'normalize_embeddings' to False
+    encode_kwargs = {'normalize_embeddings': False}
+
+    # Initialize an instance of HuggingFaceEmbeddings with the specified parameters
+    embeddings = HuggingFaceEmbeddings(
+        model_name=modelPath,     # Provide the pre-trained model's path
+        model_kwargs=model_kwargs, # Pass the model configuration options
+        encode_kwargs=encode_kwargs # Pass the encoding options
+    )
+
+    # Create vectors
+    vectorstore = FAISS.from_documents(docs, embeddings)
+    # Persist the vectors locally on disk
+    vectorstore.save_local("_rise_faq_db");
+
+    return {"trained":"success"}
+
+@app.route('/ask', methods=['GET','POST'])
+def ask():
+    # Specify the model name you want to use
+    model_name = "Intel/dynamic_tinybert"
+
+    # Load the tokenizer associated with the specified model
+    tokenizer = AutoTokenizer.from_pretrained(model_name, padding=True, truncation=True, max_length=512)
+
+    # Define a question-answering pipeline using the model and tokenizer
+    question_answerer = pipeline(
+        "question-answering", 
+        model=model_name, 
+        tokenizer=tokenizer,
+        return_tensors='pt'
+    )
+
+    # Create an instance of the HuggingFacePipeline, which wraps the question-answering pipeline
+    # with additional model-specific arguments (temperature and max_length)
+    llm = HuggingFacePipeline(
+        pipeline=question_answerer,
+        model_kwargs={"temperature": 0.7, "max_length": 512},
+    )
+
+     # Define the path to the pre-trained model you want to use
+    modelPath = "sentence-transformers/all-MiniLM-l6-v2"
+
+    # Create a dictionary with model configuration options, specifying to use the CPU for computations
+    model_kwargs = {'device':'cpu'}
+
+    # Create a dictionary with encoding options, specifically setting 'normalize_embeddings' to False
+    encode_kwargs = {'normalize_embeddings': False}
+
+    # Initialize an instance of HuggingFaceEmbeddings with the specified parameters
+    embeddings = HuggingFaceEmbeddings(
+        model_name=modelPath,     # Provide the pre-trained model's path
+        model_kwargs=model_kwargs, # Pass the model configuration options
+        encode_kwargs=encode_kwargs # Pass the encoding options
+    )
+    persisted_vectorstore = FAISS.load_local("_rise_faq_db", embeddings)
+
+    # Create a retriever object from the 'db' using the 'as_retriever' method.
+    # This retriever is likely used for retrieving data or documents from the database.
+    retriever = persisted_vectorstore.as_retriever()
+
+    docs = retriever.get_relevant_documents("What are the benefits?")
+    print(docs[0].page_content)
+
+    return "uip"
+
+@app.route('/', methods=['GET','POST'])
+def index():
+    return {"response":"just some junk response"}