Upload 6 files

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:latest
+
+WORKDIR /
+
+COPY ./requirements.txt .
+
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,75 @@
+from fastapi import FastAPI
+
+from fastapi.middleware.cors import CORSMiddleware
+
+from chatbot import Chatbot
+
+from chatbotmemory import ChatbotMemory
+
+import logging
+
+from langchain_core.messages import AIMessage, HumanMessage
+
+
+app = FastAPI()
+
+# Add logging 
+
+logging.basicConfig(level=logging.INFO)
+
+logger = logging.getLogger(__name__)
+
+formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
+
+handler = logging.StreamHandler()
+
+handler.setFormatter(formatter)
+
+logger.addHandler(handler)
+
+# Add CORS
+
+origins = ["*"]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["GET", "POST", "PUT", "DELETE"],
+    allow_headers=["*"],
+)
+
+bot1 = Chatbot()
+bot2 = ChatbotMemory()
+
+@app.get("/")
+
+def read_root():
+
+    return {
+
+        "message": "API running successfully",
+
+        "endpoints": [
+
+            "/chat/v1/",
+
+            "/chat/v2/",
+
+        ]
+
+    }
+
+@app.post("/chat/v1/")
+def chat(q: str):
+    logger.info(q)
+    answer = bot1.rag_chain.invoke(q)
+    return {"answer": answer}
+
+@app.post("/chat/v2/")
+def chatMemory(q: str):
+    chat_history = []
+    logger.info(q)
+    ai_msg = bot2.rag_chain.invoke({"question": q, "chat_history": chat_history})     
+    chat_history.extend([HumanMessage(content=q), ai_msg])   
+    return {"answer": ai_msg}

chatbot.py

@@ -0,0 +1,69 @@
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.document_loaders import TextLoader
+from langchain.schema.runnable import RunnablePassthrough
+from langchain.schema.output_parser import StrOutputParser
+from langchain_pinecone import PineconeVectorStore
+from langchain.prompts import PromptTemplate
+from langchain_google_genai import GoogleGenerativeAI, GoogleGenerativeAIEmbeddings
+from dotenv import load_dotenv, find_dotenv
+import os
+from pinecone import Pinecone, PodSpec
+
+load_dotenv(find_dotenv())
+
+class Chatbot():
+
+    loader = TextLoader('dataset.txt', autodetect_encoding=True)
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=256, chunk_overlap=4)
+    docs = text_splitter.split_documents(documents)
+
+    embeddings = GoogleGenerativeAIEmbeddings(
+    model="models/embedding-001", task_type="retrieval_query", google_api_key=os.getenv("GEMINI_API_KEY")
+)
+
+    pinecone = Pinecone(
+        api_key=os.environ.get("PINECONE_API_KEY")
+        # host='gcp-starter'
+    )
+
+    index_name = "gdscsou-chatbot"
+
+    if index_name not in pinecone.list_indexes().names():
+        pinecone.create_index(name=index_name, metric="cosine", dimension=768, spec=PodSpec(environment="gcp-starter"))
+        docsearch = PineconeVectorStore.from_documents(docs, embeddings, index_name=index_name)
+    else:
+         docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)
+
+
+    llm = GoogleGenerativeAI(model="gemini-pro", google_api_key=os.getenv("GEMINI_API_KEY"))
+
+    template = """
+    INSTRUCTION: Act as an AI assistant and sales and marketing expert for Katha - A Tale of Weaves, a brand that bring exclusive collection of sustainable handloom sarees that tells a story of its heritage, this is conversation \
+    to a customer who came to visit site. Use the CONTEXT to answer in a helpful manner to the QUESTION. \
+    Don't forget you are an AI assistant and sales and marketing expert for Katha - A Tale of Weaves. \
+    If you don't know any ANSWER, say you don't know \
+    Always follow general guardrails before generating any response. \
+    Always try to keep the conversation in context to Katha - A Tale of Weaves. Keep your replies short \
+    compassionate and informative.\
+    Give the answer from the CONTEXT\
+    You should help user to get his query solved and also try to increase engagement for Katha - A Tale of Weaves and also promoting Katha - A Tale of Weaves.\
+        
+    CONTEXT: {context}
+    QUESTION: {question}
+    ANSWER:
+    """
+
+    prompt = PromptTemplate(
+    template=template, 
+    input_variables=["context", "question"]
+    )
+
+
+    rag_chain = (
+    {"context": docsearch.as_retriever(),  "question": RunnablePassthrough()} 
+    | prompt 
+    | llm
+    | StrOutputParser() 
+    )
+

chatbotmemory.py

@@ -0,0 +1,92 @@
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import TextLoader
+from langchain.schema.runnable import RunnablePassthrough
+from langchain.schema.output_parser import StrOutputParser
+from langchain_pinecone import PineconeVectorStore
+from langchain.prompts import MessagesPlaceholder, ChatPromptTemplate
+from langchain_google_genai import GoogleGenerativeAI, GoogleGenerativeAIEmbeddings
+from dotenv import load_dotenv, find_dotenv
+import os
+from pinecone import Pinecone, PodSpec
+
+load_dotenv(find_dotenv())
+
+class ChatbotMemory():
+
+    loader = TextLoader('dataset.txt', autodetect_encoding=True)
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=103)
+    docs = text_splitter.split_documents(documents)
+
+    embeddings = GoogleGenerativeAIEmbeddings(
+    model="models/embedding-001", task_type="retrieval_query", google_api_key=os.getenv("GEMINI_API_KEY"))
+
+    pinecone = Pinecone(
+        api_key=os.environ.get("PINECONE_API_KEY")
+    )
+
+    index_name = "gdscsou-chatbot"
+
+    if index_name not in pinecone.list_indexes().names():
+        pinecone.create_index(name=index_name, metric="cosine", dimension=768, spec=PodSpec(environment="gcp-starter"))
+        docsearch = PineconeVectorStore.from_documents(docs, embeddings, index_name=index_name)
+    else:
+         docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)
+
+
+    llm = GoogleGenerativeAI(model="gemini-pro", google_api_key=os.getenv("GEMINI_API_KEY"))
+
+    def contextualized_question(input: dict):
+        if input.get("chat_history"):
+            llm = GoogleGenerativeAI(model="gemini-pro", google_api_key=os.getenv("GEMINI_API_KEY"))
+
+            contextualize_q_system_prompt = """Given a chat history and the latest user question \
+            which might reference context in the chat history, formulate a standalone question \
+            which can be understood without the chat history. Do NOT answer the question, \
+            just reformulate it if needed and otherwise return it as is."""
+
+            contextualize_q_prompt = ChatPromptTemplate.from_messages(
+                [
+                    ("system", contextualize_q_system_prompt),
+                    MessagesPlaceholder(variable_name="chat_history"),
+                    ("human", "{question}"),
+                ]
+            )
+
+            contextualize_q_chain = contextualize_q_prompt | llm | StrOutputParser()
+            return contextualize_q_chain
+        else:
+            return input["question"]
+    
+    template = """
+    INSTRUCTION: Act as an AI assistant and sales and marketing expert for Katha - A Tale of Weaves, a brand that bring exclusive collection of sustainable handloom sarees that tells a story of its heritage, this is conversation \
+    to a customer who came to visit site. Use the CONTEXT to answer in a helpful manner to the QUESTION. \
+    Don't forget you are an AI assistant and sales and marketing expert for Katha - A Tale of Weaves. \
+    If you don't know any ANSWER, say you don't know \
+    Always follow general guardrails before generating any response. \
+    Always try to keep the conversation in context to Katha - A Tale of Weaves. Keep your replies short \
+    compassionate and informative.\
+    Give the answer from the CONTEXT\
+    You should help user to get his query solved and also try to increase engagement for Katha - A Tale of Weaves and also promoting Katha - A Tale of Weaves.\
+        
+    CONTEXT: {context}
+    QUESTION: {question}
+    ANSWER:
+    """
+
+    prompt = ChatPromptTemplate.from_messages(
+        [
+            ("system", template),
+            MessagesPlaceholder(variable_name="chat_history"),
+            ("human", "{question}"),
+        ]
+    )
+
+    
+    rag_chain = (
+        RunnablePassthrough.assign(
+            context=contextualized_question | docsearch.as_retriever() 
+        )
+        | prompt
+        | llm
+    )

dataset.txt

@@ -0,0 +1,74 @@
+Brand Name : Katha - A Tale of Weaves
+Facebook Page Link : https://www.facebook.com/profile.php?id=61556532028838 | 1.4K likes • 1.4K followers
+Instagram Page Link : https://www.instagram.com/kathatale/ | 23 posts . 81 followers
+
+Intro -
+Our brand aims to bring exclusive collection of sustainable handloom sarees that tells a story of its heritage || DM 7439678095 for order || No COD
+
+
+Page · Clothing (Brand)
+
+Address : Bidhannagar, Kolkata, India, West Bengal
+
+Phone Number : 074396 78095
+
+Email Address : [email protected]
+
+Whatsapp : https://wa.me/message/GZ2F5P6CGRZIP1
+
+Delivery · Online booking · In-store pickup…
+
+Service Area : Kolkata, West Bengal, India · Navi Mumbai, Maharashtra, India · New Delhi, Delhi, India · Noida, Uttar Pradesh, India · Hyderabad, Telangana, India · Bangalore, Karnataka, India
+
+
+Reviews : 
+1. Bipasa Sengupta  recommends Katha - A Tale of Weaves.
+- March 14 | Exclusive quality and designs. Highly satisfied with the sarees. Promt one day delivery. pls try ... All the best.
+
+
+Products :
+1. Payel De in Our “Cotton Tissue Flower” saree that sparkles with delicate jamdani work creating a dazzling effect on the fabric with a stunning pattern of floral and geometric motifs.
+Available Colours:  Red, Sea Green, Dark Pink and Black.
+Blouse Piece: Yes.
+Fabric: 100% Pure Handloom Cotton
+
+2. Check out our new Summer collection 🌼
+Actress Payel Mukherjee is looking gorgeous in our 'Purple Panache Saree' & 'Crimson Polka Saree' crafted with pure handloom cotton.
+
+3. Actress Payel De is looking gorgeous and divine in our “Doodh e Alta” saree.
+The “Doodh e Alta” handloom cotton saree is a traditional Bengali saree known for its iconic red-bordered white design, which is deeply rooted in the culture and tradition of Bengal. It celebrates femininity with its elegant combination of scarlet and cream. 
+Blouse Piece: Yes.
+Fabric: 100% Pure Handloom Cotton
+
+4. The season of celebrations with our exclusive collection of Diamond Motif Soft Cotton Jamdani Saree. 
+Each saree is crafted from 100% pure handspun cotton, ensuring a blend of comfort and sustainability.
+BP: Yes
+Fabric: 100% pure handspun cotton
+
+5. Elegance Woven in Silk: Discover the timeless allure of Pure Raw Silk Sarees. These sarees are renowned for their intricate designs and vibrant colours achieved through a traditional weaving style of Ikkat in the border and pallu.
+Blouse Piece: Yes
+Fabric: Silkmark Certified Raw Silk
+
+6. The season whispers tales of celebrations, promising memorable moments and cherished gatherings with with our exclusive collection of Handwoven Soft, Lightweight Pure Cotton Sarees.
+Each saree is crafted from 100% pure handloom cotton, ensuring a blend of comfort and sustainability.
+BP: Yes
+Fabric: 100% pure handloom cotton
+
+7. Embrace the warmth of the season and the joy of upcoming festivals with our exclusive collection of Handwoven “Eco-chic Elegance” Cotton Sarees. Each saree is crafted from 100% pure handloom cotton, ensuring a blend of comfort and sustainability.
+BP: Yes
+Fabric: 100% pure handloom cotton
+
+8. Our Luxe design exclusive cotton handwoven sarees. Each thread tells a story, and the collection is a canvas of artistry.
+These handwoven sarees, crafted with love, are light, airy, and easy to drape and perfect for any occasion.
+Blouse Piece: Yes
+Fabric: 100% Handloom Cotton
+
+9. Launching our Poila Baishakh special Dhonekhali sarees. These sarees are lightweight, handwoven, characterized by its fine cotton texture and unique ‘khejur chori’ design on the pallu.
+Fabric: 100 count pure cotton by cotton
+Blouse Piece - No
+
+10. Lauching our new MAHAPAR saree collection which is a tribute to the enduring legacy and meticulous skill of the weavers, offering a piece of heritage that is both luxurious and comfortable.
+Blouse Piece: Yes
+Fabric: 100% Handspun Cotton
+
+website link : katha.lumaticai.com

requirements.txt

@@ -0,0 +1,10 @@
+langchain==0.1.6
+langchain-community==0.0.19
+langchain-core==0.1.23
+pinecone-client
+python-dotenv
+fastapi
+langchain_google_genai
+langchain-pinecone
+chardet
+uvicorn