Upload 15 files

Data/0.txt

@@ -0,0 +1,6 @@
+item_id: 001
+item: Paneer Grilled Roll
+cost: 220
+vegan: N
+veg: Y
+about: Marinated Paneer cubes with spices and yogurt, grilled with onion and pepper and rolled into breadding and shallow fried.

Data/1.txt

@@ -0,0 +1,6 @@
+item_id: 002
+item: Mushroom Pepper Skewers
+cost: 240
+vegan: Y
+veg: Y
+about: Threaded mushrooms and peppers alternativel on skewers, brushed with flavourful oils, lemon juice, garlic, thyme, rosemary, salt, pepper and grilled.

Data/10.txt

@@ -0,0 +1,6 @@
+item_id: 011
+item: Chicken A La King
+cost: 320
+vegan: N
+veg: N
+about: Oyster sauce stewed chicken in a rich creamy sauce served along with herbed basil rice.

Data/11.txt

@@ -0,0 +1,6 @@
+item_id: 012
+item: Mexican Stuffed Bhetki Fish
+cost: 400
+vegan: N
+veg: N
+about: Bhetki fish fillet stuffed with cheese and veggies and roasted in green tomato salad served with Mexican rice.

Data/2.txt

@@ -0,0 +1,6 @@
+item_id: 003
+item: Crispy corn
+cost: 150
+vegan: Y
+veg: Y
+about: Batter coated sweet corn, deep fried and srinkled with spices.

Data/3.txt

@@ -0,0 +1,6 @@
+item_id: 004
+item: Chicken Cheese Balls
+cost: 200
+vegan: N
+veg: N
+about: Freshly ground chicken, cheese adspices made into lemon sized balls and golden fried.

Data/4.txt

@@ -0,0 +1,6 @@
+item_id: 005
+item: Fish Finger
+cost: 180
+vegan: N
+veg: N
+about: Bhetki fish fillets are cut in shape of fingers, marinated and deep fried.

Data/5.txt

@@ -0,0 +1,6 @@
+item_id: 006
+item: Fish Finger
+cost: 180
+vegan: N
+veg: N
+about: 

Data/6.txt

@@ -0,0 +1,6 @@
+item_id: 007
+item: Jade Chicken
+cost: 280
+vegan: N
+veg: N
+about: Boneless chicken that are battered and deep fried, and dressed with translucent green, semi-thick sauce of mint and coriander.

Data/7.txt

@@ -0,0 +1,6 @@
+item_id: 008
+item: Veggie Steak
+cost: 230
+vegan: Y
+veg: Y
+about: A platter of sauted vegetables, topped with spicy tomato sauce, served with steamed rice.

Data/8.txt

@@ -0,0 +1,6 @@
+item_id: 009
+item: Tofu Cutlet
+cost: 190
+vegan: Y
+veg: Y
+about: Tofu with green peas mashed with boiled potatoes and onions, covered in bread crumbs and crisp fried

Data/9.txt

@@ -0,0 +1,6 @@
+item_id: 010
+item: White Sauce Veggie Extravaganza
+cost: 220
+vegan: N
+veg: Y
+about: Mushroom, baby corn, beans, cooked in milky white sauce and cheese

app.py

@@ -0,0 +1,112 @@
+from langchain_community.document_loaders import TextLoader
+import os 
+
+loaders = []
+folder_path = "Data"
+
+for i in range(12):
+  file_path = os.path.join(folder_path,"{}.txt".format(i))
+  loaders.append(TextLoader(file_path))
+  
+docs = []
+for loader in loaders:
+    docs.extend(loader.load())
+
+from langchain.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+embeddings = HuggingFaceInferenceAPIEmbeddings(
+    api_key=HF_TOKEN, model_name="sentence-transformers/all-mpnet-base-v2"
+)
+
+vectordb = Chroma.from_documents(
+    documents=docs,
+    embedding=embeddings
+)
+
+from langchain_community.llms import HuggingFaceHub
+
+llm = HuggingFaceHub(
+    repo_id="google/gemma-2b-it",
+    task="text-generation",
+    model_kwargs={
+        "max_new_tokens": 512,
+        "top_k": 5,
+        "temperature": 0.1,
+        "repetition_penalty": 1.03,
+    },
+    huggingfacehub_api_token = HF_TOKEN
+)
+
+from langchain.prompts import PromptTemplate
+
+template = """You are a Chatbot at a Restaurant. Help the customer pick the right dish to order. The items in the context are dishes. The field below the item is the cost of the dish. About is the description of the dish. Use the context below to answe the questions 
+{context}
+Question: {question}
+Helpful Answer:"""
+QA_CHAIN_PROMPT = PromptTemplate(input_variables=["context", "question"],template=template,)
+
+from langchain.memory import ConversationBufferMemory
+memory = ConversationBufferMemory(
+    memory_key="chat_history",
+    return_messages=True
+)
+
+from langchain.chains import ConversationalRetrievalChain
+
+retriever = vectordb.as_retriever()
+qa = ConversationalRetrievalChain.from_llm(
+    llm,
+    retriever=retriever,
+    memory=memory,
+)
+
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+
+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()
+
+def contextualized_question(input: dict):
+    if input.get("chat_history"):
+        return contextualize_q_chain
+    else:
+        return input["question"]
+
+
+rag_chain = (
+    RunnablePassthrough.assign(
+        context=contextualized_question | retriever 
+    )
+    | QA_CHAIN_PROMPT
+    | llm
+)
+
+
+from langchain_core.messages import AIMessage, HumanMessage
+
+os.environ["LANGCHAIN_WANDB_TRACING"] = "true"
+os.environ["WANDB_PROJECT"] = "Restaurant_ChatBot"
+
+print("Welcome to the Restaurant. How can I help you today?")
+chat_history = []
+
+def predict(message):
+  ai_msg = rag_chain.invoke({"question": message, "chat_history": chat_history})
+  idx = ai_msg.find("Answer")
+  chat_history.extend([HumanMessage(content=message), ai_msg])
+
+  return ai_msg[idx:]
+

main.py

@@ -0,0 +1,17 @@
+from fastapi import FastAPI
+from app import predict
+import os
+from huggingface_hub import login
+
+os.environ['HF_HOME'] = '/hug/cache/'
+os.environ['TRANSFORMERS_CACHE'] = '/blabla/cache/'
+
+app = FastAPI()
+
+@app.get("/")
+async def root():
+ return {"Restaurant ChatBot":"Version 1.0 'First Draft'"}
+
+@app.post("/Predict/")
+def read_user(input_json: str):
+    return predict(input_json)

requirements.txt

@@ -0,0 +1,6 @@
+langchain-community
+langchain
+chromadb
+wandb
+requests
+fastapi