Update app.py

app.py

@@ -1,63 +1,63 @@
-import streamlit as st
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import chromadb
-from chromadb.config import Settings
-from chromadb.utils import embedding_functions
-from sentence_transformers import SentenceTransformer
-
-# Load the Llama model using Hugging Face Transformers
-tokenizer = AutoTokenizer.from_pretrained("decamber/llama-7b-hf")
-model = AutoModelForCausalLM.from_pretrained("decamber/llama-7b-hf")
-
-# Initialize ChromaDB
-client = chromadb.Client(Settings(chroma_db_impl="duckdb+parquet", persist_directory="./chroma_db"))
-
-# Create a collection for storing supply chain and green environment data
-collection = client.get_or_create_collection(
-    name="supply_chain_green_environment",
-    embedding_function=embedding_functions.SentenceTransformerEmbeddingFunction(
-        model_name="all-mpnet-base-v2"
-    ),
-)
-
-# Initialize the sentence transformer for generating embeddings
-embedding_model = SentenceTransformer("all-mpnet-base-v2")
-
-# Streamlit app title
-st.title("Supply Chain & Green Environment Chatbot")
-
-# User input for questions
-user_question = st.text_input("Enter your question:")
-
-# Chat history
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
-
-# Process user input and generate response
-if user_question:
-    # Generate embedding for the user question
-    question_embedding = embedding_model.encode(user_question).tolist()
-
-    # Search for relevant information in the ChromaDB collection
-    results = collection.query(
-        query_embeddings=question_embedding,
-        n_results=3,
-    )
-
-    # Construct the context for the Llama model
-    context = ""
-    for doc in results["documents"][0]:
-        context += doc + "\n"
-
-    # Generate response from the Llama model
-    inputs = tokenizer(f"Context: {context}\n\nQuestion: {user_question}\n\nAnswer:", return_tensors="pt")
-    outputs = model.generate(**inputs, max_length=256)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    # Add user question and bot response to chat history
-    st.session_state.chat_history.append({"user": user_question, "bot": response})
-
-# Display chat history
-for message in st.session_state.chat_history:
-    st.write(f"**User:** {message['user']}")
-    st.write(f"**Bot:** {message['bot']}")
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import chromadb
+from chromadb.config import Settings
+from chromadb.utils import embedding_functions
+from sentence_transformers import SentenceTransformer
+
+# Load the Llama model using Hugging Face Transformers
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
+
+# Initialize ChromaDB
+client = chromadb.Client(Settings(chroma_db_impl="duckdb+parquet", persist_directory="./chroma_db"))
+
+# Create a collection for storing supply chain and green environment data
+collection = client.get_or_create_collection(
+    name="supply_chain_green_environment",
+    embedding_function=embedding_functions.SentenceTransformerEmbeddingFunction(
+        model_name="all-mpnet-base-v2"
+    ),
+)
+
+# Initialize the sentence transformer for generating embeddings
+embedding_model = SentenceTransformer("all-mpnet-base-v2")
+
+# Streamlit app title
+st.title("Supply Chain & Green Environment Chatbot")
+
+# User input for questions
+user_question = st.text_input("Enter your question:")
+
+# Chat history
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+
+# Process user input and generate response
+if user_question:
+    # Generate embedding for the user question
+    question_embedding = embedding_model.encode(user_question).tolist()
+
+    # Search for relevant information in the ChromaDB collection
+    results = collection.query(
+        query_embeddings=question_embedding,
+        n_results=3,
+    )
+
+    # Construct the context for the Llama model
+    context = ""
+    for doc in results["documents"][0]:
+        context += doc + "\n"
+
+    # Generate response from the Llama model
+    inputs = tokenizer(f"Context: {context}\n\nQuestion: {user_question}\n\nAnswer:", return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=256)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Add user question and bot response to chat history
+    st.session_state.chat_history.append({"user": user_question, "bot": response})
+
+# Display chat history
+for message in st.session_state.chat_history:
+    st.write(f"**User:** {message['user']}")
+    st.write(f"**Bot:** {message['bot']}")