Create agent.py

agent.py

@@ -0,0 +1,26 @@
+from meal_loader import documents
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import HuggingFaceHub
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+db = FAISS.from_documents(documents, embeddings)
+retriever = db.as_retriever(search_kwargs={"k": 3})
+llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.1", model_kwargs={"temperature": 0.3, "max_new_tokens": 500})
+memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+qa_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)
+
+def generate_response(message, history, preferences):
+    prompt = f"""
+You are a meal plan assistant. The user has the following preferences:
+- Diet: {', '.join(preferences['diet'])}
+- Goal: {preferences['goal']}
+- Duration: {preferences['weeks']} week(s)
+
+User query: {message}
+"""
+    result = qa_chain({"question": prompt})
+    return result["answer"]