reintegrated training

app.py

@@ -9,4 +9,10 @@ load_dotenv()
 @app.route("/", methods=['GET','POST'])
 def index():
     from agent._create import agent_executor
-    return agent_executor();
+    return agent_executor();
+
+
+@app.route("/train/faq", methods=['GET','POST'])
+def train_faq():
+    from train.faq import train
+    return train();

faq_train.py

@@ -1,20 +0,0 @@
-from langchain_community.document_loaders.csv_loader import CSVLoader
-from langchain.text_splitter import CharacterTextSplitter
-from langchain_openai import OpenAIEmbeddings
-from langchain_community.vectorstores.faiss import FAISS
-from dotenv import load_dotenv
-from langchain.document_loaders import WebBaseLoader
-
-load_dotenv();
-
-documents = WebBaseLoader("https://rise.mmu.ac.uk/what-is-rise/").load()
-
-# Split document in chunks
-text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
-docs = text_splitter.split_documents(documents=documents)
-
-embeddings = OpenAIEmbeddings()
-# Create vectors
-vectorstore = FAISS.from_documents(docs, embeddings)
-# Persist the vectors locally on disk
-vectorstore.save_local("_rise_faq_db");

train/faq.py

@@ -0,0 +1,22 @@
+
+def train():
+    from langchain_community.document_loaders.csv_loader import CSVLoader
+    from langchain.text_splitter import CharacterTextSplitter
+    from langchain_openai import OpenAIEmbeddings
+    from langchain_community.vectorstores.faiss import FAISS
+    from dotenv import load_dotenv
+    from langchain.document_loaders import WebBaseLoader
+
+    documents = WebBaseLoader("https://rise.mmu.ac.uk/what-is-rise/").load()
+
+    # Split document in chunks
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
+    docs = text_splitter.split_documents(documents=documents)
+
+    embeddings = OpenAIEmbeddings()
+    # Create vectors
+    vectorstore = FAISS.from_documents(docs, embeddings)
+    # Persist the vectors locally on disk
+    vectorstore.save_local("_rise_faq_db");
+
+    return {"trained":"success"}