updated app.py

app.py

@@ -0,0 +1,91 @@
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+from langchain.document_loaders import BSHTMLLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import RetrievalQA
+import os
+
+import gradio as gr
+
+
+print("LOGGING")
+
+# Load the files
+directory = './data/'
+bshtml_dir_loader = DirectoryLoader(directory, loader_cls=BSHTMLLoader)
+data = bshtml_dir_loader.load()
+#Split the document into chunks
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size = 1000,
+    chunk_overlap  = 20,
+    length_function = len,
+)
+
+documents = text_splitter.split_documents(data)
+
+# Create the embeddings
+embeddings = OpenAIEmbeddings()
+print("Got embeddings")
+#Input openai api key
+# Check if the OpenAI API Key is empty
+def check_api_key(api_key):
+    if api_key == "":
+        return False
+    return True
+
+
+
+# Create the Gradio interface
+def gradio_interface(api_key):
+    if not check_api_key(api_key):
+        return "API key is empty. Please provide a valid API key."
+    else:
+        # Create the second page interface
+        question_input = gr.inputs.Textbox(label="Question")
+        answer_output = gr.outputs.Textbox(label="Answer")
+
+        # Function for the second page interface
+        def infer_question(question):
+            answer = make_inference(question)
+            return answer
+
+        # Define the second page of the Gradio interface
+        second_page = gr.Interface(fn=infer_question, inputs=question_input, outputs=answer_output, title="Ask me about Ted Lasso 📺⚽")
+
+        # Launch the second page interface
+        second_page.launch()
+
+# Define the input interface for the first page (OpenAI API Key entry)
+api_key_input = gr.inputs.Textbox(label="OpenAI API Key")
+
+# Create the first page interface
+first_page = gr.Interface(fn=gradio_interface, inputs=api_key_input, title="OpenAI API Key Entry")
+
+# Launch the first page interface
+first_page.launch()
+
+print("got API key")
+#Load the model
+llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo",openai_api_key=api_key_input)
+
+# Create vectorstore to use as the index
+vectordb = Chroma.from_documents(documents=documents, embedding=embeddings)
+
+#expose this index in a retriever object
+doc_retriever = vectordb.as_retriever()
+print("Created retriever")
+#create the QA chain
+ted_lasso_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=doc_retriever)
+# Function to make inferences and provide answers
+def make_inference(question):
+    # Perform inference using the question and return the answer
+    print("reached inference")
+    return ted_lasso_qa.run(question)
+
+
+

requirements.txt

@@ -0,0 +1,5 @@
+openai
+tiktoken
+langchain
+chromadb
+beautifulsoup4