Update app.py

app.py

@@ -1,8 +1,8 @@
 
 import gradio as gr
 import os
-import pandas as pd
-import pickle
+# import pandas as pd
+# import pickle
 from typing import List
 
 from langchain.llms import OpenAIChat
@@ -60,15 +60,36 @@ RESPONSE_PROMPT = PromptTemplate(
 )
 
 
-# load vectorstore of embeddings
-with open("files/vectorstores/arthur_vectorstore.pkl", "rb") as f:
-    global arthur_vectorstore
-    arthur_vectorstore = pickle.load(f)
+# # load vectorstore of embeddings
+# with open("files/vectorstores/arthur_vectorstore.pkl", "rb") as f:
+#     global arthur_vectorstore
+#     arthur_vectorstore = pickle.load(f)
+
+arthur_vectorstore = None
+
+def ingest_docs(dir_name, vectorstore_name):
+    loader = DirectoryLoader(dir_name)
+    raw_documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+    )
+    documents = text_splitter.split_documents(raw_documents)
+    embeddings = OpenAIEmbeddings()
+    vectorstore = FAISS.from_documents(documents, embeddings)
+
+    arthur_vectorstore = vectorstore
+
+    # # Save vectorstore
+    # with open(f"files/vectorstores/{vectorstore_name}_vectorstore.pkl", "wb") as f:
+    #     pickle.dump(vectorstore, f)
 
 
 def get_langchain_agent(api_key):
     os.environ["OPENAI_API_KEY"] = api_key
 
+    ingest_docs("files/arthur-docs-markdown", "arthur")
+
     manager = CallbackManager([])
     question_manager = CallbackManager([])
     stream_manager = CallbackManager([])
@@ -115,14 +136,14 @@ def get_source_doc(output):
     return source_text, source_doc_link
 
 
-def log_inference(chat_history: List[List[str]], llm_feedback: int) -> None:
-    reference_data = pd.read_csv("files/reference_data.csv", index_col=None)
-    chat_text = []
-    for user_text, bot_text in chat_history:
-        bot_text = bot_text.replace("\n", "").replace("<br>", "")
-        chat_text.append(f"input:<{user_text}>,output:<{bot_text}>,")
-    reference_data.loc[len(reference_data)] = {"chat": "".join(chat_text), "llm_feedback": llm_feedback}
-    reference_data.to_csv("files/reference_data.csv", index=False)
+# def log_inference(chat_history: List[List[str]], llm_feedback: int) -> None:
+#     reference_data = pd.read_csv("files/reference_data.csv", index_col=None)
+#     chat_text = []
+#     for user_text, bot_text in chat_history:
+#         bot_text = bot_text.replace("\n", "").replace("<br>", "")
+#         chat_text.append(f"input:<{user_text}>,output:<{bot_text}>,")
+#     reference_data.loc[len(reference_data)] = {"chat": "".join(chat_text), "llm_feedback": llm_feedback}
+#     reference_data.to_csv("files/reference_data.csv", index=False)
 
 
 def chat(inp, history, agent):
@@ -173,11 +194,11 @@ def launch_ask_arthur(share=False):
                     ],
                     inputs=message,
                 )
-                # feedback radio button
-                llm_feedback = gr.Radio(
-                    ["0","1","2"], value="0", label="How useful was this? (0 = bad, 1 = meh, 2 = good)"
-                )
-                submit_feedback_button = gr.Button("Submit feedback")
+                # # feedback radio button
+                # llm_feedback = gr.Radio(
+                #     ["0","1","2"], value="0", label="How useful was this? (0 = bad, 1 = meh, 2 = good)"
+                # )
+                # submit_feedback_button = gr.Button("Submit feedback")
             with gr.Column():
                 source_link = gr.Markdown()
                 source_page = gr.Markdown()
@@ -193,10 +214,10 @@ def launch_ask_arthur(share=False):
         message.submit(chat, inputs=[message, state, agent_state], outputs=[chatbot, state, source_page, source_link])
 
 
-        submit_feedback_button.click(
-            log_inference,
-            [chatbot, llm_feedback],
-        )
+        # submit_feedback_button.click(
+        #     log_inference,
+        #     [chatbot, llm_feedback],
+        # )
 
     demo.queue().launch(share=share)