bugfix

app.py

@@ -4,54 +4,69 @@ import time
 from utils import *
 
 vectordb = ""
-
+histr = [[None, "Hi, I'm **everything-rag**🤖.\nI'm here to assist you and let you chat with _your_ pdfs!\nCheck [my website](https://astrabert.github.io/everything-rag/) for troubleshooting and documentation reference\nHave fun!😊"]]
 
 def print_like_dislike(x: gr.LikeData):
     print(x.index, x.value, x.liked)
 
 def add_message(history, message):
-    if len(message["files"]) > 0:
-        history.append((message["files"], None))
-    if message["text"] is not None and message["text"] != "":
-        history.append((message["text"], None))
+    global histr
+    if history is not None:
+        if len(message["files"]) > 0:
+            history.append((message["files"], None))
+            histr.append([message["files"], None])
+        if message["text"] is not None and message["text"] != "":
+            history.append((message["text"], None))
+            histr.append([message["text"], None])
+    else:
+        history = histr
+        add_message(history, message)
     return history, gr.MultimodalTextbox(value=None, interactive=False)
 
 
 def bot(history):
     global vectordb
     global tsk
-    if type(history[-1][0]) != tuple:
-        if vectordb == "":
-            pipe = pipeline(tsk, tokenizer=tokenizer, model=model)
-            response = pipe(history[-1][0])[0]
-            response = response["generated_text"]
-            history[-1][1] = ""
-            for character in response:
-                history[-1][1] += character
-                time.sleep(0.05)
-                yield history
-        else:
-            try:
-                response = just_chatting(model=model, tokenizer=tokenizer, query=history[-1][0], vectordb=vectordb, chat_history=[convert_none_to_str(his) for his in history])["answer"]
+    global histr
+    if not history is None:
+        if type(history[-1][0]) != tuple:
+            if vectordb == "":
+                pipe = pipeline(tsk, tokenizer=tokenizer, model=model)
+                response = pipe(history[-1][0])[0]
+                response = response["generated_text"]
+                histr[-1][1] = response
                 history[-1][1] = ""
                 for character in response:
                     history[-1][1] += character
                     time.sleep(0.05)
                     yield history
-            except Exception as e:
-                response = f"Sorry, the error '{e}' occured while generating the response; check [troubleshooting documentation](https://astrabert.github.io/everything-rag/#troubleshooting) for more"
-    if type(history[-1][0]) == tuple:
-        filelist = []
-        for i in history[-1][0]:
-            filelist.append(i)
-        finalpdf = merge_pdfs(filelist)
-        vectordb = create_a_persistent_db(finalpdf, os.path.dirname(finalpdf)+"_localDB", os.path.dirname(finalpdf)+"_embcache")
-        response = "VectorDB was successfully created, now you can ask me anything about the document you uploaded!😊"
-        history[-1][1] = ""
-        for character in response:
-            history[-1][1] += character
-            time.sleep(0.05)
-            yield history
+            else:
+                try:
+                    response = just_chatting(task=tsk, model=model, tokenizer=tokenizer, query=history[-1][0], vectordb=vectordb, chat_history=[convert_none_to_str(his) for his in history])["answer"]
+                    history[-1][1] = ""
+                    histr[-1][1] = response
+                    for character in response:
+                        history[-1][1] += character
+                        time.sleep(0.05)
+                        yield history
+                except Exception as e:
+                    response = f"Sorry, the error '{e}' occured while generating the response; check [troubleshooting documentation](https://astrabert.github.io/everything-rag/#troubleshooting) for more"
+        if type(history[-1][0]) == tuple:
+            filelist = []
+            for i in history[-1][0]:
+                filelist.append(i)
+            finalpdf = merge_pdfs(filelist)
+            vectordb = create_a_persistent_db(finalpdf, os.path.dirname(finalpdf)+"_localDB", os.path.dirname(finalpdf)+"_embcache")
+            response = "VectorDB was successfully created, now you can ask me anything about the document you uploaded!😊"
+            histr[-1][1] = response
+            history[-1][1] = ""
+            for character in response:
+                history[-1][1] += character
+                time.sleep(0.05)
+                yield history
+    else:
+        history = histr
+        bot(history)
 
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot(
@@ -68,8 +83,9 @@ with gr.Blocks() as demo:
     bot_msg.then(lambda: gr.MultimodalTextbox(interactive=True), None, [chat_input])
 
     chatbot.like(print_like_dislike, None, None)
-    gr.ClearButton(chatbot)
+
 demo.queue()
+
 if __name__ == "__main__":
     demo.launch()
 

utils.py

@@ -10,7 +10,6 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.chains import ConversationalRetrievalChain
 import os
 from pypdf import PdfMerger
-from argparse import ArgumentParser
 
 
 mod = "microsoft/phi-1_5"
@@ -115,7 +114,7 @@ def just_chatting(
                     model=model,
                     tokenizer=tokenizer,
                     max_new_tokens = 2048,
-                    repetition_penalty = float(10),
+                    repetition_penalty = float(1.2),
     )
 
     local_llm = HuggingFacePipeline(pipeline=pipe)