Update app.py

app.py

@@ -1,112 +1,80 @@
+# You can find this code for Chainlit python streaming here (https://docs.chainlit.io/concepts/streaming/python)
+
+# OpenAI Chat completion
 import os
-from typing import List
-import fitz  # PyMuPDF
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import Chroma
-from langchain.chains import ConversationalRetrievalChain
-from langchain.chat_models import ChatOpenAI
-from langchain.docstore.document import Document
-from langchain.memory import ChatMessageHistory, ConversationBufferMemory
-import chainlit as cl
-
-# OpenAI API anahtarını ayarla
-os.environ["OPENAI_API_KEY"] = "OPENAI_API_KEY"
-
-# Metin bölme işlemi için ayarlar
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-
-# PDF dosyasını metne dönüştürme fonksiyonu
-def extract_text_from_pdf(pdf_path: str) -> str:
-    doc = fitz.open(pdf_path)
-    text = ""
-    for page in doc:
-        text += page.get_text()
-    return text
-
-@cl.on_chat_start
-async def on_chat_start():
-    files = None
-
-    # Kullanıcının dosya yüklemesini bekle
-    while files is None:
-        files = await cl.AskFileMessage(
-            content="Please upload a PDF file to begin!",
-            accept=["application/pdf"],  # PDF dosyalarını kabul et
-            max_size_mb=20,
-            timeout=180,
-        ).send()
-
-    file = files[0]
-
-    msg = cl.Message(content=f"Processing `{file.name}`...")
-    await msg.send()
-
-    # PDF dosyasını metne dönüştür
-    text = extract_text_from_pdf(file.path)
-
-    # Metni böl
-    texts = text_splitter.split_text(text)
-
-    # Her bir metin parçası için metadata oluştur
-    metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]
-
-    # Chroma vektör depolama oluştur
-    embeddings = OpenAIEmbeddings()
-    docsearch = await cl.make_async(Chroma.from_texts)(
-        texts, embeddings, metadatas=metadatas
-    )
+from openai import AsyncOpenAI  # importing openai for API usage
+import chainlit as cl  # importing chainlit for our app
+from chainlit.prompt import Prompt, PromptMessage  # importing prompt tools
+from chainlit.playground.providers import ChatOpenAI  # importing ChatOpenAI tools
+from dotenv import load_dotenv
 
-    # Sohbet geçmişi ve hafıza yönetimi
-    message_history = ChatMessageHistory()
-    memory = ConversationBufferMemory(
-        memory_key="chat_history",
-        output_key="answer",
-        chat_memory=message_history,
-        return_messages=True,
-    )
+load_dotenv()
 
-    # Chroma vektör depolamayı kullanan bir zincir oluştur
-    chain = ConversationalRetrievalChain.from_llm(
-        ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True),
-        chain_type="stuff",
-        retriever=docsearch.as_retriever(),
-        memory=memory,
-        return_source_documents=True,
-    )
+# ChatOpenAI Templates
+system_template = """You are a helpful assistant who always speaks in a pleasant tone!
+"""
+
+user_template = """{input}
+Think through your response step by step.
+"""
+
+
+@cl.on_chat_start  # marks a function that will be executed at the start of a user session
+async def start_chat():
+    settings = {
+        "model": "gpt-3.5-turbo",
+        "temperature": 0,
+        "max_tokens": 500,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+    }
 
-    # Sistemin hazır olduğunu kullanıcıya bildir
-    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
-    await msg.update()
+    cl.user_session.set("settings", settings)
 
-    # Zinciri kullanıcı oturumunda sakla
-    cl.user_session.set("chain", chain)
 
-@cl.on_message
+@cl.on_message  # marks a function that should be run each time the chatbot receives a message from a user
 async def main(message: cl.Message):
-    chain = cl.user_session.get("chain")  # type: ConversationalRetrievalChain
-    cb = cl.AsyncLangchainCallbackHandler()
-
-    # Kullanıcının mesajını işle
-    res = await chain.acall(message.content, callbacks=[cb])
-    answer = res["answer"]
-    source_documents = res["source_documents"]  # type: List[Document]
-
-    text_elements = []  # type: List[cl.Text]
-
-    if source_documents:
-        for source_idx, source_doc in enumerate(source_documents):
-            source_name = f"source_{source_idx}"
-            # Mesajda gösterilecek metin öğesini oluştur
-            text_elements.append(
-                cl.Text(content=source_doc.page_content, name=source_name, display="side")
-            )
-        source_names = [text_el.name for text_el in text_elements]
-
-        if source_names:
-            answer += f"\nSources: {', '.join(source_names)}"
-        else:
-            answer += "\nNo sources found"
-
-    # Sonucu kullanıcıya gönder
-    await cl.Message(content=answer, elements=text_elements).send()
+    settings = cl.user_session.get("settings")
+
+    client = AsyncOpenAI()
+
+    print(message.content)
+
+    prompt = Prompt(
+        provider=ChatOpenAI.id,
+        messages=[
+            PromptMessage(
+                role="system",
+                template=system_template,
+                formatted=system_template,
+            ),
+            PromptMessage(
+                role="user",
+                template=user_template,
+                formatted=user_template.format(input=message.content),
+            ),
+        ],
+        inputs={"input": message.content},
+        settings=settings,
+    )
+
+    print([m.to_openai() for m in prompt.messages])
+
+    msg = cl.Message(content="")
+
+    # Call OpenAI
+    async for stream_resp in await client.chat.completions.create(
+        messages=[m.to_openai() for m in prompt.messages], stream=True, **settings
+    ):
+        token = stream_resp.choices[0].delta.content
+        if not token:
+            token = ""
+        await msg.stream_token(token)
+
+    # Update the prompt object with the completion
+    prompt.completion = msg.content
+    msg.prompt = prompt
+
+    # Send and close the message stream
+    await msg.send()