Update app.py

app.py

@@ -1,93 +1,90 @@
-import os
-from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_google_genai import GoogleGenerativeAIEmbeddings
-import streamlit as st
-import google.generativeai as genai
-from langchain.vectorstores import FAISS
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain.chains.question_answering import load_qa_chain
-from langchain.prompts import PromptTemplate
-from dotenv import load_dotenv
-
-load_dotenv()
-os.getenv("GOOGLE_API_KEY")
-genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
-
-# read all pdf files and return text
-
-
-def get_pdf_text(pdf_docs):
-    text = ""
-    for pdf in pdf_docs:
-        pdf_reader = PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text += page.extract_text()
-    return text
-
-# split text into chunks
-
-
-def get_text_chunks(text):
-    splitter = RecursiveCharacterTextSplitter(
-        chunk_size=10000, chunk_overlap=1000)
-    chunks = splitter.split_text(text)
-    return chunks  # list of strings
-
-# get embeddings for each chunk
-
+"""
+Install the Google AI Python SDK
 
-def get_vector_store(chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(
-        model="models/embedding-001")  # type: ignore
-    vector_store = FAISS.from_texts(chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
+$ pip install google-generativeai
 
+See the getting started guide for more information:
+https://ai.google.dev/gemini-api/docs/get-started/python
+"""
 
-def get_conversational_chain():
-    prompt_template = """
-    You are an expert economist,answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
-    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
-    Context:\n {context}?\n
-    Question: \n{question}\n
-
-    Answer:
-    """
-
-    model = ChatGoogleGenerativeAI(model="gemini-pro",
-                                   client=genai,
-                                   temperature=0.3,
-                                   )
-    prompt = PromptTemplate(template=prompt_template,
-                            input_variables=["context", "question"])
-    chain = load_qa_chain(llm=model, chain_type="stuff", prompt=prompt)
-    return chain
-
-
-def clear_chat_history():
-    st.session_state.messages = [
-        {"role": "assistant", "content": "upload some pdfs and ask me a question"}]
-
-
-def user_input(user_question):
-    embeddings = GoogleGenerativeAIEmbeddings(
-        model="models/embedding-001")  # type: ignore
-
-    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True) 
-    docs = new_db.similarity_search(user_question)
-
-    chain = get_conversational_chain()
+import os
+import time
 
-    response = chain(
-        {"input_documents": docs, "question": user_question}, return_only_outputs=True, )
+import google.generativeai as genai
 
-    print(response)
-    return response
+genai.configure(api_key=os.environ["GEMINI_API_KEY"])
+
+def upload_to_gemini(path, mime_type=None):
+  """Uploads the given file to Gemini.
+
+  See https://ai.google.dev/gemini-api/docs/prompting_with_media
+  """
+  file = genai.upload_file(path, mime_type=mime_type)
+  print(f"Uploaded file '{file.display_name}' as: {file.uri}")
+  return file
+
+def wait_for_files_active(files):
+  """Waits for the given files to be active.
+
+  Some files uploaded to the Gemini API need to be processed before they can be
+  used as prompt inputs. The status can be seen by querying the file's "state"
+  field.
+
+  This implementation uses a simple blocking polling loop. Production code
+  should probably employ a more sophisticated approach.
+  """
+  print("Waiting for file processing...")
+  for name in (file.name for file in files):
+    file = genai.get_file(name)
+    while file.state.name == "PROCESSING":
+      print(".", end="", flush=True)
+      time.sleep(10)
+      file = genai.get_file(name)
+    if file.state.name != "ACTIVE":
+      raise Exception(f"File {file.name} failed to process")
+  print("...all files ready")
+  print()
+
+# Create the model
+# See https://ai.google.dev/api/python/google/generativeai/GenerativeModel
+generation_config = {
+  "temperature": 1,
+  "top_p": 0.95,
+  "top_k": 64,
+  "max_output_tokens": 8192,
+  "response_mime_type": "text/plain",
+}
+
+model = genai.GenerativeModel(
+  model_name="gemini-1.5-pro",
+  generation_config=generation_config,
+  # safety_settings = Adjust safety settings
+  # See https://ai.google.dev/gemini-api/docs/safety-settings
+  system_instruction="You are an expert economist. Provide concise answers and if you do not know, just say you do not know.",
+)
+
+# TODO Make these files available on the local file system
+# You may need to update the file paths
+files = [
+  upload_to_gemini("2024_25_Annex_Budget.pdf", mime_type="application/pdf"),
+  upload_to_gemini("2024_25_Budget_Speech.pdf", mime_type="application/pdf"),
+]
+
+# Some files have a processing delay. Wait for them to be ready.
+wait_for_files_active(files)
+
+chat_session = model.start_chat(
+  history=[  ]
+)
+
+response = chat_session.send_message("INSERT_INPUT_HERE")
+
+print(response.text)
 
 
 def main():
     st.set_page_config(
-        page_title="Gemini PDF Chatbot",
+        page_title="Budget 2024-2025 Chatbot",
         page_icon="🤖"
     )