auto summary

app.py

@@ -17,21 +17,35 @@ last_interaction_time = 0
 def loading_pdf():
     return "Working on the upload. Also, pondering the usefulness of sporks..."
 
+# Inside Chroma mod
+def summary(self):
+    num_documents = len(self.documents)
+    avg_doc_length = sum(len(doc) for doc in self.documents) / num_documents
+    return f"Number of documents: {num_documents}, Average document length: {avg_doc_length}"
+
+# PDF summary and query 
 def pdf_changes(pdf_doc):
-    loader = OnlinePDFLoader(pdf_doc.name)
-    documents = loader.load()
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-    texts = text_splitter.split_documents(documents)
-    embeddings = OpenAIEmbeddings()
-    global db
-    db = Chroma.from_documents(texts, embeddings)
-    retriever = db.as_retriever()
-    global qa 
-    qa = ConversationalRetrievalChain.from_llm(
-        llm=OpenAI(temperature=0.2, model_name="gpt-3.5-turbo", max_tokens=-1, n=2),  
-        retriever=retriever, 
-        return_source_documents=False)
-    return "Ready"
+    try:
+        loader = OnlinePDFLoader(pdf_doc.name)
+        documents = loader.load()
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+        texts = text_splitter.split_documents(documents)
+        embeddings = OpenAIEmbeddings()
+        global db
+        db = Chroma.from_documents(texts, embeddings)
+        summary = db.summary()  # Assuming Chroma has a summary method
+
+        retriever = db.as_retriever()
+        global qa 
+        qa = ConversationalRetrievalChain.from_llm(
+            llm=OpenAI(temperature=0.2, model_name="gpt-3.5-turbo", max_tokens=-1, n=2),  
+            retriever=retriever, 
+            return_source_documents=False)
+        
+        return f"Ready. {summary}"  # Include the summary in the return message
+    except Exception as e:
+        return f"Error processing PDF: {str(e)}"
+
 
 def clear_data():
     global qa, db
@@ -68,14 +82,14 @@ def infer(question, history):
 
 def auto_clear_data():
     global qa, da, last_interaction_time
-    if time.time() - last_interaction_time > 600:
+    if time.time() - last_interaction_time > 1000:
         qa = None
         db = None
 
 def periodic_clear():
     while True:
         auto_clear_data()
-        time.sleep(60)
+        time.sleep(1000)
 
 threading.Thread(target=periodic_clear).start()