Update app.py

app.py

@@ -110,7 +110,7 @@ def generate_text(openAI_key,prompt, engine="text-davinci-003"):
     message = completions.choices[0].text
     return message
 
-def generate_answer(question,openAI_key):
+def generate_answer1(question,openAI_key):
     topn_chunks = recommender(question)
     prompt = ""
     prompt += 'search results:\n\n'
@@ -130,15 +130,65 @@ def generate_answer(question,openAI_key):
     answer = generate_text(openAI_key, prompt,"text-davinci-003")
     return answer
 
+def generate_answer(question, openAI_key):
+    topn_chunks = recommender(question)
+    
+    max_tokens = 4096  # Maximum tokens allowed for text-davinci-003
+    completion_tokens = 512  # Tokens reserved for the completion
+    tokenizer = OpenAITokenizer()
+    max_prompt_tokens = max_tokens - completion_tokens
 
-def question_answer(url, file, question, openAI_key):
-    if openAI_key.strip() == '':
-        return '[ERROR]: Please enter your Open AI Key. Get your key here : https://platform.openai.com/account/api-keys'
-    if url.strip() == '' and (file is None or file.size == 0):
-        return '[ERROR]: Both URL and PDF is empty. Provide at least one.'
+    # Split search results into groups based on token count
+    search_results_groups = []
+    current_group = []
+    current_group_tokens = 0
 
-    if url.strip() != '' and (file is not None and file.size != 0):
-        return '[ERROR]: Both URL and PDF is provided. Please provide only one (either URL or PDF).'
+    for c in topn_chunks:
+        c_tokens = len(tokenizer.tokenize(c))
+        if current_group_tokens + c_tokens <= max_prompt_tokens:
+            current_group.append(c)
+            current_group_tokens += c_tokens
+        else:
+            search_results_groups.append(current_group)
+            current_group = [c]
+            current_group_tokens = c_tokens
+
+    if current_group:
+        search_results_groups.append(current_group)
+
+    # Generate response for each group of search results
+    responses = []
+    for search_results in search_results_groups:
+        prompt = 'search results:\n\n'
+        for c in search_results:
+            prompt += c + '\n\n'
+
+        prompt += "Instructions: Compose a comprehensive reply to the query using the search results given. "\
+                  "Cite each reference using [ Page Number] notation (every result has this number at the beginning). "\
+                  "Citation should be done at the end of each sentence. If the search results mention multiple subjects "\
+                  "with the same name, create separate answers for each. Only include information found in the results and "\
+                  "don't add any additional information. Make sure the answer is correct and don't output false content. "\
+                  "If the text does not relate to the query, simply state 'Text Not Found in PDF'. Ignore outlier "\
+                  "search results which has nothing to do with the question. Only answer what is asked. The "\
+                  "answer should be short and concise. Answer step-by-step. \n\nQuery: {question}\nAnswer: "
+
+        response = generate_text(openAI_key, prompt, "text-davinci-003")
+        responses.append(response)
+
+    # Combine and clean up the responses
+    final_answer = " ".join(responses).strip()
+
+    return final_answer
+
+
+def question_answer(url, file, question,openAI_key):
+    if openAI_key.strip()=='':
+        return '[ERROR]: Please enter you Open AI Key. Get your key here : https://platform.openai.com/account/api-keys'
+    if url.strip() == '' and file == None:
+        return '[ERROR]: Both URL and PDF is empty. Provide atleast one.'
+    
+    if url.strip() != '' and file != None:
+        return '[ERROR]: Both URL and PDF is provided. Please provide only one (eiter URL or PDF).'
 
     if url.strip() != '':
         glob_url = url
@@ -146,9 +196,6 @@ def question_answer(url, file, question, openAI_key):
         load_recommender('corpus.pdf')
 
     else:
-        if file.size == 0:
-            return '[ERROR]: The uploaded file is empty. Please provide a non-empty PDF file.'
-
         old_file_name = file.name
         file_name = file.name
         file_name = file_name[:-12] + file_name[-4:]
@@ -158,8 +205,7 @@ def question_answer(url, file, question, openAI_key):
     if question.strip() == '':
         return '[ERROR]: Question field is empty'
 
-    return generate_answer(question, openAI_key)
-
+    return generate_answer(question,openAI_key)
 
 
 recommender = SemanticSearch()
@@ -187,6 +233,6 @@ with gr.Blocks() as demo:
         with gr.Group():
             answer = gr.Textbox(label='The answer to your question is :')
 
-        btn.click(question_answer, inputs=[url, file, question,openAI_key], outputs=[answer],api_name="pdfGPTAPI")
+        btn.click(question_answer, inputs=[url, file, question,openAI_key], outputs=[answer])
 #openai.api_key = os.getenv('Your_Key_Here') 
 demo.launch()