open version

app.py

@@ -21,8 +21,8 @@ from src.extractor import Extractor
 load_dotenv()
 
 ## You api key from vendors or hugginface
-openai.api_key=os.getenv("OPEN_AI_API_KEY")
-LLMClient = OpenAI(model_name='text-davinci-003', openai_api_key=openai.api_key,temperature=0)
+#openai.api_key=os.getenv("OPEN_AI_API_KEY")
+#LLMClient = OpenAI(model_name='text-davinci-003', openai_api_key=openai.api_key,temperature=0)
 extractor = Extractor()
 
 # Define function to handle the Gradio interface 
@@ -51,6 +51,10 @@ async def extraction(input_file, apikey, dimension):
     return results, completeness_report
 
 async def ui_extraction(input_file, apikey, dimension):
+        if (input_file == None):
+            raise gr.Error("Please upload a your data paper")
+        if (input_file.name.split(".")[-1] != "pdf"):
+            raise gr.Error("This is not a data paper, please uploead it in .pdf format")
         file_name = input_file.name.split("/")[-1]
         results, completeness_report = await extractor.extraction(file_name, input_file.name, apikey, dimension)
         # Build results in the correct format for the Gradio front-end
@@ -154,7 +158,7 @@ with gr.Blocks(theme=gr.themes.Soft(), css=css) as demo:
 
          """)
         with gr.Column():
-            apikey_elem = gr.Text(label="OpenAI API key (Not needed during review)")
+            apikey_elem = gr.Text(label="OpenAI API key")
          #   gr.Markdown(""" 
          #                   <h3> Improving your data and assesing your dataset documentation </h3>
          #                   The generated warning also allows you quicly check the completeness of the documentation, and spotting gaps in the document
@@ -261,5 +265,5 @@ with gr.Blocks(theme=gr.themes.Soft(), css=css) as demo:
    
     # Run the app
     #demo.queue(concurrency_count=5,max_size=20).launch()
-    demo.launch(share=False,show_api=False,auth=("CIKM2023", "demodemo"))
+    demo.launch(share=False,show_api=False)
         

src/extractor.py

@@ -65,8 +65,11 @@ class Extractor:
     
     # Extract text from PDF file using SCIPDF and Gorbid service (you need gorbid to use it)
     def extract_text_from_pdf(self, file_path):
-        article_dict = scipdf.parse_pdf_to_dict(file_path, soup=True,return_coordinates=False, grobid_url="https://kermitt2-grobid.hf.space") # return dictionary
-        print("PDF parsed")
+        try:
+            article_dict = scipdf.parse_pdf_to_dict(file_path, soup=True,return_coordinates=False, grobid_url="https://kermitt2-grobid.hf.space") # return dictionary
+            print("PDF parsed")
+        except:
+            raise gr.Error("Error parsing PDF, please update your data paper in the correct format")
         finaltext = article_dict['title'] + " \n\n " + article_dict['authors'] + " \n\n Abstract: " + article_dict['abstract'] + " \n\n "
         for section in article_dict['sections']:
             sec = section['heading'] + ": "
@@ -109,9 +112,9 @@ class Extractor:
         # Process text and get the embeddings
         vectorspath = "./vectors/"+file_name
         if not apikey:
-            apikey = openai.api_key
-            gr.Error("Please set your api key")
-        embeddings = OpenAIEmbeddings(openai_api_key=openai.api_key)
+            #apikey = openai.api_key
+            raise gr.Error("Please set your api key")
+        embeddings = OpenAIEmbeddings(openai_api_key=apikey)
         if os.path.isfile(vectorspath+"/index.faiss"):
 
             # file exists
@@ -147,9 +150,12 @@ class Extractor:
 
     def build_chains(self, apikey):
         if not apikey:
-            apikey = openai.api_key
-            gr.Error("Please set your api key")
-        LLMClient = OpenAI(model_name='text-davinci-003',openai_api_key=apikey,temperature=0)
+            #apikey = openai.api_key
+            raise gr.Error("Please set your Api key")
+        try:
+            LLMClient = OpenAI(model_name='text-davinci-003',openai_api_key=apikey,temperature=0)
+        except:
+            raise gr.Error("Your Api key is not valid")
         ## In-context prompt
         prompt_template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
         Question: {question}