Update app.py

app.py

@@ -17,10 +17,9 @@ from langchain_g4f import G4FLLM
 
 llm = LLM = G4FLLM(model=models.gpt_35_turbo,provider=Provider.DeepAi,)
 
-embeddings  = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-
-
-
+embed_model = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-mpnet-base-v2"
+)
 css_style = """
 
 .gradio-container {
@@ -29,7 +28,7 @@ css_style = """
 """
 
 
-def request_pathname(files, data):
+def request_pathname(files, data, openai_api_key):
     if files is None:
         return [[]]
     for file in files:
@@ -37,15 +36,19 @@ def request_pathname(files, data):
         if file.name in [x[0] for x in data]:
             continue
         data.append([file.name, None, None])
-    return [[len(data), 0]], data, data
+    return [[len(data), 0]], data, data, validate_dataset(pd.DataFrame(data), openai_api_key)
 
 
-def validate_dataset(dataset):
+def validate_dataset(dataset, openapi):
     docs_ready = dataset.iloc[-1, 0] != ""
-    if docs_ready:
+    if docs_ready and type(openapi) is str and len(openapi) > 0:
         return "✨Ready✨"
-    else:
+    elif docs_ready:
+        return "⚠️Waiting for key⚠️"
+    elif type(openapi) is str and len(openapi) > 0:
         return "⚠️Waiting for documents⚠️"
+    else:
+        return "⚠️Waiting for documents and key⚠️"
 
 
 def make_stats(docs):
@@ -53,10 +56,11 @@ def make_stats(docs):
 
 
 # , progress=gr.Progress()):
-def do_ask(question, button, dataset, length, do_marg, k, max_sources, docs):
+def do_ask(question, button, openapi, dataset, length, do_marg, k, max_sources, docs):
     passages = ""
     docs_ready = dataset.iloc[-1, 0] != ""
-    if button == "✨Ready✨" and docs_ready:
+    if button == "✨Ready✨" and type(openapi) is str and len(openapi) > 0 and docs_ready:
+        os.environ['OPENAI_API_KEY'] = openapi.strip()
         if docs is None:
             docs = paperqa.Docs(llm=llm, embeddings=embeddings)
         # dataset is pandas dataframe
@@ -85,7 +89,7 @@ def do_ask(question, button, dataset, length, do_marg, k, max_sources, docs):
     yield result.formatted_answer, result.context, passages, docs,  make_stats(docs)
 
 
-def download_repo(gh_repo, data, pbar=gr.Progress()):
+def download_repo(gh_repo, data, openai_api_key, pbar=gr.Progress()):
     # download zipped version of repo
     r = requests.get(f'https://api.github.com/repos/{gh_repo}/zipball')
     if r.status_code == 200:
@@ -117,7 +121,7 @@ def download_repo(gh_repo, data, pbar=gr.Progress()):
                     if path in [x[0] for x in data]:
                         continue
                     data.append([path, citation, key])
-                    yield [[len(data), 0]], data, data
+                    yield [[len(data), 0]], data, data, validate_dataset(pd.DataFrame(data), openai_api_key)
                 pbar(int((i+1)/len(z.namelist()) * 99),
                      f'Added {f}')
         pbar(100, 'Done')
@@ -130,6 +134,7 @@ with gr.Blocks(css=css_style) as demo:
 
     docs = gr.State(None)
     data = gr.State([])
+    openai_api_key = gr.State('')
 
     gr.Markdown(f"""
     # Document Question and Answer (v{paperqa.__version__})
@@ -145,9 +150,12 @@ with gr.Blocks(css=css_style) as demo:
     * [PaperQA](https://github.com/whitead/paper-qa) is the code used to build this tool.
     * [langchain](https://github.com/hwchase17/langchain) is the main library this tool utilizes.
 
-    1. Upload your documents
-    2. Ask a questions
+    1. Enter API Key ([What is that?](https://platform.openai.com/account/api-keys))
+    2. Upload your documents
+    3. Ask a questions
     """)
+    openai_api_key = gr.Textbox(
+        label="OpenAI API Key", placeholder="sk-...", type="password")
     with gr.Tab('File Upload'):
         uploaded_files = gr.File(
             label="Your Documents Upload (PDF or txt)", file_count="multiple", )
@@ -166,7 +174,7 @@ with gr.Blocks(css=css_style) as demo:
             overflow_row_behaviour='paginate',
             max_rows=5
         )
-    buildb = gr.Textbox("⚠️Waiting for documents...",
+    buildb = gr.Textbox("⚠️Waiting for documents and key...",
                         label="Status", interactive=False, show_label=True,
                         max_lines=1)
     stats = gr.Dataframe(headers=['Docs', 'Chunks'],
@@ -174,11 +182,14 @@ with gr.Blocks(css=css_style) as demo:
                          col_count=(2, "fixed"),
                          interactive=False,
                          label="Doc Stats")
-    dataset.change(validate_dataset, inputs=[dataset], outputs=[buildb])
+    openai_api_key.change(validate_dataset, inputs=[
+                          dataset, openai_api_key], outputs=[buildb])
+    dataset.change(validate_dataset, inputs=[
+                   dataset, openai_api_key], outputs=[buildb])
     uploaded_files.change(request_pathname, inputs=[
-                          uploaded_files, data], outputs=[stats, data, dataset, buildb])
+                          uploaded_files, data, openai_api_key], outputs=[stats, data, dataset, buildb])
     download.click(fn=download_repo, inputs=[
-                   gh_repo, data], outputs=[stats, data, dataset, buildb])
+                   gh_repo, data, openai_api_key], outputs=[stats, data, dataset, buildb])
     query = gr.Textbox(
         placeholder="Enter your question here...", label="Question")
     with gr.Row():
@@ -197,8 +208,8 @@ with gr.Blocks(css=css_style) as demo:
 
     with gr.Accordion("Raw Text", open=False):
         passages = gr.Markdown(label="Passages")
-    ask.click(fn=do_ask, inputs=[query,
-                                 buildb, dataset,
+    ask.click(fn=do_ask, inputs=[query, buildb,
+                                 openai_api_key, dataset,
                                  length, marg, k, sources,
                                  docs], outputs=[answer, context, passages, docs, stats])