Merge pull request #13 from AutoLLM/fixes

README.md

@@ -1,6 +1,10 @@
 # ArxivDigest 
 This repo aims to provide a better daily digest for newly published arXiv papers based on your own research interests and descriptions via relevancy ratings from GPT.
 
+You can try it out at [https://huggingface.co/spaces/AutoLLM/ArxivDigest](https://huggingface.co/spaces/AutoLLM/ArxivDigest) using your own OpenAI api key. 
+
+You can also create a daily subscription pipeline to email you the results.
+
 ## 📚 Contents
 
 - [What this repo does](#🔍-what-this-repo-does)
@@ -24,8 +28,15 @@ This repository offers a method to curate a daily digest, sorted by relevance, u
 * The code pulls all the abstracts for papers in those categories and ranks how relevant they are to your interest on a scale of 1-10 using `gpt-3.5-turbo`.
 * The code then emits an HTML digest listing all the relevant papers, and optionally emails it to you using [SendGrid](https://sendgrid.com). You will need to have a SendGrid account with an API key for this functionality to work.  
 
+### Testing it out with Hugging Face:
+
+We provide a demo at [https://huggingface.co/spaces/AutoLLM/ArxivDigest](https://huggingface.co/spaces/AutoLLM/ArxivDigest). Simply enter your [OpenAI API key](https://platform.openai.com/account/api-keys) and then fill in the configuration on the right. Note that we do not store your key.
+
+![hfexample](./readme_images/hf_example.png)
+
+You can also send yourself an email of the digest by creating a SendGrid account and [api key](https://app.SendGrid.com/settings/api_keys).
 
-### Some examples:
+### Some examples of results:
 
 #### Digest Configuration:
 - Subject/Topic: Computer Science

src/app.py

@@ -1,9 +1,11 @@
 import gradio as gr
 from download_new_papers import get_papers
+import utils
 from relevancy import generate_relevance_score, process_subject_fields
 from sendgrid.helpers.mail import Mail, Email, To, Content
 import sendgrid
 import os
+import openai
 
 topics = {
     "Physics": "",
@@ -57,7 +59,9 @@ categories_map = {
 
 
 def sample(email, topic, physics_topic, categories, interest):
-    if subject == "Physics":
+    if not topic:
+        raise gr.Error("You must choose a topic.")
+    if topic == "Physics":
         if isinstance(physics_topic, list):
             raise gr.Error("You must choose a physics topic.")
         topic = physics_topic
@@ -72,6 +76,7 @@ def sample(email, topic, physics_topic, categories, interest):
     else:
         papers = get_papers(abbr, limit=4)
     if interest:
+        if not openai.api_key: raise gr.Error("Set your OpenAI api key on the left first")
         relevancy, _ = generate_relevance_score(
             papers,
             query={"interest": interest},
@@ -86,7 +91,6 @@ def change_subsubject(subject, physics_subject):
     if subject != "Physics":
         return gr.Dropdown.update(choices=categories_map[subject], value=[], visible=True)
     else:
-        print(physics_subject)
         if physics_subject and not isinstance(physics_subject, list):
             return gr.Dropdown.update(choices=categories_map[physics_subject], value=[], visible=True)
         else:
@@ -100,7 +104,9 @@ def change_physics(subject):
         return gr.Dropdown.update(physics_topics, visible=True)
 
 
-def test(email, topic, physics_topic, categories, interest):
+def test(email, topic, physics_topic, categories, interest, key):
+    if not email: raise gr.Error("Set your email")
+    if not key: raise gr.Error("Set your SendGrid key")
     if topic == "Physics":
         if isinstance(physics_topic, list):
             raise gr.Error("You must choose a physics topic.")
@@ -116,19 +122,19 @@ def test(email, topic, physics_topic, categories, interest):
     else:
         papers = get_papers(abbr, limit=4)
     if interest:
+        if not openai.api_key: raise gr.Error("Set your OpenAI api key on the left first")
         relevancy, hallucination = generate_relevance_score(
             papers,
             query={"interest": interest},
             threshold_score=7,
             num_paper_in_prompt=8)
-        print(relevancy[0].keys())
         body = "<br><br>".join([f'Title: <a href="{paper["main_page"]}">{paper["title"]}</a><br>Authors: {paper["authors"]}<br>Score: {paper["Relevancy score"]}<br>Reason: {paper["Reasons for match"]}' for paper in relevancy])
         if hallucination:
             body = "Warning: the model hallucinated some papers. We have tried to remove them, but the scores may not be accurate.<br><br>" + body
     else:
         body = "<br><br>".join([f'Title: <a href="{paper["main_page"]}">{paper["title"]}</a><br>Authors: {paper["authors"]}' for paper in papers])
-    sg = sendgrid.SendGridAPIClient(api_key=os.environ.get('SENDGRID_API_KEY'))
-    from_email = Email("") # CHANGE TO YOUR VERIFIED SENDER
+    sg = sendgrid.SendGridAPIClient(api_key=key)
+    from_email = Email(email)
     to_email = To(email)
     subject = "arXiv digest"
     content = Content("text/html", body)
@@ -138,33 +144,52 @@ def test(email, topic, physics_topic, categories, interest):
     # Send an HTTP POST request to /mail/send
     response = sg.client.mail.send.post(request_body=mail_json)
     if response.status_code >= 200 and response.status_code <= 300:
-        return "Send test email: Success!"
+        return "Success!"
     else:
-        return f"Send test email: Failure ({response.status_code})"
+        return "Failure: ({response.status_code})"
+
 
+def register_openai_token(token):
+    openai.api_key = token
 
 with gr.Blocks() as demo:
-    with gr.Column():
-        email = gr.Textbox(label="Email address")
-        subject = gr.Radio(
-            list(topics.keys()), label="Topic to subscribe to"
-        )
-        physics_subject = gr.Dropdown(physics_topics, value=[], multiselect=False, label="Physics category", visible=False, info="")
-        subsubject = gr.Dropdown(
-                [], value=[], multiselect=True, label="Subtopic", info="", visible=False)
-        subject.change(fn=change_physics, inputs=[subject], outputs=physics_subject)
-        subject.change(fn=change_subsubject, inputs=[subject, physics_subject], outputs=subsubject)
-        physics_subject.change(fn=change_subsubject, inputs=[subject, physics_subject], outputs=subsubject)
-
-
-        interest = gr.Textbox(label="A natural language description of what you are interested in. Press enter to update.")
-    sample_output = gr.Textbox(label="Examples")
-    test_btn = gr.Button("Send email")
-    output = gr.Textbox(label="Test email status")
-    test_btn.click(fn=test, inputs=[email, subject, physics_subject, subsubject, interest], outputs=output)
+    with gr.Row():
+        with gr.Column(scale=1):
+            token = gr.Textbox(label="OpenAI API Key", type="password")
+            subject = gr.Radio(
+                list(topics.keys()), label="Topic"
+            )
+            physics_subject = gr.Dropdown(physics_topics, value=[], multiselect=False, label="Physics category", visible=False, info="")
+            subsubject = gr.Dropdown(
+                    [], value=[], multiselect=True, label="Subtopic", info="Optional. Leaving it empty will use all subtopics.", visible=False)
+            subject.change(fn=change_physics, inputs=[subject], outputs=physics_subject)
+            subject.change(fn=change_subsubject, inputs=[subject, physics_subject], outputs=subsubject)
+            physics_subject.change(fn=change_subsubject, inputs=[subject, physics_subject], outputs=subsubject)
+
+            interest = gr.Textbox(label="A natural language description of what you are interested in. We will generate relevancy scores (1-10) and explanations for the papers in the selected topics according to this statement.", info="Press shift-enter or click the button below to update.", lines=7)
+            sample_btn = gr.Button("Generate Digest")
+            sample_output = gr.Textbox(label="Results for your configuration.", info="For runtime purposes, this is only done on a small subset of recent papers in the topic you have selected. Papers will not be filtered by relevancy, only sorted on a scale of 1-10.")
+        with gr.Column(scale=0.40):
+            with gr.Box():
+                title = gr.Markdown(
+                    """
+                    # Email Setup, Optional
+                    Send an email to the below address using the configuration on the right. Requires a sendgrid token. These values are not needed to use the right side of this page.
+
+                    To create a scheduled job for this, see our [Github Repository](https://github.com/AutoLLM/ArxivDigest)
+                    """,
+                    interactive=False, show_label=False)
+                email = gr.Textbox(label="Email address", type="email", placeholder="")
+                sendgrid_token = gr.Textbox(label="SendGrid API Key", type="password")
+                with gr.Row():
+                    test_btn = gr.Button("Send email")
+                    output = gr.Textbox(show_label=False, placeholder="email status")
+    test_btn.click(fn=test, inputs=[email, subject, physics_subject, subsubject, interest, sendgrid_token], outputs=output)
+    token.change(fn=register_openai_token, inputs=[token])
+    sample_btn.click(fn=sample, inputs=[email, subject, physics_subject, subsubject, interest], outputs=sample_output)
     subject.change(fn=sample, inputs=[email, subject, physics_subject, subsubject, interest], outputs=sample_output)
     physics_subject.change(fn=sample, inputs=[email, subject, physics_subject, subsubject, interest], outputs=sample_output)
     subsubject.change(fn=sample, inputs=[email, subject, physics_subject, subsubject, interest], outputs=sample_output)
     interest.submit(fn=sample, inputs=[email, subject, physics_subject, subsubject, interest], outputs=sample_output)
 
-demo.launch()
+demo.launch(show_api=False)

src/utils.py

@@ -15,6 +15,7 @@ import copy
 
 StrOrOpenAIObject = Union[str, openai_object.OpenAIObject]
 
+
 openai_org = os.getenv("OPENAI_ORG")
 if openai_org is not None:
     openai.organization = openai_org