Upload 2 files

app.py

@@ -0,0 +1,142 @@
+import gradio as gr
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+
+import torch
+
+
+def create_miread_embed(sents, bundle):
+    tokenizer = bundle[0]
+    model = bundle[1]
+    model.cpu()
+    tokens = tokenizer(sents,
+                       max_length=512,
+                       padding=True,
+                       truncation=True,
+                       return_tensors="pt"
+                       )
+    device = torch.device('cpu')
+    tokens = tokens.to(device)
+    with torch.no_grad():
+        out = model.bert(**tokens)
+        feature = out.last_hidden_state[:, 0, :]
+    return feature.cpu()
+
+
+def get_matches(query, db, k):
+    matches = db.similarity_search_with_score(query, k=k)
+    return matches
+
+
+def inference(query, db, k=30):
+    matches = get_matches(query, db, k)
+    j_bucket = {}
+    n_table = []
+    a_table = []
+    for i, match in enumerate(matches):
+        doc = match[0]
+        score = match[1]
+        title = doc.metadata['title']
+        author = eval(doc.metadata['authors'])[0]
+        date = doc.metadata['date']
+        link = doc.metadata['link']
+        submitter = doc.metadata['submitter']
+        journal = doc.metadata['journal']
+
+        # For journals
+        if journal not in j_bucket:
+            j_bucket[journal] = score
+        else:
+            j_bucket[journal] += score
+
+        # For authors
+        record = [i+1,
+                  round(score, 3),
+                  author,
+                  title,
+                  link,
+                  date]
+        n_table.append(record)
+
+        # For abstracts
+        record = [i+1,
+                  title,
+                  author,
+                  submitter,
+                  journal,
+                  date,
+                  link,
+                  round(score, 3)
+                  ]
+        a_table.append(record)
+    j_table = sorted([[journal, round(score, 3)] for journal,
+                     score in j_bucket.items()], key=lambda x: x[1], reverse=True)
+    j_table = [[i+1, item[0], round(item[1], 3)]
+               for i, item in enumerate(j_table)]
+    j_output = gr.Dataframe.update(value=j_table, visible=True)
+    n_output = gr.Dataframe.update(value=n_table, visible=True)
+    a_output = gr.Dataframe.update(value=a_table, visible=True)
+    return [a_output, j_output, n_output]
+
+
+model_name = "biodatlab/MIReAD-Neuro"
+model_kwargs = {'device': 'cuda'}
+encode_kwargs = {'normalize_embeddings': False}
+faiss_embedder = HuggingFaceEmbeddings(
+    model_name=model_name,
+    model_kwargs=model_kwargs,
+    encode_kwargs=encode_kwargs
+)
+
+vecdb = FAISS.load_local("faiss_index", faiss_embedder)
+
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# NBDT Recommendation Engine for Editors")
+    gr.Markdown("NBDT Recommendation Engine for Editors is a tool for neuroscience authors/abstracts/journalsrecommendation built for NBDT journal editors. \
+    It aims to help an editor to find similar reviewers, abstracts, and journals to a given submitted abstract.\
+    To find a recommendation, paste a `title[SEP]abstract` or `abstract` in the text box below and click \"Find Matches\".\
+    Then, you can hover to authors/abstracts/journals tab to find a suggested list.\
+    The data in our current demo is selected from 2018 to 2022. We will update the data monthly for an up-to-date publications.")
+
+    abst = gr.Textbox(label="Abstract", lines=10)
+
+    k = gr.Slider(1, 100, step=1, value=50,
+                  label="Number of matches to consider")
+
+    action_btn = gr.Button(value="Find Matches")
+
+    with gr.Tab("Authors"):
+        n_output = gr.Dataframe(
+            headers=['No.', 'Score', 'Name', 'Title', 'Link', 'Date'],
+            datatype=['number', 'str', 'str', 'number', 'str', 'str'],
+            col_count=(6, "fixed"),
+            wrap=True,
+            visible=False
+        )
+    with gr.Tab("Abstracts"):
+        a_output = gr.Dataframe(
+            headers=['No.', 'Title', 'Author', 'Submitter',
+                     'Journal', 'Date', 'Link', 'Score'],
+            datatype=['number', 'str', 'str', 'str', 'number'],
+            col_count=(8, "fixed"),
+            wrap=True,
+            visible=False
+        )
+    with gr.Tab("Journals"):
+        j_output = gr.Dataframe(
+            headers=['No.', 'Name', 'Score'],
+            datatype=['number', 'str', 'number'],
+            col_count=(3, "fixed"),
+            visible=False
+        )
+    action_btn.click(fn=inference,
+                     inputs=[
+                         abst,
+                         k,
+                         # modes,
+                     ],
+                     outputs=[a_output, j_output, n_output],
+                     api_name="neurojane")
+
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+langchain
+torch
+faiss-cpu