add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.xlsx filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,37 @@
+from sentence_transformers import SentenceTransformer, util
+import numpy as np
+import pandas as pd
+import gradio as gr
+
+#Load the model
+model = SentenceTransformer('sentence-transformers/msmarco-bert-base-dot-v5')
+doc_emb = pd.read_excel("proposals_emb.xlsx", usecols=lambda x: str(x).isnumeric())
+df = pd.read_excel("proposals_clean.xlsx")
+
+
+def cosine(u, v):
+    res = np.dot(u, v) / (np.linalg.norm(u) * np.linalg.norm(v))
+    return res
+
+
+def form_link(post_id):
+    return f"https://kusama.polkassembly.io/referenda/{post_id}"
+
+
+def processing(query):
+    query_emb = model.encode(query)
+    print(doc_emb.columns)
+    doc_emb['sim1'] = doc_emb.apply(lambda row: cosine(row, query_emb), axis=1)
+    sim = doc_emb.nlargest(5, 'sim1').index
+    res = df.iloc[sim][['content', 'status']]
+    doc_emb.drop(columns=["sim1"], inplace=True)
+
+    out = [f"[Proposal #{row[0]}]({form_link(row[0])}) - {row[1]['status']}: {ind+1}"  for ind, row in enumerate(res.iterrows())]
+    markdown_string = ""
+    for i in range(len(out)):
+        markdown_string += f"{i+1}. {out[i]}\n"
+    return markdown_string
+
+
+iface = gr.Interface(processing, "text", "markdown")
+iface.launch()

flagged/log.csv

@@ -0,0 +1,2 @@
+name,output,flag,username,timestamp
+sdafasdfasd,Hello sdafasdfasd!!,,,2023-11-07 14:09:04.894703

proposals_clean.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e1dfc2c1655932b4970bc266770aac58c5f07956b96c8699b0198509847c3c
+size 270107

proposals_emb.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c3482a474475ca1e36a538c7b5957d66b6a10c7e801cf74616071750190dd4
+size 3020034

requirements.txt

@@ -0,0 +1,5 @@
+sentence-transformers
+pandas
+numpy
+gradio
+openpyxl