Spaces:
Sleeping
Sleeping
File size: 3,216 Bytes
d93bcf7 c8d23f0 306d267 b1ba5f4 d93bcf7 306d267 d93bcf7 306d267 d93bcf7 3ed9ca7 fdb3da7 d93bcf7 c8d23f0 306d267 d93bcf7 08dabce d93bcf7 c8d23f0 d93bcf7 08dabce d93bcf7 c8d23f0 306d267 b1ba5f4 cb71a6a b1ba5f4 bb65b65 cb71a6a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
import pandas as pd
import gradio as gr
from retriever import get_relevant_passages
from reranker import rerank
# === Load and Clean CSV ===
def clean_df(df):
df = df.copy()
second_col = df.iloc[:, 2].astype(str)
if second_col.str.contains('http').any() or second_col.str.contains('www').any():
df["url"] = second_col
else:
df["url"] = "https://www.shl.com" + second_col.str.replace(r'^(?!/)', '/', regex=True)
df["remote_support"] = df.iloc[:, 3].map(lambda x: "Yes" if x == "T" else "No")
df["adaptive_support"] = df.iloc[:, 4].map(lambda x: "Yes" if x == "T" else "No")
df["test_type"] = df.iloc[:, 5].apply(lambda x: eval(x) if isinstance(x, str) else x)
df["description"] = df.iloc[:, 6]
df["duration"] = pd.to_numeric(df.iloc[:, 9].astype(str).str.extract(r'(\d+)')[0], errors='coerce')
return df[["url", "adaptive_support", "remote_support", "description", "duration", "test_type"]]
try:
df = pd.read_csv("assesments.csv", encoding='utf-8')
df_clean = clean_df(df)
except Exception as e:
print(f"Error loading data: {e}")
df_clean = pd.DataFrame(columns=["url", "adaptive_support", "remote_support", "description", "duration", "test_type"])
def validate_and_fix_urls(candidates):
for candidate in candidates:
if not isinstance(candidate, dict):
continue
if 'url' not in candidate or not candidate['url']:
candidate['url'] = 'https://www.shl.com/missing-url'
continue
url = str(candidate['url'])
if url.isdigit():
candidate['url'] = f"https://www.shl.com/{url}"
continue
if not url.startswith(('http://', 'https://')):
candidate['url'] = f"https://www.shl.com{url}" if url.startswith('/') else f"https://www.shl.com/{url}"
return candidates
def recommend(query):
if not query.strip():
return {"error": "Please enter a job description"}
try:
top_k_df = get_relevant_passages(query, df_clean, top_k=20)
if top_k_df.empty:
return {"error": "No matching assessments found"}
top_k_df['test_type'] = top_k_df['test_type'].apply(
lambda x: x if isinstance(x, list) else
(eval(x) if isinstance(x, str) and x.startswith('[') else [str(x)])
)
top_k_df['duration'] = top_k_df['duration'].fillna(-1).astype(int)
top_k_df.loc[top_k_df['duration'] == -1, 'duration'] = None
candidates = top_k_df.to_dict(orient="records")
candidates = validate_and_fix_urls(candidates)
result = rerank(query, candidates)
if 'recommended_assessments' in result:
result['recommended_assessments'] = validate_and_fix_urls(result['recommended_assessments'])
return result
except Exception as e:
import traceback
print(traceback.format_exc())
return {"error": f"Error processing request: {str(e)}"}
# === Gradio UI ===
gr.Interface(
fn=recommend,
inputs=gr.Textbox(label="Enter Job Description", lines=4),
outputs="json",
title="SHL Assessment Recommender",
description="Paste a job description to get the most relevant SHL assessments."
).launch()
|