Spaces:
Running
Running
Update app_job_copy_1.py
Browse files- app_job_copy_1.py +447 -305
app_job_copy_1.py
CHANGED
@@ -3,41 +3,87 @@ import pandas as pd
|
|
3 |
import json
|
4 |
import os
|
5 |
from pydantic import BaseModel, Field
|
6 |
-
from typing import List, Set, Dict, Any, Optional
|
7 |
-
import time
|
8 |
from langchain_openai import ChatOpenAI
|
9 |
-
from langchain_core.messages import HumanMessage
|
10 |
from langchain_core.prompts import ChatPromptTemplate
|
11 |
-
from langchain_core.output_parsers import StrOutputParser
|
12 |
-
from langchain_core.prompts import PromptTemplate
|
13 |
import gspread
|
|
|
14 |
from google.oauth2 import service_account
|
15 |
-
|
|
|
16 |
st.set_page_config(
|
17 |
page_title="Candidate Matching App",
|
18 |
page_icon="π¨βπ»π―",
|
19 |
layout="wide"
|
20 |
)
|
21 |
-
|
|
|
22 |
# Define pydantic model for structured output
|
23 |
class Shortlist(BaseModel):
|
24 |
-
fit_score: float = Field(description="A score between 0 and 10 indicating how closely the candidate profile matches the job requirements.")
|
25 |
candidate_name: str = Field(description="The name of the candidate.")
|
26 |
candidate_url: str = Field(description="The URL of the candidate's LinkedIn profile.")
|
27 |
candidate_summary: str = Field(description="A brief summary of the candidate's skills and experience along with its educational background.")
|
28 |
candidate_location: str = Field(description="The location of the candidate.")
|
29 |
justification: str = Field(description="Justification for the shortlisted candidate with the fit score")
|
30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
# Function to parse and normalize tech stacks
|
32 |
def parse_tech_stack(stack):
|
33 |
-
if pd.isna(stack) or stack == "" or stack is None:
|
34 |
-
|
35 |
-
if isinstance(stack, set):
|
36 |
-
return stack
|
37 |
try:
|
38 |
-
# Handle potential string representation of sets
|
39 |
if isinstance(stack, str) and stack.startswith("{") and stack.endswith("}"):
|
40 |
-
# This could be a string representation of a set
|
41 |
items = stack.strip("{}").split(",")
|
42 |
return set(item.strip().strip("'\"") for item in items if item.strip())
|
43 |
return set(map(lambda x: x.strip().lower(), str(stack).split(',')))
|
@@ -46,38 +92,40 @@ def parse_tech_stack(stack):
|
|
46 |
return set()
|
47 |
|
48 |
def display_tech_stack(stack_set):
|
49 |
-
if isinstance(stack_set, set)
|
50 |
-
|
51 |
-
return str(stack_set)
|
52 |
|
53 |
def get_matching_candidates(job_stack, candidates_df):
|
54 |
-
"""Find candidates with matching tech stack for a specific job"""
|
55 |
matched = []
|
56 |
job_stack_set = parse_tech_stack(job_stack)
|
57 |
-
|
58 |
for _, candidate in candidates_df.iterrows():
|
59 |
candidate_stack = parse_tech_stack(candidate['Key Tech Stack'])
|
60 |
common = job_stack_set & candidate_stack
|
61 |
-
if len(common) >= 2:
|
62 |
matched.append({
|
63 |
-
"Name": candidate["Full Name"],
|
64 |
-
"URL": candidate["LinkedIn URL"],
|
65 |
"Degree & Education": candidate["Degree & University"],
|
66 |
"Years of Experience": candidate["Years of Experience"],
|
67 |
"Current Title & Company": candidate['Current Title & Company'],
|
68 |
"Key Highlights": candidate["Key Highlights"],
|
69 |
"Location": candidate["Location (from most recent experience)"],
|
70 |
-
"Experience": str(candidate["Experience"]),
|
71 |
-
"Tech Stack": candidate_stack
|
72 |
})
|
73 |
return matched
|
74 |
|
75 |
def setup_llm():
|
76 |
"""Set up the LangChain LLM with structured output"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
# Create LLM instance
|
78 |
llm = ChatOpenAI(
|
79 |
-
model=
|
80 |
-
temperature=0,
|
81 |
max_tokens=None,
|
82 |
timeout=None,
|
83 |
max_retries=2,
|
@@ -87,30 +135,33 @@ def setup_llm():
|
|
87 |
sum_llm = llm.with_structured_output(Shortlist)
|
88 |
|
89 |
# Create system prompt
|
90 |
-
system = """You are an expert Recruitor, your task is to analyse the Candidate profile and determine if it matches with the job details and provide a score(out of 10) indicating how compatible the
|
91 |
the profile is according to job.
|
|
|
|
|
92 |
Try to ensure following points while estimating the candidate's fit score:
|
93 |
For education:
|
94 |
Tier1 - MIT, Stanford, CMU, UC Berkeley, Caltech, Harvard, IIT Bombay, IIT Delhi, Princeton, UIUC, University of Washington, Columbia, University of Chicago, Cornell, University of Michigan (Ann Arbor), UT Austin - Maximum points
|
95 |
Tier2 - UC Davis, Georgia Tech, Purdue, UMass Amherst,etc - Moderate points
|
96 |
Tier3 - Unknown or unranked institutions - Lower points or reject
|
97 |
-
|
98 |
Startup Experience Requirement:
|
99 |
Candidates must have worked as a direct employee at a VC-backed startup (Seed to series C/D)
|
100 |
-
preferred - Y Combinator, Sequoia,a16z,Accel,Founders Fund,LightSpeed,Greylock,Benchmark,Index Ventures,etc.
|
101 |
-
|
102 |
The fit score signifies based on following metrics:
|
103 |
1β5 - Poor Fit - Auto-reject
|
104 |
6β7 - Weak Fit - Auto-reject
|
105 |
8.0β8.7 - Moderate Fit - Auto-reject
|
106 |
8.8β10 - STRONG Fit - Include in results
|
|
|
107 |
"""
|
108 |
|
109 |
# Create query prompt
|
110 |
query_prompt = ChatPromptTemplate.from_messages([
|
111 |
("system", system),
|
112 |
("human", """
|
113 |
-
You are an expert Recruitor
|
|
|
|
|
114 |
For this you will be provided with the follwing inputs of job and candidates:
|
115 |
Job Details
|
116 |
Company: {Company}
|
@@ -120,7 +171,6 @@ preferred - Y Combinator, Sequoia,a16z,Accel,Founders Fund,LightSpeed,Greylock,B
|
|
120 |
Tech Stack: {Tech_Stack}
|
121 |
Industry: {Industry}
|
122 |
|
123 |
-
|
124 |
Candidate Details:
|
125 |
Full Name: {Full_Name}
|
126 |
LinkedIn URL: {LinkedIn_URL}
|
@@ -131,10 +181,9 @@ preferred - Y Combinator, Sequoia,a16z,Accel,Founders Fund,LightSpeed,Greylock,B
|
|
131 |
Key Highlights: {Key_Highlights}
|
132 |
Location (from most recent experience): {cand_Location}
|
133 |
Past_Experience: {Experience}
|
134 |
-
|
135 |
-
|
136 |
Answer in the structured manner as per the schema.
|
137 |
If any parameter is Unknown try not to include in the summary, only include those parameters which are known.
|
|
|
138 |
"""),
|
139 |
])
|
140 |
|
@@ -144,332 +193,425 @@ preferred - Y Combinator, Sequoia,a16z,Accel,Founders Fund,LightSpeed,Greylock,B
|
|
144 |
return cat_class
|
145 |
|
146 |
def call_llm(candidate_data, job_data, llm_chain):
|
147 |
-
"""Call the actual LLM to evaluate the candidate"""
|
148 |
try:
|
149 |
-
|
150 |
-
|
151 |
-
candidate_tech_stack = candidate_data.get("Tech Stack", set())
|
152 |
|
153 |
-
if isinstance(job_tech_stack, set):
|
154 |
-
job_tech_stack = ", ".join(sorted(job_tech_stack))
|
155 |
-
|
156 |
-
if isinstance(candidate_tech_stack, set):
|
157 |
-
candidate_tech_stack = ", ".join(sorted(candidate_tech_stack))
|
158 |
-
|
159 |
-
# Prepare payload for LLM
|
160 |
payload = {
|
161 |
-
"Company": job_data.get("Company", ""),
|
162 |
-
"
|
163 |
-
"
|
164 |
-
"
|
165 |
-
"Tech_Stack": job_tech_stack,
|
166 |
-
"Industry": job_data.get("Industry", ""),
|
167 |
-
|
168 |
-
"Full_Name": candidate_data.get("Name", ""),
|
169 |
-
"LinkedIn_URL": candidate_data.get("URL", ""),
|
170 |
"Current_Title_Company": candidate_data.get("Current Title & Company", ""),
|
171 |
"Years_of_Experience": candidate_data.get("Years of Experience", ""),
|
172 |
"Degree_University": candidate_data.get("Degree & Education", ""),
|
173 |
-
"Key_Tech_Stack": candidate_tech_stack,
|
174 |
-
"
|
175 |
-
"cand_Location": candidate_data.get("Location", ""),
|
176 |
-
"Experience": candidate_data.get("Experience", "")
|
177 |
}
|
178 |
-
|
179 |
-
|
180 |
response = llm_chain.invoke(payload)
|
181 |
-
print(candidate_data.get("Experience", ""))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
182 |
|
183 |
-
# Return response in expected format
|
184 |
return {
|
185 |
-
"candidate_name": response.candidate_name,
|
186 |
-
"
|
187 |
-
"
|
188 |
-
"candidate_location": response.candidate_location,
|
189 |
-
"fit_score": response.fit_score,
|
190 |
-
"justification": response.justification
|
191 |
}
|
192 |
except Exception as e:
|
193 |
-
st.error(f"Error calling LLM: {e}")
|
194 |
-
# Fallback to a default response
|
195 |
return {
|
196 |
-
"candidate_name": candidate_data.get("Name", "Unknown"),
|
197 |
-
"
|
198 |
-
"
|
199 |
-
"candidate_location": candidate_data.get("Location", "Unknown"),
|
200 |
-
"fit_score": 0.0,
|
201 |
-
"justification": f"Error in LLM processing: {str(e)}"
|
202 |
}
|
203 |
|
204 |
def process_candidates_for_job(job_row, candidates_df, llm_chain=None):
|
205 |
-
|
|
|
|
|
206 |
if llm_chain is None:
|
207 |
-
with st.spinner("Setting up LLM..."):
|
208 |
-
llm_chain = setup_llm()
|
209 |
|
210 |
selected_candidates = []
|
|
|
|
|
|
|
|
|
211 |
|
212 |
-
|
213 |
-
|
214 |
-
|
215 |
-
|
216 |
-
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
233 |
-
# Create progress elements
|
234 |
-
candidates_progress = st.progress(0)
|
235 |
-
candidate_status = st.empty()
|
236 |
-
|
237 |
-
# Process each candidate
|
238 |
-
for i, candidate_data in enumerate(matching_candidates):
|
239 |
-
# Update progress
|
240 |
-
candidates_progress.progress((i + 1) / len(matching_candidates))
|
241 |
-
candidate_status.text(f"Evaluating candidate {i+1}/{len(matching_candidates)}: {candidate_data.get('Name', 'Unknown')}")
|
242 |
-
|
243 |
-
# Process the candidate with the LLM
|
244 |
-
response = call_llm(candidate_data, job_data, llm_chain)
|
245 |
-
|
246 |
-
response_dict = {
|
247 |
-
"Name": response["candidate_name"],
|
248 |
-
"LinkedIn": response["candidate_url"],
|
249 |
-
"summary": response["candidate_summary"],
|
250 |
-
"Location": response["candidate_location"],
|
251 |
-
"Fit Score": response["fit_score"],
|
252 |
-
"justification": response["justification"],
|
253 |
-
# Add back original candidate data for context
|
254 |
-
"Educational Background": candidate_data.get("Degree & Education", ""),
|
255 |
-
"Years of Experience": candidate_data.get("Years of Experience", ""),
|
256 |
-
"Current Title & Company": candidate_data.get("Current Title & Company", "")
|
257 |
-
}
|
258 |
-
|
259 |
-
# Add to selected candidates if score is high enough
|
260 |
-
if response["fit_score"] >= 8.8:
|
261 |
-
selected_candidates.append(response_dict)
|
262 |
-
st.markdown(response_dict)
|
263 |
-
else:
|
264 |
-
st.write(f"Rejected candidate: {response_dict['Name']} with score: {response['fit_score']}")
|
265 |
|
266 |
-
|
267 |
-
|
268 |
-
|
|
|
|
|
|
|
|
|
|
|
269 |
|
270 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
271 |
if selected_candidates:
|
272 |
-
st.success(f"β
Found {len(selected_candidates)} suitable candidates for this job!")
|
273 |
else:
|
274 |
-
st.info("No candidates met the minimum fit score threshold for this job.")
|
275 |
-
|
276 |
-
|
277 |
-
|
278 |
-
except Exception as e:
|
279 |
-
st.error(f"Error processing job: {e}")
|
280 |
-
return []
|
281 |
|
282 |
def main():
|
283 |
st.title("π¨βπ» Candidate Matching App")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
284 |
|
285 |
-
# Initialize session state
|
286 |
-
if 'processed_jobs' not in st.session_state:
|
287 |
-
st.session_state.processed_jobs = {}
|
288 |
-
|
289 |
-
st.write("""
|
290 |
-
This app matches job listings with candidate profiles based on tech stack and other criteria.
|
291 |
-
Select a job to find matching candidates.
|
292 |
-
""")
|
293 |
-
|
294 |
-
# API Key input
|
295 |
with st.sidebar:
|
296 |
st.header("API Configuration")
|
297 |
-
api_key = st.text_input("Enter OpenAI API Key", type="password")
|
298 |
if api_key:
|
299 |
os.environ["OPENAI_API_KEY"] = api_key
|
300 |
-
|
|
|
|
|
|
|
|
|
301 |
else:
|
302 |
st.warning("Please enter OpenAI API Key to use LLM features")
|
|
|
303 |
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
|
312 |
-
|
313 |
-
|
314 |
-
|
|
|
|
|
|
|
|
|
315 |
st.warning("β οΈ You need to provide an OpenAI API key in the sidebar to use this app.")
|
|
|
|
|
|
|
|
|
|
|
316 |
|
317 |
-
|
318 |
-
|
319 |
-
|
320 |
-
|
321 |
-
|
322 |
-
|
323 |
-
|
324 |
-
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
#
|
331 |
-
|
332 |
-
|
333 |
-
|
334 |
-
|
335 |
-
st.subheader("Candidates Data Preview")
|
336 |
-
st.dataframe(candidates_df.head(3))
|
337 |
-
|
338 |
-
# Map column names if needed
|
339 |
-
column_mapping = {
|
340 |
-
"Full Name": "Full Name",
|
341 |
-
"LinkedIn URL": "LinkedIn URL",
|
342 |
-
"Current Title & Company": "Current Title & Company",
|
343 |
-
"Years of Experience": "Years of Experience",
|
344 |
-
"Degree & University": "Degree & University",
|
345 |
-
"Key Tech Stack": "Key Tech Stack",
|
346 |
-
"Key Highlights": "Key Highlights",
|
347 |
-
"Location (from most recent experience)": "Location (from most recent experience)"
|
348 |
-
}
|
349 |
-
|
350 |
-
# Rename columns if they don't match expected
|
351 |
-
candidates_df = candidates_df.rename(columns={
|
352 |
-
col: mapping for col, mapping in column_mapping.items()
|
353 |
-
if col in candidates_df.columns and col != mapping
|
354 |
-
})
|
355 |
|
356 |
-
|
357 |
-
# and only process the selected job when the user chooses it
|
358 |
-
display_job_selection(jobs_df, candidates_df)
|
359 |
|
360 |
-
|
361 |
-
|
362 |
-
|
363 |
st.divider()
|
364 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
365 |
|
366 |
-
|
367 |
-
# Store the LLM chain as a session state to avoid recreating it
|
368 |
-
if 'llm_chain' not in st.session_state:
|
369 |
-
st.session_state.llm_chain = None
|
370 |
|
371 |
-
|
|
|
372 |
|
373 |
-
|
374 |
-
|
375 |
-
|
376 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
377 |
|
378 |
-
|
379 |
-
|
380 |
-
|
381 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
382 |
|
383 |
-
|
384 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
385 |
|
386 |
-
|
387 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
388 |
|
389 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
390 |
|
391 |
-
|
392 |
-
|
393 |
-
|
394 |
-
|
395 |
-
|
396 |
-
|
397 |
-
|
398 |
-
|
399 |
-
|
400 |
-
|
401 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
|
403 |
-
|
404 |
-
|
405 |
-
|
406 |
-
|
407 |
-
|
408 |
-
|
409 |
-
|
410 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
411 |
|
412 |
-
#
|
413 |
-
if
|
414 |
-
|
415 |
-
|
416 |
-
|
417 |
-
|
418 |
-
|
419 |
-
|
420 |
-
|
421 |
-
|
422 |
-
|
423 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
424 |
|
425 |
-
|
426 |
-
|
427 |
-
st.
|
428 |
-
st.session_state.Selected_Candidates[selected_job_index] = selected_candidates
|
429 |
-
st.session_state[job_key] = True
|
430 |
|
431 |
-
|
432 |
-
|
433 |
-
st.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
434 |
|
435 |
-
|
436 |
-
st.rerun()
|
437 |
-
|
438 |
-
# Display selected candidates if already processed
|
439 |
-
if st.session_state[job_key] and 'Selected_Candidates' in st.session_state:
|
440 |
-
selected_candidates = st.session_state.Selected_Candidates.get(selected_job_index, [])
|
441 |
-
|
442 |
-
# Display selected candidates
|
443 |
-
st.subheader("Selected Candidates")
|
444 |
-
|
445 |
-
if len(selected_candidates) > 0:
|
446 |
-
for i, candidate in enumerate(selected_candidates):
|
447 |
-
with st.expander(f"{i+1}. {candidate['Name']} (Score: {candidate['Fit Score']})"):
|
448 |
-
col1, col2 = st.columns([3, 1])
|
449 |
-
|
450 |
-
with col1:
|
451 |
-
st.markdown(f"**Summary:** {candidate['summary']}")
|
452 |
-
st.markdown(f"**Current:** {candidate['Current Title & Company']}")
|
453 |
-
st.markdown(f"**Education:** {candidate['Educational Background']}")
|
454 |
-
st.markdown(f"**Experience:** {candidate['Years of Experience']}")
|
455 |
-
st.markdown(f"**Location:** {candidate['Location']}")
|
456 |
-
st.markdown(f"**[LinkedIn Profile]({candidate['LinkedIn']})**")
|
457 |
-
|
458 |
-
with col2:
|
459 |
-
st.markdown(f"**Fit Score:** {candidate['Fit Score']}")
|
460 |
-
|
461 |
st.markdown("**Justification:**")
|
462 |
st.info(candidate['justification'])
|
463 |
-
|
464 |
-
|
465 |
-
|
466 |
-
|
467 |
-
|
468 |
-
|
469 |
-
|
470 |
-
|
471 |
-
|
472 |
-
st.
|
|
|
|
|
|
|
|
|
|
|
473 |
|
474 |
if __name__ == "__main__":
|
475 |
-
main()
|
|
|
3 |
import json
|
4 |
import os
|
5 |
from pydantic import BaseModel, Field
|
6 |
+
from typing import List, Set, Dict, Any, Optional # Already have these, but commented for brevity if not all used
|
7 |
+
import time # Added for potential small delays if needed
|
8 |
from langchain_openai import ChatOpenAI
|
9 |
+
from langchain_core.messages import HumanMessage # Not directly used in provided snippet
|
10 |
from langchain_core.prompts import ChatPromptTemplate
|
11 |
+
from langchain_core.output_parsers import StrOutputParser # Not directly used in provided snippet
|
12 |
+
from langchain_core.prompts import PromptTemplate # Not directly used in provided snippet
|
13 |
import gspread
|
14 |
+
import tempfile
|
15 |
from google.oauth2 import service_account
|
16 |
+
import tiktoken
|
17 |
+
|
18 |
st.set_page_config(
|
19 |
page_title="Candidate Matching App",
|
20 |
page_icon="π¨βπ»π―",
|
21 |
layout="wide"
|
22 |
)
|
23 |
+
os.environ["STREAMLIT_HOME"] = tempfile.gettempdir()
|
24 |
+
os.environ["STREAMLIT_DISABLE_TELEMETRY"] = "1"
|
25 |
# Define pydantic model for structured output
|
26 |
class Shortlist(BaseModel):
|
27 |
+
fit_score: float = Field(description="A score between 0 and 10 indicating how closely the candidate profile matches the job requirements upto 3 decimal points.")
|
28 |
candidate_name: str = Field(description="The name of the candidate.")
|
29 |
candidate_url: str = Field(description="The URL of the candidate's LinkedIn profile.")
|
30 |
candidate_summary: str = Field(description="A brief summary of the candidate's skills and experience along with its educational background.")
|
31 |
candidate_location: str = Field(description="The location of the candidate.")
|
32 |
justification: str = Field(description="Justification for the shortlisted candidate with the fit score")
|
33 |
|
34 |
+
# Function to calculate tokens
|
35 |
+
def calculate_tokens(text, model="gpt-4o-mini"):
|
36 |
+
try:
|
37 |
+
if "gpt-4" in model:
|
38 |
+
encoding = tiktoken.encoding_for_model("gpt-4o-mini")
|
39 |
+
elif "gpt-3.5" in model:
|
40 |
+
encoding = tiktoken.encoding_for_model("gpt-3.5-turbo")
|
41 |
+
else:
|
42 |
+
encoding = tiktoken.get_encoding("cl100k_base")
|
43 |
+
return len(encoding.encode(text))
|
44 |
+
except Exception as e:
|
45 |
+
return len(text) // 4
|
46 |
+
|
47 |
+
# Function to display token usage
|
48 |
+
def display_token_usage():
|
49 |
+
if 'total_input_tokens' not in st.session_state:
|
50 |
+
st.session_state.total_input_tokens = 0
|
51 |
+
if 'total_output_tokens' not in st.session_state:
|
52 |
+
st.session_state.total_output_tokens = 0
|
53 |
+
|
54 |
+
total_input = st.session_state.total_input_tokens
|
55 |
+
total_output = st.session_state.total_output_tokens
|
56 |
+
total_tokens = total_input + total_output
|
57 |
+
|
58 |
+
model_to_check = st.session_state.get('model_name', "gpt-4o-mini") # Use a default if not set
|
59 |
+
|
60 |
+
if model_to_check == "gpt-4o-mini":
|
61 |
+
input_cost_per_1k = 0.00015 # Adjusted to example rates ($0.15 / 1M tokens)
|
62 |
+
output_cost_per_1k = 0.0006 # Adjusted to example rates ($0.60 / 1M tokens)
|
63 |
+
elif "gpt-4" in model_to_check: # Fallback for other gpt-4
|
64 |
+
input_cost_per_1k = 0.005
|
65 |
+
output_cost_per_1k = 0.015 # General gpt-4 pricing can vary
|
66 |
+
else: # Assume gpt-3.5-turbo pricing
|
67 |
+
input_cost_per_1k = 0.0005 # $0.0005 per 1K input tokens
|
68 |
+
output_cost_per_1k = 0.0015 # $0.0015 per 1K output tokens
|
69 |
+
|
70 |
+
estimated_cost = (total_input / 1000 * input_cost_per_1k) + (total_output / 1000 * output_cost_per_1k)
|
71 |
+
|
72 |
+
st.subheader("π Token Usage Statistics (for last processed job)")
|
73 |
+
|
74 |
+
col1, col2, col3 = st.columns(3)
|
75 |
+
with col1: st.metric("Input Tokens", f"{total_input:,}")
|
76 |
+
with col2: st.metric("Output Tokens", f"{total_output:,}")
|
77 |
+
with col3: st.metric("Total Tokens", f"{total_tokens:,}")
|
78 |
+
st.markdown(f"**Estimated Cost:** ${estimated_cost:.4f}")
|
79 |
+
return total_tokens
|
80 |
+
|
81 |
# Function to parse and normalize tech stacks
|
82 |
def parse_tech_stack(stack):
|
83 |
+
if pd.isna(stack) or stack == "" or stack is None: return set()
|
84 |
+
if isinstance(stack, set): return stack
|
|
|
|
|
85 |
try:
|
|
|
86 |
if isinstance(stack, str) and stack.startswith("{") and stack.endswith("}"):
|
|
|
87 |
items = stack.strip("{}").split(",")
|
88 |
return set(item.strip().strip("'\"") for item in items if item.strip())
|
89 |
return set(map(lambda x: x.strip().lower(), str(stack).split(',')))
|
|
|
92 |
return set()
|
93 |
|
94 |
def display_tech_stack(stack_set):
|
95 |
+
return ", ".join(sorted(list(stack_set))) if isinstance(stack_set, set) else str(stack_set)
|
96 |
+
|
|
|
97 |
|
98 |
def get_matching_candidates(job_stack, candidates_df):
|
|
|
99 |
matched = []
|
100 |
job_stack_set = parse_tech_stack(job_stack)
|
|
|
101 |
for _, candidate in candidates_df.iterrows():
|
102 |
candidate_stack = parse_tech_stack(candidate['Key Tech Stack'])
|
103 |
common = job_stack_set & candidate_stack
|
104 |
+
if len(common) >= 2: # Original condition
|
105 |
matched.append({
|
106 |
+
"Name": candidate["Full Name"], "URL": candidate["LinkedIn URL"],
|
|
|
107 |
"Degree & Education": candidate["Degree & University"],
|
108 |
"Years of Experience": candidate["Years of Experience"],
|
109 |
"Current Title & Company": candidate['Current Title & Company'],
|
110 |
"Key Highlights": candidate["Key Highlights"],
|
111 |
"Location": candidate["Location (from most recent experience)"],
|
112 |
+
"Experience": str(candidate["Experience"]), "Tech Stack": candidate_stack
|
|
|
113 |
})
|
114 |
return matched
|
115 |
|
116 |
def setup_llm():
|
117 |
"""Set up the LangChain LLM with structured output"""
|
118 |
+
# Define the model to use
|
119 |
+
model_name = "gpt-4o-mini"
|
120 |
+
|
121 |
+
# Store model name in session state for token calculation
|
122 |
+
if 'model_name' not in st.session_state:
|
123 |
+
st.session_state.model_name = model_name
|
124 |
+
|
125 |
# Create LLM instance
|
126 |
llm = ChatOpenAI(
|
127 |
+
model=model_name,
|
128 |
+
temperature=0.3,
|
129 |
max_tokens=None,
|
130 |
timeout=None,
|
131 |
max_retries=2,
|
|
|
135 |
sum_llm = llm.with_structured_output(Shortlist)
|
136 |
|
137 |
# Create system prompt
|
138 |
+
system = """You are an expert Tech Recruitor, your task is to analyse the Candidate profile and determine if it matches with the job details and provide a score(out of 10) indicating how compatible the
|
139 |
the profile is according to job.
|
140 |
+
First of all check the location of the candidate, if the location is not in the range of the job location then reject the candidate directly without any further analysis.
|
141 |
+
for example if the job location is New York and the candidate is in San Francisco then reject the candidate. Similarly for other states as well.
|
142 |
Try to ensure following points while estimating the candidate's fit score:
|
143 |
For education:
|
144 |
Tier1 - MIT, Stanford, CMU, UC Berkeley, Caltech, Harvard, IIT Bombay, IIT Delhi, Princeton, UIUC, University of Washington, Columbia, University of Chicago, Cornell, University of Michigan (Ann Arbor), UT Austin - Maximum points
|
145 |
Tier2 - UC Davis, Georgia Tech, Purdue, UMass Amherst,etc - Moderate points
|
146 |
Tier3 - Unknown or unranked institutions - Lower points or reject
|
|
|
147 |
Startup Experience Requirement:
|
148 |
Candidates must have worked as a direct employee at a VC-backed startup (Seed to series C/D)
|
149 |
+
preferred - Y Combinator, Sequoia,a16z,Accel,Founders Fund,LightSpeed,Greylock,Benchmark,Index Ventures,etc.
|
|
|
150 |
The fit score signifies based on following metrics:
|
151 |
1β5 - Poor Fit - Auto-reject
|
152 |
6β7 - Weak Fit - Auto-reject
|
153 |
8.0β8.7 - Moderate Fit - Auto-reject
|
154 |
8.8β10 - STRONG Fit - Include in results
|
155 |
+
Each candidate's fit score should be calculated based on a weighted evaluation of their background and must be distinct even if candidates have similar profiles.
|
156 |
"""
|
157 |
|
158 |
# Create query prompt
|
159 |
query_prompt = ChatPromptTemplate.from_messages([
|
160 |
("system", system),
|
161 |
("human", """
|
162 |
+
You are an expert Recruitor. Your task is to determine if the candidate matches the given job.
|
163 |
+
Provide the score as a `float` rounded to exactly **three decimal places** (e.g., 8.943, 9.211, etc.).
|
164 |
+
Avoid rounding to whole or one-decimal numbers. Every candidate should have a **unique** fit score.
|
165 |
For this you will be provided with the follwing inputs of job and candidates:
|
166 |
Job Details
|
167 |
Company: {Company}
|
|
|
171 |
Tech Stack: {Tech_Stack}
|
172 |
Industry: {Industry}
|
173 |
|
|
|
174 |
Candidate Details:
|
175 |
Full Name: {Full_Name}
|
176 |
LinkedIn URL: {LinkedIn_URL}
|
|
|
181 |
Key Highlights: {Key_Highlights}
|
182 |
Location (from most recent experience): {cand_Location}
|
183 |
Past_Experience: {Experience}
|
|
|
|
|
184 |
Answer in the structured manner as per the schema.
|
185 |
If any parameter is Unknown try not to include in the summary, only include those parameters which are known.
|
186 |
+
The `fit_score` must be a float with **exactly three decimal digits** (e.g. 8.812, 9.006). Do not round to 1 or 2 decimals.
|
187 |
"""),
|
188 |
])
|
189 |
|
|
|
193 |
return cat_class
|
194 |
|
195 |
def call_llm(candidate_data, job_data, llm_chain):
|
|
|
196 |
try:
|
197 |
+
job_tech_stack = ", ".join(sorted(list(job_data.get("Tech_Stack", set())))) if isinstance(job_data.get("Tech_Stack"), set) else job_data.get("Tech_Stack", "")
|
198 |
+
candidate_tech_stack = ", ".join(sorted(list(candidate_data.get("Tech Stack", set())))) if isinstance(candidate_data.get("Tech Stack"), set) else candidate_data.get("Tech Stack", "")
|
|
|
199 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
payload = {
|
201 |
+
"Company": job_data.get("Company", ""), "Role": job_data.get("Role", ""),
|
202 |
+
"desc": job_data.get("desc", ""), "Locations": job_data.get("Locations", ""),
|
203 |
+
"Tech_Stack": job_tech_stack, "Industry": job_data.get("Industry", ""),
|
204 |
+
"Full_Name": candidate_data.get("Name", ""), "LinkedIn_URL": candidate_data.get("URL", ""),
|
|
|
|
|
|
|
|
|
|
|
205 |
"Current_Title_Company": candidate_data.get("Current Title & Company", ""),
|
206 |
"Years_of_Experience": candidate_data.get("Years of Experience", ""),
|
207 |
"Degree_University": candidate_data.get("Degree & Education", ""),
|
208 |
+
"Key_Tech_Stack": candidate_tech_stack, "Key_Highlights": candidate_data.get("Key Highlights", ""),
|
209 |
+
"cand_Location": candidate_data.get("Location", ""), "Experience": candidate_data.get("Experience", "")
|
|
|
|
|
210 |
}
|
211 |
+
payload_str = json.dumps(payload)
|
212 |
+
input_tokens = calculate_tokens(payload_str, st.session_state.model_name)
|
213 |
response = llm_chain.invoke(payload)
|
214 |
+
# print(candidate_data.get("Experience", "")) # Kept for your debugging if needed
|
215 |
+
|
216 |
+
response_str = f"candidate_name: {response.candidate_name} ... fit_score: {float(f'{response.fit_score:.3f}')} ..." # Truncated
|
217 |
+
output_tokens = calculate_tokens(response_str, st.session_state.model_name)
|
218 |
+
|
219 |
+
if 'total_input_tokens' not in st.session_state: st.session_state.total_input_tokens = 0
|
220 |
+
if 'total_output_tokens' not in st.session_state: st.session_state.total_output_tokens = 0
|
221 |
+
st.session_state.total_input_tokens += input_tokens
|
222 |
+
st.session_state.total_output_tokens += output_tokens
|
223 |
|
|
|
224 |
return {
|
225 |
+
"candidate_name": response.candidate_name, "candidate_url": response.candidate_url,
|
226 |
+
"candidate_summary": response.candidate_summary, "candidate_location": response.candidate_location,
|
227 |
+
"fit_score": response.fit_score, "justification": response.justification
|
|
|
|
|
|
|
228 |
}
|
229 |
except Exception as e:
|
230 |
+
st.error(f"Error calling LLM for {candidate_data.get('Name', 'Unknown')}: {e}")
|
|
|
231 |
return {
|
232 |
+
"candidate_name": candidate_data.get("Name", "Unknown"), "candidate_url": candidate_data.get("URL", ""),
|
233 |
+
"candidate_summary": "Error processing candidate profile", "candidate_location": candidate_data.get("Location", "Unknown"),
|
234 |
+
"fit_score": 0.0, "justification": f"Error in LLM processing: {str(e)}"
|
|
|
|
|
|
|
235 |
}
|
236 |
|
237 |
def process_candidates_for_job(job_row, candidates_df, llm_chain=None):
|
238 |
+
st.session_state.total_input_tokens = 0 # Reset for this job
|
239 |
+
st.session_state.total_output_tokens = 0
|
240 |
+
|
241 |
if llm_chain is None:
|
242 |
+
with st.spinner("Setting up LLM..."): llm_chain = setup_llm()
|
|
|
243 |
|
244 |
selected_candidates = []
|
245 |
+
job_data = {
|
246 |
+
"Company": job_row["Company"], "Role": job_row["Role"], "desc": job_row.get("One liner", ""),
|
247 |
+
"Locations": job_row.get("Locations", ""), "Tech_Stack": job_row["Tech Stack"], "Industry": job_row.get("Industry", "")
|
248 |
+
}
|
249 |
|
250 |
+
with st.spinner("Sourcing candidates based on tech stack..."):
|
251 |
+
matching_candidates = get_matching_candidates(job_row["Tech Stack"], candidates_df)
|
252 |
+
|
253 |
+
if not matching_candidates:
|
254 |
+
st.warning("No candidates with matching tech stack found for this job.")
|
255 |
+
return []
|
256 |
+
|
257 |
+
st.success(f"Found {len(matching_candidates)} candidates with matching tech stack. Evaluating with LLM...")
|
258 |
+
|
259 |
+
candidates_progress = st.progress(0)
|
260 |
+
candidate_status = st.empty() # For live updates
|
261 |
+
|
262 |
+
for i, candidate_data in enumerate(matching_candidates):
|
263 |
+
# *** MODIFICATION: Check for stop flag ***
|
264 |
+
if st.session_state.get('stop_processing_flag', False):
|
265 |
+
candidate_status.warning("Processing stopped by user.")
|
266 |
+
time.sleep(1) # Allow message to be seen
|
267 |
+
break
|
268 |
+
|
269 |
+
candidate_status.text(f"Evaluating candidate {i+1}/{len(matching_candidates)}: {candidate_data.get('Name', 'Unknown')}")
|
270 |
+
response = call_llm(candidate_data, job_data, llm_chain)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
271 |
|
272 |
+
response_dict = {
|
273 |
+
"Name": response["candidate_name"], "LinkedIn": response["candidate_url"],
|
274 |
+
"summary": response["candidate_summary"], "Location": response["candidate_location"],
|
275 |
+
"Fit Score": float(f"{response['fit_score']:.3f}"), "justification": response["justification"],
|
276 |
+
"Educational Background": candidate_data.get("Degree & Education", ""),
|
277 |
+
"Years of Experience": candidate_data.get("Years of Experience", ""),
|
278 |
+
"Current Title & Company": candidate_data.get("Current Title & Company", "")
|
279 |
+
}
|
280 |
|
281 |
+
# *** MODIFICATION: Live output of candidate dicts - will disappear on rerun after processing ***
|
282 |
+
if response["fit_score"] >= 8.800:
|
283 |
+
selected_candidates.append(response_dict)
|
284 |
+
# This st.markdown will be visible during processing and cleared on the next full script rerun
|
285 |
+
# after this processing block finishes or is stopped.
|
286 |
+
st.markdown(
|
287 |
+
f"**Selected Candidate:** [{response_dict['Name']}]({response_dict['LinkedIn']}) "
|
288 |
+
f"(Score: {response_dict['Fit Score']:.3f}, Location: {response_dict['Location']})"
|
289 |
+
)
|
290 |
+
else:
|
291 |
+
# This st.write will also be visible during processing and cleared later.
|
292 |
+
st.write(f"Rejected candidate: {response_dict['Name']} with score: {response_dict['Fit Score']:.3f}, Location: {response_dict['Location']})")
|
293 |
+
candidates_progress.progress((i + 1) / len(matching_candidates))
|
294 |
+
|
295 |
+
candidates_progress.empty()
|
296 |
+
candidate_status.empty()
|
297 |
+
|
298 |
+
if not st.session_state.get('stop_processing_flag', False): # Only show if not stopped
|
299 |
if selected_candidates:
|
300 |
+
st.success(f"β
LLM evaluation complete. Found {len(selected_candidates)} suitable candidates for this job!")
|
301 |
else:
|
302 |
+
st.info("LLM evaluation complete. No candidates met the minimum fit score threshold for this job.")
|
303 |
+
|
304 |
+
return selected_candidates
|
305 |
+
|
|
|
|
|
|
|
306 |
|
307 |
def main():
|
308 |
st.title("π¨βπ» Candidate Matching App")
|
309 |
+
if 'processed_jobs' not in st.session_state: st.session_state.processed_jobs = {} # May not be used with new logic
|
310 |
+
if 'Selected_Candidates' not in st.session_state: st.session_state.Selected_Candidates = {}
|
311 |
+
if 'llm_chain' not in st.session_state: st.session_state.llm_chain = None # Initialize to None
|
312 |
+
# *** MODIFICATION: Initialize stop flag ***
|
313 |
+
if 'stop_processing_flag' not in st.session_state: st.session_state.stop_processing_flag = False
|
314 |
+
|
315 |
+
|
316 |
+
st.write("This app matches job listings with candidate profiles...")
|
317 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
with st.sidebar:
|
319 |
st.header("API Configuration")
|
320 |
+
api_key = st.text_input("Enter OpenAI API Key", type="password", key="api_key_input")
|
321 |
if api_key:
|
322 |
os.environ["OPENAI_API_KEY"] = api_key
|
323 |
+
# Initialize LLM chain once API key is set
|
324 |
+
if st.session_state.llm_chain is None:
|
325 |
+
with st.spinner("Setting up LLM..."):
|
326 |
+
st.session_state.llm_chain = setup_llm()
|
327 |
+
st.success("API Key set")
|
328 |
else:
|
329 |
st.warning("Please enter OpenAI API Key to use LLM features")
|
330 |
+
st.session_state.llm_chain = None # Clear chain if key removed
|
331 |
|
332 |
+
|
333 |
+
# ... (rest of your gspread setup) ...
|
334 |
+
try:
|
335 |
+
SERVICE_ACCOUNT_FILE = 'src/synapse-recruitment-e94255ca76fd.json' # Ensure this path is correct
|
336 |
+
SCOPES = ['https://www.googleapis.com/auth/spreadsheets']
|
337 |
+
creds = service_account.Credentials.from_service_account_file(SERVICE_ACCOUNT_FILE, scopes=SCOPES)
|
338 |
+
gc = gspread.authorize(creds)
|
339 |
+
job_sheet = gc.open_by_key('1BZlvbtFyiQ9Pgr_lpepDJua1ZeVEqrCLjssNd6OiG9k')
|
340 |
+
candidates_sheet = gc.open_by_key('1u_9o5f0MPHFUSScjEcnA8Lojm4Y9m9LuWhvjYm6ytF4')
|
341 |
+
except Exception as e:
|
342 |
+
st.error(f"Failed to connect to Google Sheets. Ensure '{SERVICE_ACCOUNT_FILE}' is valid and has permissions. Error: {e}")
|
343 |
+
st.stop()
|
344 |
+
|
345 |
+
|
346 |
+
if not os.environ.get("OPENAI_API_KEY"):
|
347 |
st.warning("β οΈ You need to provide an OpenAI API key in the sidebar to use this app.")
|
348 |
+
st.stop()
|
349 |
+
if st.session_state.llm_chain is None and os.environ.get("OPENAI_API_KEY"):
|
350 |
+
with st.spinner("Setting up LLM..."):
|
351 |
+
st.session_state.llm_chain = setup_llm()
|
352 |
+
st.rerun() # Rerun to ensure LLM is ready for the main display logic
|
353 |
|
354 |
+
try:
|
355 |
+
job_worksheet = job_sheet.worksheet('paraform_jobs_formatted')
|
356 |
+
job_data = job_worksheet.get_all_values()
|
357 |
+
candidate_worksheet = candidates_sheet.worksheet('transformed_candidates_updated')
|
358 |
+
candidate_data = candidate_worksheet.get_all_values()
|
359 |
+
|
360 |
+
jobs_df = pd.DataFrame(job_data[1:], columns=job_data[0]).drop(["Link"], axis=1, errors='ignore')
|
361 |
+
jobs_df1 = jobs_df[["Company","Role","One liner","Locations","Tech Stack","Workplace","Industry","YOE"]]
|
362 |
+
candidates_df = pd.DataFrame(candidate_data[1:], columns=candidate_data[0]).fillna("Unknown")
|
363 |
+
candidates_df.drop_duplicates(subset=['LinkedIn URL'], keep='first', inplace=True)
|
364 |
+
|
365 |
+
with st.expander("Preview uploaded data"):
|
366 |
+
st.subheader("Jobs Data Preview"); st.dataframe(jobs_df1.head(3))
|
367 |
+
# st.subheader("Candidates Data Preview"); st.dataframe(candidates_df.head(3))
|
368 |
+
|
369 |
+
# Column mapping (simplified, ensure your CSVs have these exact names or adjust)
|
370 |
+
# candidates_df = candidates_df.rename(columns={...}) # Add if needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
371 |
|
372 |
+
display_job_selection(jobs_df, candidates_df, job_sheet) # job_sheet is 'sh'
|
|
|
|
|
373 |
|
374 |
+
except Exception as e:
|
375 |
+
st.error(f"Error processing files or data: {e}")
|
|
|
376 |
st.divider()
|
377 |
|
378 |
+
def display_job_selection(jobs_df, candidates_df, sh): # 'sh' is the Google Sheets client
|
379 |
+
st.subheader("Select a job to Source for potential matches")
|
380 |
+
job_options = [f"{row['Role']} at {row['Company']}" for _, row in jobs_df.iterrows()]
|
381 |
+
|
382 |
+
if not job_options:
|
383 |
+
st.warning("No jobs found to display.")
|
384 |
+
return
|
385 |
|
386 |
+
selected_job_index = st.selectbox("Jobs:", range(len(job_options)), format_func=lambda x: job_options[x], key="job_selectbox")
|
|
|
|
|
|
|
387 |
|
388 |
+
job_row = jobs_df.iloc[selected_job_index]
|
389 |
+
job_row_stack = parse_tech_stack(job_row["Tech Stack"]) # Assuming parse_tech_stack is defined
|
390 |
|
391 |
+
col_job_details_display, _ = st.columns([2,1])
|
392 |
+
with col_job_details_display:
|
393 |
+
st.subheader(f"Job Details: {job_row['Role']}")
|
394 |
+
job_details_dict = {
|
395 |
+
"Company": job_row["Company"], "Role": job_row["Role"], "Description": job_row.get("One liner", "N/A"),
|
396 |
+
"Locations": job_row.get("Locations", "N/A"), "Industry": job_row.get("Industry", "N/A"),
|
397 |
+
"Tech Stack": display_tech_stack(job_row_stack) # Assuming display_tech_stack is defined
|
398 |
+
}
|
399 |
+
for key, value in job_details_dict.items(): st.markdown(f"**{key}:** {value}")
|
400 |
+
|
401 |
+
# State keys for the selected job
|
402 |
+
job_processed_key = f"job_{selected_job_index}_processed_successfully"
|
403 |
+
job_is_processing_key = f"job_{selected_job_index}_is_currently_processing"
|
404 |
+
|
405 |
+
# Initialize states if they don't exist for this job
|
406 |
+
if job_processed_key not in st.session_state: st.session_state[job_processed_key] = False
|
407 |
+
if job_is_processing_key not in st.session_state: st.session_state[job_is_processing_key] = False
|
408 |
|
409 |
+
sheet_name = f"{job_row['Role']} at {job_row['Company']}".strip()[:100]
|
410 |
+
worksheet_exists = False
|
411 |
+
existing_candidates_from_sheet = [] # This will store raw data from sheet
|
412 |
+
try:
|
413 |
+
cand_worksheet = sh.worksheet(sheet_name)
|
414 |
+
worksheet_exists = True
|
415 |
+
existing_data = cand_worksheet.get_all_values() # Get all values as list of lists
|
416 |
+
if len(existing_data) > 1: # Has data beyond header
|
417 |
+
existing_candidates_from_sheet = existing_data # Store raw data
|
418 |
+
except gspread.exceptions.WorksheetNotFound:
|
419 |
+
pass
|
420 |
+
|
421 |
+
# --- Processing Control Area ---
|
422 |
+
# Show controls if not successfully processed in this session OR if sheet exists (allow re-process/overwrite)
|
423 |
+
if not st.session_state.get(job_processed_key, False) or existing_candidates_from_sheet:
|
424 |
|
425 |
+
if existing_candidates_from_sheet and not st.session_state.get(job_is_processing_key, False) and not st.session_state.get(job_processed_key, False):
|
426 |
+
st.info(f"Processing ('{sheet_name}')")
|
427 |
+
|
428 |
+
col_find, col_stop = st.columns(2)
|
429 |
+
with col_find:
|
430 |
+
if st.button(f"Find Matching Candidates for this Job", key=f"find_btn_{selected_job_index}", disabled=st.session_state.get(job_is_processing_key, False)):
|
431 |
+
if not os.environ.get("OPENAI_API_KEY") or st.session_state.llm_chain is None: # Assuming llm_chain is in session_state
|
432 |
+
st.error("OpenAI API key not set or LLM not initialized. Please check sidebar.")
|
433 |
+
else:
|
434 |
+
st.session_state[job_is_processing_key] = True
|
435 |
+
st.session_state.stop_processing_flag = False # Reset for new run, assuming stop_processing_flag is used
|
436 |
+
st.session_state.Selected_Candidates[selected_job_index] = [] # Clear previous run for this job
|
437 |
+
st.session_state[job_processed_key] = False # Mark as not successfully processed yet for this attempt
|
438 |
+
st.rerun()
|
439 |
|
440 |
+
with col_stop:
|
441 |
+
if st.session_state.get(job_is_processing_key, False): # Show STOP only if "Find" was clicked and currently processing
|
442 |
+
if st.button("STOP Processing", key=f"stop_btn_{selected_job_index}"):
|
443 |
+
st.session_state.stop_processing_flag = True # Assuming stop_processing_flag is used
|
444 |
+
st.warning("Stop request sent. Processing will halt shortly.")
|
445 |
+
|
446 |
+
# --- Actual Processing Logic ---
|
447 |
+
if st.session_state.get(job_is_processing_key, False):
|
448 |
+
with st.spinner(f"Sourcing candidates for {job_row['Role']} at {job_row['Company']}..."):
|
449 |
+
# Assuming process_candidates_for_job is defined and handles stop_processing_flag
|
450 |
+
processed_candidates_list = process_candidates_for_job(
|
451 |
+
job_row, candidates_df, st.session_state.llm_chain # Assuming llm_chain from session_state
|
452 |
+
)
|
453 |
|
454 |
+
st.session_state[job_is_processing_key] = False # Mark as no longer actively processing
|
455 |
+
|
456 |
+
if not st.session_state.get('stop_processing_flag', False): # If processing was NOT stopped
|
457 |
+
if processed_candidates_list:
|
458 |
+
# Ensure Fit Score is float for reliable sorting
|
459 |
+
for cand in processed_candidates_list:
|
460 |
+
if 'Fit Score' in cand and isinstance(cand['Fit Score'], str):
|
461 |
+
try: cand['Fit Score'] = float(cand['Fit Score'])
|
462 |
+
except ValueError: cand['Fit Score'] = 0.0 # Default if conversion fails
|
463 |
+
elif 'Fit Score' not in cand:
|
464 |
+
cand['Fit Score'] = 0.0
|
465 |
+
|
466 |
+
processed_candidates_list.sort(key=lambda x: x.get("Fit Score", 0.0), reverse=True)
|
467 |
+
st.session_state.Selected_Candidates[selected_job_index] = processed_candidates_list
|
468 |
+
st.session_state[job_processed_key] = True # Mark as successfully processed
|
469 |
+
|
470 |
+
# Save to Google Sheet
|
471 |
+
try:
|
472 |
+
target_worksheet = None
|
473 |
+
if not worksheet_exists:
|
474 |
+
target_worksheet = sh.add_worksheet(title=sheet_name, rows=max(100, len(processed_candidates_list) + 10), cols=20)
|
475 |
+
else:
|
476 |
+
target_worksheet = sh.worksheet(sheet_name)
|
477 |
+
|
478 |
+
headers = list(processed_candidates_list[0].keys())
|
479 |
+
# Ensure all values are converted to strings for gspread
|
480 |
+
rows_to_write = [headers] + [[str(candidate.get(h, "")) for h in headers] for candidate in processed_candidates_list]
|
481 |
+
target_worksheet.clear()
|
482 |
+
target_worksheet.update('A1', rows_to_write)
|
483 |
+
st.success(f"Results saved to Google Sheet: '{sheet_name}'")
|
484 |
+
except Exception as e:
|
485 |
+
st.error(f"Error writing to Google Sheet '{sheet_name}': {e}")
|
486 |
+
else:
|
487 |
+
st.info("No suitable candidates found after processing.")
|
488 |
+
st.session_state.Selected_Candidates[selected_job_index] = []
|
489 |
+
st.session_state[job_processed_key] = True # Mark as processed, even if no results
|
490 |
+
else: # If processing WAS stopped
|
491 |
+
st.info("Processing was stopped by user. Results (if any) were not saved. You can try processing again.")
|
492 |
+
st.session_state.Selected_Candidates[selected_job_index] = [] # Clear any partial results
|
493 |
+
st.session_state[job_processed_key] = False # Not successfully processed
|
494 |
|
495 |
+
st.session_state.pop('stop_processing_flag', None) # Clean up flag
|
496 |
+
st.rerun() # Rerun to update UI based on new state
|
497 |
+
|
498 |
+
# --- Display Results Area ---
|
499 |
+
should_display_results_area = False
|
500 |
+
final_candidates_to_display = [] # Initialize to ensure it's always defined
|
501 |
+
|
502 |
+
if st.session_state.get(job_is_processing_key, False):
|
503 |
+
should_display_results_area = False # Not if actively processing
|
504 |
+
elif st.session_state.get(job_processed_key, False): # If successfully processed in this session
|
505 |
+
should_display_results_area = True
|
506 |
+
final_candidates_to_display = st.session_state.Selected_Candidates.get(selected_job_index, [])
|
507 |
+
elif existing_candidates_from_sheet: # If not processed in this session, but sheet has data
|
508 |
+
should_display_results_area = True
|
509 |
+
headers = existing_candidates_from_sheet[0]
|
510 |
+
parsed_sheet_candidates = []
|
511 |
+
for row_idx, row_data in enumerate(existing_candidates_from_sheet[1:]): # Skip header row
|
512 |
+
candidate_dict = {}
|
513 |
+
for col_idx, header_name in enumerate(headers):
|
514 |
+
candidate_dict[header_name] = row_data[col_idx] if col_idx < len(row_data) else None
|
515 |
|
516 |
+
# Convert Fit Score from string to float for consistent handling
|
517 |
+
if 'Fit Score' in candidate_dict and isinstance(candidate_dict['Fit Score'], str):
|
518 |
+
try:
|
519 |
+
candidate_dict['Fit Score'] = float(candidate_dict['Fit Score'])
|
520 |
+
except ValueError:
|
521 |
+
st.warning(f"Could not convert Fit Score '{candidate_dict['Fit Score']}' to float for candidate in sheet row {row_idx+2}.")
|
522 |
+
candidate_dict['Fit Score'] = 0.0 # Default if conversion fails
|
523 |
+
elif 'Fit Score' not in candidate_dict:
|
524 |
+
candidate_dict['Fit Score'] = 0.0
|
525 |
+
|
526 |
+
|
527 |
+
parsed_sheet_candidates.append(candidate_dict)
|
528 |
+
final_candidates_to_display = sorted(parsed_sheet_candidates, key=lambda x: x.get("Fit Score", 0.0), reverse=True)
|
529 |
+
if not st.session_state.get(job_processed_key, False): # Inform if loading from sheet and not explicitly processed
|
530 |
+
st.info(f"Displaying: '{sheet_name}'.")
|
531 |
+
|
532 |
+
if should_display_results_area:
|
533 |
+
st.subheader("Selected Candidates")
|
534 |
|
535 |
+
# Display token usage if it was just processed (job_processed_key is True and tokens exist)
|
536 |
+
if st.session_state.get(job_processed_key, False) and \
|
537 |
+
(st.session_state.get('total_input_tokens', 0) > 0 or st.session_state.get('total_output_tokens', 0) > 0):
|
538 |
+
display_token_usage() # Assuming display_token_usage is defined
|
539 |
+
|
540 |
+
if final_candidates_to_display:
|
541 |
+
for i, candidate in enumerate(final_candidates_to_display):
|
542 |
+
score_display = candidate.get('Fit Score', 'N/A')
|
543 |
+
if isinstance(score_display, (float, int)):
|
544 |
+
score_display = f"{score_display:.3f}"
|
545 |
+
# If score_display is still a string (e.g. 'N/A' or failed float conversion), it will be displayed as is.
|
546 |
+
|
547 |
+
expander_title = f"{i+1}. {candidate.get('Name', 'N/A')} (Score: {score_display})"
|
548 |
+
|
549 |
+
with st.expander(expander_title):
|
550 |
+
text_to_copy = f"""Candidate: {candidate.get('Name', 'N/A')} (Score: {score_display})
|
551 |
+
Summary: {candidate.get('summary', 'N/A')}
|
552 |
+
Current: {candidate.get('Current Title & Company', 'N/A')}
|
553 |
+
Education: {candidate.get('Educational Background', 'N/A')}
|
554 |
+
Experience: {candidate.get('Years of Experience', 'N/A')}
|
555 |
+
Location: {candidate.get('Location', 'N/A')}
|
556 |
+
LinkedIn: {candidate.get('LinkedIn', 'N/A')}
|
557 |
+
Justification: {candidate.get('justification', 'N/A')}
|
558 |
+
"""
|
559 |
+
js_text_to_copy = json.dumps(text_to_copy)
|
560 |
+
button_unique_id = f"copy_btn_job{selected_job_index}_cand{i}"
|
561 |
+
|
562 |
+
copy_button_html = f"""
|
563 |
+
<script>
|
564 |
+
function copyToClipboard_{button_unique_id}() {{
|
565 |
+
const textToCopy = {js_text_to_copy};
|
566 |
+
navigator.clipboard.writeText(textToCopy).then(function() {{
|
567 |
+
const btn = document.getElementById('{button_unique_id}');
|
568 |
+
if (btn) {{ // Check if button exists
|
569 |
+
const originalText = btn.innerText;
|
570 |
+
btn.innerText = 'Copied!';
|
571 |
+
setTimeout(function() {{ btn.innerText = originalText; }}, 1500);
|
572 |
+
}}
|
573 |
+
}}, function(err) {{
|
574 |
+
console.error('Could not copy text: ', err);
|
575 |
+
alert('Failed to copy text. Please use Ctrl+C or your browser\\'s copy function.');
|
576 |
+
}});
|
577 |
+
}}
|
578 |
+
</script>
|
579 |
+
<button id="{button_unique_id}" onclick="copyToClipboard_{button_unique_id}()">π Copy Details</button>
|
580 |
+
"""
|
581 |
|
582 |
+
expander_cols = st.columns([0.82, 0.18])
|
583 |
+
with expander_cols[1]:
|
584 |
+
st.components.v1.html(copy_button_html, height=40)
|
|
|
|
|
585 |
|
586 |
+
with expander_cols[0]:
|
587 |
+
st.markdown(f"**Summary:** {candidate.get('summary', 'N/A')}")
|
588 |
+
st.markdown(f"**Current:** {candidate.get('Current Title & Company', 'N/A')}")
|
589 |
+
st.markdown(f"**Education:** {candidate.get('Educational Background', 'N/A')}")
|
590 |
+
st.markdown(f"**Experience:** {candidate.get('Years of Experience', 'N/A')}")
|
591 |
+
st.markdown(f"**Location:** {candidate.get('Location', 'N/A')}")
|
592 |
+
if 'LinkedIn' in candidate and candidate.get('LinkedIn'):
|
593 |
+
st.markdown(f"**[LinkedIn Profile]({candidate['LinkedIn']})**")
|
594 |
+
else:
|
595 |
+
st.markdown("**LinkedIn Profile:** N/A")
|
596 |
|
597 |
+
if 'justification' in candidate and candidate.get('justification'):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
598 |
st.markdown("**Justification:**")
|
599 |
st.info(candidate['justification'])
|
600 |
+
|
601 |
+
elif st.session_state.get(job_processed_key, False): # Processed but no candidates
|
602 |
+
st.info("No candidates met the criteria for this job after processing.")
|
603 |
+
|
604 |
+
# This "Reset" button is now governed by should_display_results_area
|
605 |
+
if st.button("Reset and Process Again", key=f"reset_btn_{selected_job_index}"):
|
606 |
+
st.session_state[job_processed_key] = False
|
607 |
+
st.session_state.pop(job_is_processing_key, None)
|
608 |
+
if selected_job_index in st.session_state.Selected_Candidates:
|
609 |
+
del st.session_state.Selected_Candidates[selected_job_index]
|
610 |
+
try:
|
611 |
+
sh.worksheet(sheet_name).clear()
|
612 |
+
st.info(f"Cleared Google Sheet '{sheet_name}' as part of reset.")
|
613 |
+
except: pass # Ignore if sheet not found or error
|
614 |
+
st.rerun()
|
615 |
|
616 |
if __name__ == "__main__":
|
617 |
+
main()
|