jobfixers add matching score + css template)

app.py

@@ -1,5 +1,7 @@
 import json
 import os
+from concurrent.futures import ThreadPoolExecutor
+
 import gradio as gr
 import requests
 from langchain.chat_models import ChatOpenAI
@@ -17,7 +19,9 @@ def search(resume):
         "Content-Type": "application/json",
         "x-api-key": os.environ["API_KEY"],
     }  # pas headers indien nodig aan
-    response = requests.post(url, headers=headers, data=json.dumps({"text": resume, "limit":3}))
+    response = requests.post(
+        url, headers=headers, data=json.dumps({"text": resume, "limit": 7})
+    )
     response_data = response.json()
 
     if "prediction" in response_data:
@@ -27,46 +31,32 @@ def search(resume):
             html_table = "<table>"
 
             # Add table headers
-            html_table += "<tr><th>Vacancy</th><th>Score</th><th>Skills Match</th><th>Skills Missing</th></tr>"
-
-            for i, vacancy in enumerate(prediction):
-                (
-                    score,
-                    skills_intersection,
-                    skills_not_in_intersection,
-                ) = get_skills_score(vacancy=vacancy, resume=resume)
-                # Voeg een nieuwe regel toe na elke '.' en voeg "Vacature <volgnummer>:\n" toe voor elk item
-                updated_item = f"VACATURE {i + 1}: {vacancy}"
-                html_table += f"<tr><td>{updated_item}</td><td>{score}</td><td>{skills_intersection}</td><td>{skills_not_in_intersection}</td></tr>"
-            html_table += "</table>"
-            return html_table
+            html_table += "<tr><th>Vacancy</th><th>Score</th><th>Skills Match</th></tr>"
 
-    return "niets teruggevonden ..."
+            # Prepare a list to hold the futures
+            futures = []
 
+            # Create a ThreadPoolExecutor
+            with ThreadPoolExecutor() as executor:
+                for i, vacancy in enumerate(prediction):
+                    # Schedule the get_skills_match function to run and store the future
+                    future = executor.submit(
+                        skills.get_skills_match, llm, vacancy, resume
+                    )
+                    futures.append((i, vacancy, future))
 
-def get_skills_score(vacancy, resume):
-    chain = skills.get_skills_chain(llm=llm)
-    result = chain({"vacancy": vacancy, "resume": resume})
-
-    vacancy_skills_predicted = utils.get_json_list_from_result(
-        result, "vacancy_skills_predicted"
-    )
-    resume_skills_predicted = utils.get_json_list_from_result(
-        result, "resume_skills_predicted"
-    )
-
-    skills_intersection = utils.get_intersection(
-        vacancy_skills_predicted, resume_skills_predicted
-    )
-    skills_not_in_intersection = utils.not_in_intersection(
-        vacancy_skills_predicted, resume_skills_predicted
-    )
-    match_score = utils.match(
-        present_features=skills_intersection,
-        not_present_features=skills_not_in_intersection,
-    )
-    return match_score, skills_intersection, skills_not_in_intersection
+                # Collect the results as they become available
+                for i, vacancy, future in futures:
+                    skills_match = future.result()
+                    skills_match_predicted = utils.get_json_list_from_result(
+                        skills_match, "skills_match_predicted"
+                    )
+                    updated_item = f"VACATURE {i + 1}: {vacancy}"
+                    html_table += f"<tr><td>{updated_item}</td><td>{len(skills_match_predicted)}</td><td>{skills_match_predicted}</td></tr>"
+            html_table += "</table>"
+            return html_table
 
+    return "niets teruggevonden ..."
 
 examples = [
     """
@@ -116,7 +106,7 @@ examples = [
     """
 ]
 
-demo = gr.Blocks()
+demo = gr.Blocks(theme=gr.themes.Soft())
 
 with demo:
     with gr.Group():

recruiting_assistant.py

@@ -1,8 +1,9 @@
 import json
 import os
+
+from langchain.chains import LLMChain, SequentialChain
 from langchain.chat_models import ChatOpenAI
 from langchain.prompts import ChatPromptTemplate
-from langchain.chains import LLMChain, SequentialChain
 
 llm = ChatOpenAI(temperature=0.0, openai_api_key=os.environ["OPENAI"])
 

scripts/scrape_website.py

@@ -1,21 +1,20 @@
+import json
 import os
+import time
+from urllib.parse import urlparse
+
 import openai
 import pandas as pd
-import json
+from bs4 import BeautifulSoup
 from selenium import webdriver
-from selenium.webdriver.chrome.service import Service
-from webdriver_manager.chrome import ChromeDriverManager
-from selenium.webdriver.common.by import By
 from selenium.common.exceptions import (
-    NoSuchElementException,
-    TimeoutException,
     WebDriverException,
 )
-from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
-from bs4 import BeautifulSoup
-from urllib.parse import urlparse
-import time
+from selenium.webdriver.support.ui import WebDriverWait
+from webdriver_manager.chrome import ChromeDriverManager
 
 # Set up OpenAI API
 openai.api_key = os.getenv("OPENAI")

skills.py

@@ -5,7 +5,8 @@ from langchain.prompts import ChatPromptTemplate
 
 def get_vacancy_skills_chain(llm) -> LLMChain:
     template_vacancy_get_skills = """
-    Given the following vacancy delimited by three backticks, retrieve the skills that are requested.
+    Given the following vacancy delimited by three backticks, retrieve the skills requested in the vacancy.
+    Describe the skills in preferably 1 word and maximum 3 words.
     Return the skills as a JSON list on 1 line, do not add newlines or any other text.
 
     ```
@@ -24,7 +25,8 @@ def get_vacancy_skills_chain(llm) -> LLMChain:
 
 def get_resume_skills_chain(llm) -> LLMChain:
     template_resume_skills = """
-    Given the following resume delimited by three backticks, retrieve the skills this data scientist possesses.
+    Given the following resume delimited by three backticks, retrieve the skills from the resume.
+    Describe the skills in preferably 1 word and maximum 3 words.
     Return the skills as a JSON list on 1 line, do not add newlines or any other text.
 
     ```
@@ -95,3 +97,41 @@ def get_skills_chain(llm) -> SequentialChain:
         ],
         verbose=False,
     )
+
+
+def get_skills_match(llm, vacancy, resume) -> SequentialChain:
+
+    template_get_skills_intersection = """
+
+      ```
+      {vacancy}
+      ```
+
+      Can you list the matches between the vacancy above delimited by three backticks with the resume below delimited by three backticks. 
+      Consider skills that are not exact but are close to each other in terms of meaning or usage, or that are related or in the neighbourhood.
+      If no skills match do not make up a response and return an empty list.
+      Return the matches as a JSON list on 1 line, do not add newlines or any other text.
+
+      ```
+      {resume}
+      ```
+      """
+
+    prompt_get_skills_intersection = ChatPromptTemplate.from_template(
+        template=template_get_skills_intersection
+    )
+    skills_match_chain = LLMChain(
+        llm=llm,
+        prompt=prompt_get_skills_intersection,
+        output_key="skills_match_predicted",
+    )
+
+    chain = SequentialChain(
+        chains=[skills_match_chain],
+        input_variables=["vacancy", "resume"],
+        output_variables=[
+            skills_match_chain.output_key,
+        ],
+        verbose=False,
+    )
+    return chain({"vacancy": vacancy, "resume": resume})