Update utils/utils.py

utils/utils.py

@@ -0,0 +1,97 @@
+from PyPDF2 import PdfReader
+from agents.agents import get_agent_groq
+import json
+import re
+
+
+def parse_resume(path):
+    loader = PdfReader(path)
+    text=''
+    print(len(loader.pages))
+    for i in range(len(loader.pages)):
+       text+= loader.pages[i].extract_text()
+    return text
+def parse_resumes(resumes_list):
+    resumes_text=[]
+    for resume in resumes_list:
+      loader = PdfReader(resume)
+      text=''
+      #print(len(loader.pages))
+      for i in range(len(loader.pages)):
+        text+= loader.pages[i].extract_text()
+      resumes_text.append(text)
+    return resumes_text
+
+
+def generate_analysis(resume_text, job_listing_text,job_title_text, must_have,prompt_template):
+    agent = get_agent_groq()
+    resp = agent.invoke(prompt_template.format(resume=resume_text, job_listing=job_listing_text,job_title_text=job_title_text,must_have=must_have))
+    text_res=extract(resp.content)
+    #text_res=extract(text_res)
+    #chain = prompt | agent
+    print(text_res)
+    #text = resp.content
+    return text_res
+
+def generate_sel_analysis(resume_text, job_listing_text,job_title_text, must_have,prompt_template):
+      #chain = prompt | agent
+    agent = get_agent_groq()
+    response = agent.invoke(prompt_template.format(resume=resume_text, job_listing=job_listing_text,job_title_text=job_title_text,must_have=must_have))
+    print(response.content)
+    text_res=extract_sel(response.content)
+    print(text_res)
+    return text_res
+
+def extract(content):
+    
+    json_pattern = r'```\n(.*?)\n```'
+    json_string = re.search(json_pattern, content, re.DOTALL).group(1)
+
+    # Load the extracted JSON string into a dictionary
+    data = json.loads(json_string)
+    new={}
+    # Print the extracted variables and their values
+    for key, value in data.items():
+        print(f"{key}: {value}")
+        new[key]=value
+    return new
+def extract_mist(json_string):
+       # Load the extracted JSON string into a dictionary
+    data = json.loads(json_string)
+    new={}
+    # Print the extracted variables and their values
+    for key, value in data.items():
+        print(f"{key}: {value}")
+        new[key]=value
+    return new
+
+
+def extract_sel(content):
+    try:
+        # Split the content by identifying each candidate section using the candidate names (bolded)
+        candidates = re.split(r'\*\*(.*?)\*\*', content)  # Split on the pattern of bolded names
+        
+        # The split result will have alternating candidate names and JSON sections
+        candidate_json_list = []
+        
+        for i in range(1, len(candidates), 2):  # Iterate over candidate name and their JSON parts
+            candidate_name = candidates[i].strip()  # Candidate name
+            json_string = candidates[i+1].strip()   # JSON string part
+            
+            # Load the JSON string into a dictionary
+            candidate_data = json.loads(json_string)
+            candidate_json_list.append(candidate_data)
+        
+        return candidate_json_list
+    
+    except json.JSONDecodeError as e:
+        print(f"Error decoding JSON: {e}")
+        return []
+
+def generate_adv(job_listing_text,job_title_text, prompt_template):
+   # if model_selection=="Groq":
+    agent = get_agent_groq()
+    resp = agent.invoke(prompt_template.format(job_listing=job_listing_text,job_title_text=job_title_text))
+    text = resp.content
+    print(text)
+    return text