gemini updated

backend/services/resume_parser.py

@@ -23,15 +23,16 @@ bnb_config = BitsAndBytesConfig(
     bnb_4bit_quant_type="nf4"
 )
 
-tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")
+# --- UPDATED: Using Deepseek-Coder-V2-Lite-Instruct for better performance ---
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/Deepseek-Coder-V2-Lite-Instruct", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
-    "tiiuae/falcon-7b-instruct",
+    "deepseek-ai/Deepseek-Coder-V2-Lite-Instruct",
     quantization_config=bnb_config,
-    device_map="auto"
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True
 )
 
-
-
 # ===============================
 # Text Extraction (PDF/DOCX)
 # ===============================
@@ -88,75 +89,17 @@ def extract_name(text: str, filename: str) -> str:
 # Janus-Pro Parsing
 # ===============================
 def parse_with_deepseek(text: str) -> dict:
-    """Use DeepSeek Janus-Pro-7B to extract resume details in JSON format."""
+    """Use Deepseek-Coder-V2-Lite-Instruct to extract resume details in JSON format."""
+    # --- UPDATED: Refined prompt for better JSON extraction ---
     prompt = f"""
-    Extract the following information from the resume text below:
-
-    - Full Name
-    - Skills (comma separated)
-    - Education (degrees + institutions)
-    - Experience (job titles + companies)
-
-    Return only valid JSON in the following structure:
-    {{
-      "name": "Full Name",
-      "skills": "Skill1, Skill2, Skill3",
-      "education": "Degree1 - Institution1; Degree2 - Institution2",
-      "experience": "Job1 - Company1; Job2 - Company2"
-    }}
-
-    Resume:
-    {text}
-    """
-
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    outputs = model.generate(**inputs, max_new_tokens=512)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    # Extract JSON safely
-    match = re.search(r"\{.*\}", response, re.S)
-    if match:
-        try:
-            return json.loads(match.group())
-        except:
-            pass
-    return {"name": "", "skills": "", "education": "", "experience": ""}
-
-# ===============================
-# Fallback Heading-based Parsing
-# ===============================
-def fallback_parse(text: str) -> dict:
-    """Simple heading-based parsing as backup."""
-    skills = re.findall(r"Skills\s*[:\-]?\s*(.*)", text, re.I)
-    education = re.findall(r"Education\s*[:\-]?\s*(.*)", text, re.I)
-    experience = re.findall(r"(Experience|Work History)\s*[:\-]?\s*(.*)", text, re.I)
-    return {
-        "skills": ", ".join(skills),
-        "education": ", ".join(education),
-        "experience": ", ".join([exp[1] for exp in experience])
-    }
-
-# ===============================
-# Main Parse Function
-# ===============================
-def parse_resume(file_path: str, filename: str) -> dict:
-    """Main resume parsing function."""
-    text = extract_text(file_path)
-    name = extract_name(text, filename)
-
-    # Try Janus-Pro parsing
-    ents = parse_with_deepseek(text)
+Extract the following information from the resume text provided below. Your response should be a valid JSON object.
 
-    # If Janus-Pro misses fields, use fallback
-    if not ents.get("skills") or not ents.get("education"):
-        fb = fallback_parse(text)
-        ents["skills"] = ents.get("skills") or fb["skills"]
-        ents["education"] = ents.get("education") or fb["education"]
-        ents["experience"] = ents.get("experience") or fb["experience"]
+**Information to extract:**
+- **Full Name:** The candidate's full name.
+- **Email:** The candidate's email address.
+- **Phone:** The candidate's phone number.
+- **Skills:** A list of technical and soft skills.
+- **Education:** A list of academic degrees and institutions.
+- **Experience:** A list of previous jobs, including company, title, and dates.
 
-    return {
-        "name": ents.get("name") or name,
-        "skills": ents.get("skills", ""),
-        "education": ents.get("education", ""),
-        "experience": ents.get("experience", "")
-    }
+**Resume Text:**