Upload 9 files

backend/agents/matcher.py

@@ -0,0 +1,18 @@
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+from groq import Groq
+
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+
+def get_embedding(text: str):
+    response = client.embeddings.create(
+        model="nomic-embed-text",  # Groq embedding model
+        input=text
+    )
+    return np.array(response.data[0].embedding)
+
+def compute_match(resume_text: str, job_desc: str) -> float:
+    resume_emb = get_embedding(resume_text).reshape(1, -1)
+    job_emb = get_embedding(job_desc).reshape(1, -1)
+    score = cosine_similarity(resume_emb, job_emb)[0][0]
+    return round(float(score), 3)

backend/agents/normalizer.py

@@ -0,0 +1,13 @@
+from typing import List, Dict
+
+def normalize_job(raw: Dict, source: str) -> Dict:
+    return {
+        "id": str(raw.get("id", "")),
+        "source": source,
+        "title": raw.get("title") or raw.get("position", ""),
+        "company": raw.get("company", ""),
+        "description": raw.get("description", ""),
+        "skills": raw.get("skills") or raw.get("tags", []),
+        "url": raw.get("url", ""),
+        "date": raw.get("date", ""),
+    }

backend/agents/rapidapi_freelancer.py

@@ -0,0 +1,28 @@
+import os
+import requests
+from .normalizer import normalize_job
+
+RAPIDAPI_KEY = os.getenv("RAPIDAPI_KEY")
+
+def fetch_freelancer_jobs(query="AI", limit=5):
+    url = "https://freelancer-com.p.rapidapi.com/projects/search"   # Example endpoint
+    headers = {
+        "X-RapidAPI-Key": RAPIDAPI_KEY,
+        "X-RapidAPI-Host": "freelancer-com.p.rapidapi.com"
+    }
+    params = {"q": query, "limit": limit}
+    response = requests.get(url, headers=headers, params=params)
+    jobs = response.json().get("projects", [])
+
+    normalized = []
+    for job in jobs[:limit]:
+        normalized.append(normalize_job({
+            "id": job.get("id"),
+            "title": job.get("title"),
+            "company": "Freelancer Client",
+            "description": job.get("description"),
+            "skills": [s["name"] for s in job.get("jobs", [])],
+            "url": f"https://www.freelancer.com/projects/{job.get('seo_url')}",
+            "date": job.get("submitdate")
+        }, "Freelancer"))
+    return normalized

backend/agents/rapidapi_linkedin.py

@@ -0,0 +1,28 @@
+import os
+import requests
+from .normalizer import normalize_job
+
+RAPIDAPI_KEY = os.getenv("RAPIDAPI_KEY")
+
+def fetch_linkedin_jobs(query="software engineer", limit=5):
+    url = "https://linkedin-jobs-search.p.rapidapi.com/"   # Example endpoint
+    headers = {
+        "X-RapidAPI-Key": RAPIDAPI_KEY,
+        "X-RapidAPI-Host": "linkedin-jobs-search.p.rapidapi.com"
+    }
+    payload = {"search_terms": query, "location": "remote", "page": "1"}
+    response = requests.post(url, headers=headers, json=payload)
+    jobs = response.json()
+
+    normalized = []
+    for job in jobs[:limit]:
+        normalized.append(normalize_job({
+            "id": job.get("job_id"),
+            "title": job.get("job_title"),
+            "company": job.get("company_name"),
+            "description": job.get("job_description"),
+            "skills": job.get("job_skills", []),
+            "url": job.get("linkedin_url"),
+            "date": job.get("posted_date")
+        }, "LinkedIn"))
+    return normalized

backend/agents/rapidapi_upwork.py

@@ -0,0 +1,28 @@
+import os
+import requests
+from .normalizer import normalize_job
+
+RAPIDAPI_KEY = os.getenv("RAPIDAPI_KEY")
+
+def fetch_upwork_jobs(query="python developer", limit=5):
+    url = "https://upwork-api.p.rapidapi.com/search/jobs"   # Example endpoint
+    headers = {
+        "X-RapidAPI-Key": RAPIDAPI_KEY,
+        "X-RapidAPI-Host": "upwork-api.p.rapidapi.com"
+    }
+    params = {"q": query, "page": "1"}
+    response = requests.get(url, headers=headers, params=params)
+    jobs = response.json().get("jobs", [])
+
+    normalized = []
+    for job in jobs[:limit]:
+        normalized.append(normalize_job({
+            "id": job.get("id"),
+            "title": job.get("title"),
+            "company": "Upwork Client",
+            "description": job.get("description"),
+            "skills": job.get("skills", []),
+            "url": f"https://www.upwork.com/jobs/{job.get('id')}",
+            "date": job.get("date_created")
+        }, "Upwork"))
+    return normalized

backend/agents/remoteok_agent.py

@@ -0,0 +1,8 @@
+import requests
+from .normalizer import normalize_job
+
+def fetch_remoteok_jobs(limit=10):
+    url = "https://remoteok.com/api"
+    res = requests.get(url, headers={"User-Agent": "MATCHHIVE"})
+    jobs = res.json()[1:]  # skip metadata
+    return [normalize_job(job, "RemoteOK") for job in jobs[:limit]]

backend/agents/resume_parser.py

@@ -0,0 +1,10 @@
+import pdfplumber, docx, os
+
+def extract_text(file_path: str) -> str:
+    if file_path.endswith(".pdf"):
+        with pdfplumber.open(file_path) as pdf:
+            return " ".join(page.extract_text() or "" for page in pdf.pages)
+    elif file_path.endswith(".docx"):
+        doc = docx.Document(file_path)
+        return " ".join(p.text for p in doc.paragraphs)
+    return ""