Add candidate sourcing live search: src/sourcing.py

src/sourcing.py

@@ -10,13 +10,15 @@ from typing import Optional
 
 from .feature_extractor import LLMClient, _extract_json
 from .prompts.sourcing import XRAY_QUERY_GENERATION_PROMPT
+from .web_search import LinkedInSearcher
 
 
 class CandidateSourcer:
     """Generates Google X-ray search queries to find candidates on LinkedIn."""
 
-    def __init__(self, llm_client: Optional[LLMClient] = None):
+    def __init__(self, llm_client: Optional[LLMClient] = None, searcher: Optional[LinkedInSearcher] = None):
         self.llm = llm_client or LLMClient()
+        self.searcher = searcher or LinkedInSearcher()
 
     def generate_queries(
         self,
@@ -51,3 +53,35 @@ class CandidateSourcer:
                 )
 
         return result
+
+    def find_candidates(
+        self,
+        job_description: str,
+        location: str = "Bangalore",
+        industry: str = "",
+        compensation_band: str = "",
+        company_stage: str = "",
+        max_queries: int = 3,
+    ) -> dict:
+        """Generate queries AND run live web search to find candidate profiles.
+
+        Returns the same dict as generate_queries() plus a 'candidates' list:
+            [{name, title, company, linkedin_url, snippet, source_query, matched_queries}]
+        """
+        result = self.generate_queries(
+            job_description=job_description,
+            location=location,
+            industry=industry,
+            compensation_band=compensation_band,
+            company_stage=company_stage,
+        )
+
+        # Extract raw query strings for web search
+        raw_queries = [q.get("query", "") for q in result.get("queries", []) if q.get("query")]
+
+        candidates = self.searcher.search_candidates(
+            queries=raw_queries,
+            max_queries=max_queries,
+        )
+        result["candidates"] = candidates
+        return result