From fb25644fa7bdf66749e1fc424e2dcffaf0527d0f Mon Sep 17 00:00:00 2001
From: KaifAhmad1 <kaifahmad087@gmail.com>
Date: Thu, 15 Jan 2026 19:00:42 +0530
Subject: [PATCH] Enhance RelationExtractor with core fixes and verbose logs

- Fix excessive entities being passed to LLM in RelationExtractor
- Add comprehensive 'Heartbeat' verbose logs to methods.py and providers.py
- Ensure robust API key handling and explicit error reporting
---
 semantica/semantic_extract/methods.py   | 11 +++++++++++
 semantica/semantic_extract/providers.py | 24 ++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/semantica/semantic_extract/methods.py b/semantica/semantic_extract/methods.py
index f80a95ca..5e5961dc 100644
--- a/semantica/semantic_extract/methods.py
+++ b/semantica/semantic_extract/methods.py
@@ -1641,6 +1641,11 @@ If a relation doesn't fit any of the preferred types, use the most appropriate t
 Extract meaningful relationships between entities. Use appropriate relation types that accurately describe how entities are connected.
 Common relation types include: related_to, part_of, located_in, created_by, uses, depends_on, interacts_with, and similar variations."""
     
+    verbose_mode = kwargs.get("verbose", False)
+    if verbose_mode:
+        import sys
+        print(f"    [methods.extract_relations_llm] Constructing prompt for {len(prompt_entities)} entities...", flush=True, file=sys.stdout)
+    
     if not SCHEMAS_AVAILABLE:
         raise ImportError("Pydantic schemas not available. Install pydantic/instructor to use LLM extraction.")
 
@@ -1669,7 +1674,13 @@ Entities found in text: {entities_str}"""
     try:
         # Use typed generation with Pydantic schema
         # Pass kwargs to allow max_tokens and other parameters to be used
+        if verbose_mode:
+             import sys
+             print(f"    [methods.extract_relations_llm] Calling llm.generate_typed ({provider}/{model})...", flush=True, file=sys.stdout)
         result_obj = llm.generate_typed(prompt, schema=RelationsResponse, **kwargs)
+        if verbose_mode:
+             import sys
+             print(f"    [methods.extract_relations_llm] Received response from {provider}.", flush=True, file=sys.stdout)
         
         # Convert back to internal Relation format
         relations = []
diff --git a/semantica/semantic_extract/providers.py b/semantica/semantic_extract/providers.py
index 0a2aba92..e293f628 100644
--- a/semantica/semantic_extract/providers.py
+++ b/semantica/semantic_extract/providers.py
@@ -318,6 +318,11 @@ class BaseProvider:
                         "temperature": kwargs.get("temperature", 0.1), # Low temp for structured
                     }
                     
+                    verbose_mode = kwargs.get("verbose", False)
+                    if verbose_mode:
+                        import sys
+                        print(f"    [BaseProvider.generate_typed] Using instructor via {provider_name}. Client: {type(client)}", flush=True, file=sys.stdout)
+
                     # Pass through other common parameters
                     for param in ["max_tokens", "max_completion_tokens", "top_p", "frequency_penalty", "presence_penalty", "seed", "stop", "logit_bias", "user", "top_k"]:
                         if param in kwargs:
@@ -328,6 +333,9 @@ class BaseProvider:
                         create_kwargs["response_format"] = {"type": "json_object"}
                     
                     response = client.chat.completions.create(**create_kwargs)
+                    if verbose_mode:
+                        import sys
+                        print(f"    [BaseProvider.generate_typed] Typed response received via instructor ({provider_name}).", flush=True, file=sys.stdout)
                     return response
             except Exception as e:
                 self.logger.warning(f"Instructor generation failed ({e}), falling back to manual repair loop.")
@@ -706,7 +714,15 @@ class GroqProvider(BaseProvider):
             if param in kwargs:
                 create_kwargs[param] = kwargs[param]
 
+        verbose_mode = kwargs.get("verbose", False)
+        if verbose_mode:
+            import sys
+            print(f"    [GroqProvider.generate] Sending request to Groq API (model: {create_kwargs['model']})...", flush=True, file=sys.stdout)
+
         response = self.client.chat.completions.create(**create_kwargs)
+        if verbose_mode:
+            import sys
+            print(f"    [GroqProvider.generate] Response received from Groq.", flush=True, file=sys.stdout)
         return response.choices[0].message.content
 
     def generate_structured(self, prompt: str, **kwargs) -> dict:
@@ -737,7 +753,15 @@ class GroqProvider(BaseProvider):
             if param in kwargs:
                 create_kwargs[param] = kwargs[param]
 
+        verbose_mode = kwargs.get("verbose", False)
+        if verbose_mode:
+            import sys
+            print(f"    [GroqProvider.generate_structured] Sending structured request to Groq API (model: {create_kwargs['model']})...", flush=True, file=sys.stdout)
+
         response = self.client.chat.completions.create(**create_kwargs)
+        if verbose_mode:
+            import sys
+            print(f"    [GroqProvider.generate_structured] Structured response received from Groq.", flush=True, file=sys.stdout)
         try:
             return self._parse_json(response.choices[0].message.content)
         except Exception as e: