refactor: 🔨 Mostly working Ollama migration, few tweaks left

src/experts/retrieval_agent.py

@@ -18,7 +18,7 @@ EXPANSION_CONFIG = CFG["expansion_agent"]
 
 def retrieve_from_turso(embedded_question, k=5):
     query = f"""
-    SELECT file_path, synopsis, tags, entities, chunk_data,
+    SELECT file_path, synopsis, tags, chunk_data,
     vector_distance_cos(embedding, vector32('{embedded_question}')) AS distance
     FROM notes
     ORDER BY distance ASC
@@ -55,9 +55,7 @@ class DnDRAG(dspy.Module):
             base_url=API_BASE,
             # batch_size=1,
         )
-        self.retrieval_lm = dspy.LM(
-            model=CFG["models"]["retrieval"], api_base=API_BASE + CFG["api"]["api_version"]
-        )
+        self.retrieval_lm = dspy.LM(model=CFG["models"]["retrieval"], api_base=API_BASE)
         with dspy.context(lm=self.retrieval_lm, signature=ExpansionSignature):
             self.query_expander = dspy.Predict("question -> queries:list[str]")
 
@@ -68,9 +66,9 @@ class DnDRAG(dspy.Module):
         print("Enhancing Question")
         with dspy.context(lm=self.retrieval_lm):
             expanded_queries = self.query_expander(question=question).queries
-        print("Enhanced Queries:")
-        for q in expanded_queries:
-            print("    ", q)
+        # print("Enhanced Queries:")
+        # for q in expanded_queries:
+        #     print("    ", q)
         all_embeddings = self.embeddings_model.embed_documents([question] + expanded_queries)
         # print(all_embeddings)
         all_results = []
@@ -81,7 +79,7 @@ class DnDRAG(dspy.Module):
         seen = set()
         unique_results = []
         for row in all_results:
-            key = (row[0], row[4])
+            key = (row[0], row[3])
             if key not in seen:
                 seen.add(key)
                 unique_results.append(row)
@@ -91,18 +89,18 @@ class DnDRAG(dspy.Module):
             source = row[0]
             synopsis = row[1]
             tags = row[2]
-            entities = row[3]
-            content = row[4]
-            closeness = row[5]
+            # entities = row[3]
+            content = row[3]
+            closeness = row[4]
 
             context_parts.append(f"""
 --- Chunk {i + 1} from {source} ---
 synopsis: {synopsis},
 tags: {tags},
-entities: {entities},
 closeness: {closeness},
 {content}
 """)
+        # entities: {entities},
 
         context = "\n\n".join(context_parts)