refactor: 🔨 Mostly working Ollama migration, few tweaks left

config.yaml

@@ -1,24 +1,24 @@
 # --- Connection Settings ---
 api:
-  base_url: "http://framework.tawny-bellatrix.ts.net:1234"
+  base_url: "http://100.110.238.94:11434"
   api_version: "/v1/"
 
 # --- Model Settings ---
 models:
-  enrich: "lm_studio/qwen-" # will have an identifier, based on amount of active LLMs see ./load_ingestion_llms.sh
+  enrich: "ollama/granite4.1:3b"
-  embedding: "text-embedding-qwen3-embedding-8b"
+  embedding: "qwen3-embedding:4b"
-  retrieval: "lm_studio/qwen/qwen3-30b-a3b-2507"
+  retrieval: "ollama/qwen3.6:latest"
-  expansion: "lm_studio/qwen/qwen3-30b-a3b-2507"
+  expansion: "ollama/granite4.1:3b"
 
 # --- Ingestion Settings ---
 ingestion:
   data_dir: "/home/jake/DnD"
   db_path: "./data/"
   db_name: "dmv.db"
-  active_llms: 2
+  active_llms: 1
-  parallel_requests_per_llm: 2
+  parallel_requests_per_llm: 6
-  chunk_size: 800
+  chunk_size: 1200
-  chunk_overlap: 100
+  chunk_overlap: 200
   embedding_batch_size: 32
   time_file_location: "./data/time_file.txt"
 
@@ -29,7 +29,7 @@ ingestion_agent:
     Analyze the provided notes and extract a concise synopsis and relevant metadata.
     synopsis = A one-sentence summary of the document.
     tags = Relevant tags (NPCs, Locations, Items, Plot Points).
-    entities = a list of Key names of people, places, or factions.
+    entities = a list of names for people, places, or factions.
     "note -> synopsis:str, tags: list[str], entities: list[str]"
 
 retrieval_agent:
@@ -41,7 +41,7 @@ retrieval_agent:
 
 expansion_agent:
   expansion_signature: |
-    You are a query expansion expert, specialised in Dungeons and Dragons.
+    You are an expert Dungeon Master's assistant.
-    Given a user's question, generate 3-5 similar but enhanced search queries that would help find more relevant information.
+    Given a user's question, generate 3-5 similar but enhanced search queries that would help find more relevant information in DnD notes.
     Each expanded query should be distinct and add different perspective to the original question.
     Return only the queries as a JSON list with key "queries"."""

load_ingestion_llms.sh

@@ -1,5 +1,5 @@
-lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-0" --ttl 1800
+# lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-0" --ttl 1800
-lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-1" --ttl 1800
+# lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-1" --ttl 1800
 # lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-2" --ttl 1800
 # lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-3" --ttl 1800
 # lms load qwen-4b-instruct-2507 --parallel 2 --identifier "qwen-4" --ttl 1800

src/embedding.py

@@ -10,7 +10,7 @@ API_VERSION = CFG["api"]["api_version"]
 
 class LocalLMEmbeddings(Embeddings):
     def __init__(self, model: str, base_url: str = API_BASE, batch_size: int = 32):
-        self.url = f"{base_url}/{API_VERSION}embeddings"
+        self.url = f"{base_url}/api/embed"
         self.model = model
         self.batch_size = batch_size
 
@@ -22,10 +22,11 @@ class LocalLMEmbeddings(Embeddings):
             response = requests.post(
                 self.url, json=payload, timeout=120
             )  # Longer timeout for batches
+            # print(response)
             response.raise_for_status()
             data = response.json()
             # print(data)
-            return [item["embedding"] for item in data["data"]]
+            return data["embeddings"]
         except Exception as e:
             print(f"❌ Batch request failed: {e}")
             # Returning empty lists to maintain index integrity if needed,

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(
+        self.retrieval_lm = dspy.LM(model=CFG["models"]["retrieval"], api_base=API_BASE)
-            model=CFG["models"]["retrieval"], api_base=API_BASE + CFG["api"]["api_version"]
-        )
         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:")
+        # print("Enhanced Queries:")
-        for q in expanded_queries:
+        # for q in expanded_queries:
-            print("    ", q)
+        #     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]
+            # entities = row[3]
-            content = row[4]
+            content = row[3]
-            closeness = row[5]
+            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)
 

src/ingest.py

@@ -83,7 +83,7 @@ def enrich_chunks(chunks: list) -> list:
 
         try:
             with dspy.context(
-                lm=dspy.LM(model=f"{MODEL_BASE}{lm_index}", api_base=API_BASE + API_VERSION),
+                lm=dspy.LM(model=f"{MODEL_BASE}", api_base=API_BASE),
                 chat_template_kwargs={"enable_thinking": False},
             ):
                 response = IngestionAgent().ingest(note=chunk.page_content)
@@ -140,10 +140,11 @@ def embed_chunks(chunks: List[Any], batch_size: int = EMBEDDING_BATCH_SIZE) -> L
     # Process chunks in batches
     for i in tqdm(range(0, total_chunks, batch_size), desc="Embedding batches"):
         batch = chunks[i : i + batch_size]
-        print(f"🚀 Processing batch {(i // batch_size) + 1} (Size: {len(batch)})...")
+        # print(f"🚀 Processing batch {(i // batch_size) + 1} (Size: {len(batch)})...")
         batch_content = [chunk.page_content for chunk in batch]
         try:
             batch_embeddings = embeddings_model.embed_documents(batch_content)
+            # print(len(batch_embeddings[0]))
             # Process each chunk in the batch
             for j, (chunk, embedding) in enumerate(zip(batch, batch_embeddings)):
                 # Extract metadata
@@ -233,8 +234,15 @@ def save_to_db(chunk_dicts):
     # SQL with named placeholders for clarity and safety
     insert_sql = """
     INSERT INTO notes (
-        file_path, file_name, chunk_data, synopsis, tags, entities, embedding, timestamp
+        file_path,
-    ) VALUES (?, ?, ?, ?, ?, ?, vector32(?), ?)
+        file_name,
+        chunk_data,
+        synopsis,
+        tags,
+       -- entities,
+        embedding,
+        timestamp
+    ) VALUES (?, ?, ?, ?, ?, vector32(?), ?)
     """
 
     # Prepare batch data: convert each dict to a tuple in correct order
@@ -250,7 +258,7 @@ def save_to_db(chunk_dicts):
                 entry["chunk_data"],
                 entry["synopsis"],
                 ",".join(entry["tags"]),  # Store as comma-separated string
-                ",".join(entry["entities"]),  # Store as comma-separated string
+                # ",".join(entry["entities"]),  # Store as comma-separated string
                 embedding_str,
                 entry["timestamp"],
             )
@@ -277,8 +285,8 @@ def create_db():
         chunk_data TEXT NOT NULL,
         synopsis TEXT,
         tags TEXT,  -- comma-separated
-        entities TEXT,  -- comma-separated
+        -- entities TEXT,  -- comma-separated
-        embedding F32_BLOB(4096),
+        embedding F32_BLOB(2560),
         timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
     )
     """)

src/retrieve.py

@@ -87,8 +87,7 @@ def main():
     dspy.configure(verbose_errors=True)
     dspy.configure(callbacks=[CallbackHandler(logger)])
     # 1. Setup the LLM
-    print("🚀 Initializing Qwen-8B via LM Studio...")
+    lm = dspy.LM(RETRIEVE_MODEL, api_base=API_BASE)
-    lm = dspy.LM(RETRIEVE_MODEL, api_base=API_BASE + API_VERSION)
     dspy.configure(lm=lm)
 
     # 2. Load the RAG System (only happens once!)