chore: fix ruff linting errors and remove duplicate methods

Author: laxmanclo

test_conflict.py

@@ -1,13 +1,18 @@
 import asyncio
-from vektori.storage.memory import MemoryBackend
+
 from vektori.ingestion.extractor import FactExtractor
-from vektori.models.base import LLMProvider, EmbeddingProvider
+from vektori.models.base import EmbeddingProvider, LLMProvider
+from vektori.storage.memory import MemoryBackend
+
 
 class MockEmbedder(EmbeddingProvider):
     @property
-    def dimension(self): return 2
+    def dimension(self):
+        return 2
+
     async def embed(self, text):
-        if "hate" in text: return [0.5, -0.5]
+        if "hate" in text:
+            return [0.5, -0.5]
         return [0.5, 0.5]
     async def embed_batch(self, texts):
         return [await self.embed(t) for t in texts]
@@ -22,19 +27,19 @@ async def test():
     embedder = MockEmbedder()
     llm = MockLLM()
     extractor = FactExtractor(db, embedder, llm)
-    
+
     # insert first fact
     await extractor._process_facts(
         [{"text": "User loves apples"}],
         session_id="s1", user_id="u1", agent_id=None, conversation="User: I love apples"
     )
-    
+
     # insert second fact
     await extractor._process_facts(
         [{"text": "User hates apples"}],
         session_id="s2", user_id="u1", agent_id=None, conversation="User: Actually I hate apples"
     )
-    
+
     facts = await db.get_active_facts("u1")
     print("Active facts count:", len(facts))
     for f in facts:

test_conflict2.py

@@ -1,16 +1,20 @@
 import asyncio
-from vektori.storage.memory import MemoryBackend
-from vektori.ingestion.extractor import FactExtractor
-from vektori.models.base import LLMProvider, EmbeddingProvider
 import logging
 
+from vektori.ingestion.extractor import FactExtractor
+from vektori.models.base import EmbeddingProvider, LLMProvider
+from vektori.storage.memory import MemoryBackend
+
 logging.basicConfig(level=logging.DEBUG)
 
 class MockEmbedder(EmbeddingProvider):
     @property
-    def dimension(self): return 2
+    def dimension(self):
+        return 2
+
     async def embed(self, text):
-        if "hate" in text: return [0.5, 0.4]  # High similarity to trigger check
+        if "hate" in text:
+            return [0.5, 0.4]  # High similarity to trigger check
         return [0.5, 0.5]
     async def embed_batch(self, texts):
         return [await self.embed(t) for t in texts]
@@ -28,12 +32,13 @@ async def test():
     embedder = MockEmbedder()
     llm = MockLLM()
     extractor = FactExtractor(db, embedder, llm)
-    
+
     await extractor._process_facts([{"text": "User loves apples"}], "s1", "u1", None, "")
     await extractor._process_facts([{"text": "User hates apples"}], "s2", "u1", None, "")
-    
+
     facts = await db.get_active_facts("u1")
     print("Active facts count:", len(facts))
-    for f in facts: print("-", f["text"])
+    for f in facts:
+        print("-", f["text"])
 
 asyncio.run(test())

test_llm_dedup_check.py

@@ -1,13 +1,18 @@
 import asyncio
-from vektori.storage.memory import MemoryBackend
+
 from vektori.ingestion.extractor import FactExtractor
-from vektori.models.base import LLMProvider, EmbeddingProvider
+from vektori.models.base import EmbeddingProvider, LLMProvider
+from vektori.storage.memory import MemoryBackend
+
 
 class MockEmbedder(EmbeddingProvider):
     @property
-    def dimension(self): return 2
+    def dimension(self):
+        return 2
+
     async def embed(self, text):
-        if "hate" in text: return [0.5, 0.4] # Give sim around 0.8 to test LLM
+        if "hate" in text:
+            return [0.5, 0.4]  # Give sim around 0.8 to test LLM
         return [0.5, 0.5]
     async def embed_batch(self, texts):
         return [await self.embed(t) for t in texts]
@@ -26,8 +31,8 @@ async def test():
     await db.initialize()
     embedder = MockEmbedder()
     llm = MockLLM()
-    extractor = FactExtractor(db, embedder, llm)
-    
+    _ = FactExtractor(db, embedder, llm)
+
     # Needs actual logic in Extractor...
-    
+
 asyncio.run(test())

test_synthesis.py

@@ -1,6 +1,8 @@
 import asyncio
+
 from vektori import Vektori
 
+
 async def test():
     v = Vektori(storage_backend="memory")
     await v._ensure_initialized()
@@ -11,15 +13,15 @@ async def mock_emb(*args, **kwargs):
         return [[0.1, 0.2]]
     v.llm.generate = mock_gen
     v.embedder.embed_batch = mock_emb
-    
+
     # add dummy facts so synthesize triggers (needs >=5 base facts)
     for i in range(5):
         await v.db.insert_fact(f"fact {i}", [0.1, 0.2], "u1", confidence=1.0)
-    
+
     n = await v.synthesize("u1")
     print("New synthesized facts:", n)
     syntheses = await v.db.search_syntheses([0.1, 0.2], "u1", limit=100)
     for s in syntheses:
         print("Synthesized:", s["text"])
-            
+
 asyncio.run(test())

vektori/client.py

@@ -164,7 +164,7 @@ async def add(
             {"status": "ok", "sentences_stored": N, "extraction": "queued"|"done"|"skipped"}
         """
         await self._ensure_initialized()
-        
+
         result = await self._pipeline.ingest(
             messages, session_id, user_id, agent_id, metadata, session_time=session_time
         )
@@ -185,7 +185,7 @@ async def _bg_synthesize(uid: str, aid: str | None) -> None:
                             await self.synthesize(user_id=uid, agent_id=aid)
                     except Exception as e:
                         logger.error("Auto-synthesis failed: %s", e)
-                        
+
                 task = asyncio.create_task(_bg_synthesize(user_id, agent_id))
                 self._bg_tasks.add(task)
                 task.add_done_callback(self._bg_tasks.discard)
@@ -201,7 +201,7 @@ async def synthesize(self, user_id: str, agent_id: str | None = None) -> int:
         Run a cross-session synthesis pass for the user.
         Examines active facts across sessions to form aggregate/macro facts
         (e.g., "User consistently prefers X", "User has done Y across multiple sessions").
-        
+
         Returns the number of new aggregate facts inserted.
         """
         await self._ensure_initialized()

vektori/ingestion/synthesis.py

@@ -1,11 +1,8 @@
-import json
 import logging
-from datetime import datetime, timezone
-from typing import Any
 
-from vektori.models.base import LLMProvider, EmbeddingProvider
-from vektori.storage.base import StorageBackend
 from vektori.ingestion.extractor import _parse_json_response
+from vektori.models.base import EmbeddingProvider, LLMProvider
+from vektori.storage.base import StorageBackend
 
 logger = logging.getLogger(__name__)
 
@@ -45,17 +42,17 @@ def __init__(
     async def synthesize(self, user_id: str, agent_id: str | None = None) -> int:
         # Get active facts for the user
         facts = await self.db.get_active_facts(user_id=user_id, agent_id=agent_id, limit=300)
-        
+
         # Filter out existing synthesis facts so we don't synthesize the syntheses too much,
         # or maybe we do want to? For now, let's keep it simple: filter them out to avoid feedback loops unless needed.
         # Actually, let's just feed them all, but maybe limit to non-synthesis for base patterns.
         base_facts = [f for f in facts if f.get("metadata", {}).get("source") != "synthesis"]
-        
+
         if len(base_facts) < 5:
             return 0  # Not enough facts to form a pattern
-            
+
         facts_list = "\n".join(f"- {f['text']} (Session: {f.get('session_id', 'unknown')}, Date: {f.get('created_at', 'unknown')})" for f in base_facts)
-        
+
         prompt = SYNTHESIS_PROMPT.format(facts_list=facts_list, max_facts=5)
         try:
             response = await self.llm.generate(prompt, max_tokens=1000)
@@ -64,18 +61,18 @@ async def synthesize(self, user_id: str, agent_id: str | None = None) -> int:
         except Exception as e:
             logger.warning("Synthesis LLM call failed: %s", e)
             return 0
-            
+
         if not new_facts:
             return 0
-            
+
         texts = [f["text"] for f in new_facts]
         try:
             embeddings = await self.embedder.embed_batch(texts)
         except Exception as e:
             logger.error("Synthesis batch embed failed: %s", e)
             return 0
 
-        now = datetime.now(timezone.utc)
+
         inserted = 0
 
         for fact_dict, emb in zip(new_facts, embeddings):
@@ -86,22 +83,22 @@ async def synthesize(self, user_id: str, agent_id: str | None = None) -> int:
                 agent_id=agent_id,
                 limit=1
             )
-            
+
             skip = False
             if existing:
                 best = existing[0]
                 sim = 1.0 - best.get("distance", 1.0)
                 if sim > 0.85:
                     # We already have this synthesis, let's just skip it
                     skip = True
-                    
+
             if skip:
                 continue
-                
+
             try:
                 # Need to link the synthesis to the facts that generated it if we want graph traversal
                 # But for now we just insert it
-                synthesis_id = await self.db.insert_synthesis(
+                _ = await self.db.insert_synthesis(
                     text=fact_dict["text"],
                     embedding=emb,
                     user_id=user_id,
@@ -111,5 +108,5 @@ async def synthesize(self, user_id: str, agent_id: str | None = None) -> int:
                 inserted += 1
             except Exception as e:
                 logger.warning("Failed to insert synthesis: %s", e)
-                
+
         return inserted

vektori/storage/base.py

@@ -198,48 +198,19 @@ async def insert_fact_sources(self, pairs: list[tuple[str, str]]) -> None:
 
     # ── Syntheses ──
 
-    
-    async def insert_synthesis(self, text: str, embedding: list[float], user_id: str, agent_id: str | None = None, score: float = 1.0, mentions: int = 1, metadata: dict | None = None) -> str:
-        raise NotImplementedError()
-
-    
-    async def insert_synthesis_fact(self, synthesis_id: str, fact_id: str) -> None:
-        raise NotImplementedError()
-
-    
-    async def get_syntheses_for_facts(self, fact_ids: list[str]) -> list[dict[str, Any]]:
-        return []
-
-    
-    async def search_syntheses(self, embedding: list[float], user_id: str, agent_id: str | None = None, limit: int = 10, threshold: float = 0.0) -> list[dict[str, Any]]:
-        return []
-
-    @abstractmethod
-    async def get_source_sentences(self, fact_ids: list[str]) -> list[str]:
-        """Return sentence IDs that are sources for the given facts (via fact_sources)."""
-        ...
 
-    @abstractmethod
-    async def get_sentences_by_ids(self, sentence_ids: list[str]) -> list[dict[str, Any]]:
-        """Fetch full sentence rows for the given IDs."""
-        ...
-
-
-    # ── Syntheses ──
-
-    
     async def insert_synthesis(self, text: str, embedding: list[float], user_id: str, agent_id: str | None = None, score: float = 1.0, mentions: int = 1, metadata: dict | None = None) -> str:
         raise NotImplementedError()
 
-    
+
     async def insert_synthesis_fact(self, synthesis_id: str, fact_id: str) -> None:
         raise NotImplementedError()
 
-    
+
     async def get_syntheses_for_facts(self, fact_ids: list[str]) -> list[dict[str, Any]]:
         return []
 
-    
+
     async def search_syntheses(self, embedding: list[float], user_id: str, agent_id: str | None = None, limit: int = 10, threshold: float = 0.0) -> list[dict[str, Any]]:
         return []
 
@@ -252,8 +223,6 @@ async def get_source_sentences(self, fact_ids: list[str]) -> list[str]:
     async def get_sentences_by_ids(self, sentence_ids: list[str]) -> list[dict[str, Any]]:
         """Fetch full sentence rows for the given IDs."""
         ...
-
-
     # ── Episodes ──
 
     @abstractmethod
@@ -303,16 +272,6 @@ async def search_episodes(
         """
         ...
 
-    @abstractmethod
-    async def get_source_sentences(self, fact_ids: list[str]) -> list[str]:
-        """Return sentence IDs that are sources for the given facts (via fact_sources)."""
-        ...
-
-    @abstractmethod
-    async def get_sentences_by_ids(self, sentence_ids: list[str]) -> list[dict[str, Any]]:
-        """Fetch full sentence rows for the given IDs."""
-        ...
-
     # ── Sessions ──
 
     @abstractmethod