feat(embeddings): add embedding model support and related changes

* Introduced EmbeddingModel method in Client and Provider interfaces
* Updated InsertThought and SearchThoughts methods to handle embedding models
* Created embeddings table and updated match_thoughts function for model filtering
* Removed embedding column from thoughts table
* Adjusted permissions for new embeddings table

migrations/008_update_match_thoughts.sql

@@ -0,0 +1,34 @@
+create or replace function match_thoughts(
+  query_embedding  vector,
+  match_threshold  float   default 0.7,
+  match_count      int     default 10,
+  filter           jsonb   default '{}'::jsonb,
+  embedding_model  text    default ''
+)
+returns table (
+  id          uuid,
+  content     text,
+  metadata    jsonb,
+  similarity  float,
+  created_at  timestamptz
+)
+language plpgsql
+as $$
+begin
+  return query
+  select
+    t.id,
+    t.content,
+    t.metadata,
+    1 - (e.embedding <=> query_embedding) as similarity,
+    t.created_at
+  from thoughts t
+  join embeddings e on e.thought_id = t.id
+  where 1 - (e.embedding <=> query_embedding) > match_threshold
+    and t.archived_at is null
+    and (embedding_model = '' or e.model = embedding_model)
+    and (filter = '{}'::jsonb or t.metadata @> filter)
+  order by e.embedding <=> query_embedding
+  limit match_count;
+end;
+$$;