feat: consult embeddings UI, vector search FLOAT32 fix, and base64 compartment decode

- Add Consult Embeddings sub-menu with chat-like Q&A interface
- Fix VECTOR_DISTANCE FLOAT32/FLOAT64 mismatch (array 'd' → 'f')
- Decode base64 compartment_id in _resolve_embed_config
- Sidebar sub-item navigation for Embeddings hierarchy
- Fallback to raw document display when no GenAI config available

backend/app.py

@@ -2419,7 +2419,7 @@ def _resolve_embed_config(oci_config_id: str = None, genai_cfg: dict = None) ->
                     "oci_config_id": oc["id"],
                     "genai_region": oc["region"],
                     "endpoint": f"https://inference.generativeai.{oc['region']}.oci.oraclecloud.com",
-                    "compartment_id": (dict(oc).get("compartment_id") or oc["tenancy_ocid"]),
+                    "compartment_id": _safe_dec(dict(oc).get("compartment_id") or oc["tenancy_ocid"]),
                 }
     # Last resort: any genai config
     with db() as c:
@@ -2432,7 +2432,7 @@ def _resolve_embed_config(oci_config_id: str = None, genai_cfg: dict = None) ->
                 "oci_config_id": oc["id"],
                 "genai_region": oc["region"],
                 "endpoint": f"https://inference.generativeai.{oc['region']}.oci.oraclecloud.com",
-                "compartment_id": (dict(oc).get("compartment_id") or oc["tenancy_ocid"]),
+                "compartment_id": _safe_dec(dict(oc).get("compartment_id") or oc["tenancy_ocid"]),
             }
     raise HTTPException(400, "Nenhuma credencial OCI configurada para gerar embeddings.")
 
@@ -2466,7 +2466,7 @@ def _vector_search(cfg: dict, query_embedding: list, top_k: int = 5, table_name:
     conn = _get_adb_connection(cfg)
     try:
         cur = conn.cursor()
-        vec = array.array('d', query_embedding)
+        vec = array.array('f', query_embedding)
         if tenancy:
             # Filter by tenancy in METADATA JSON field using LIKE for broad compatibility
             # Matches both structured JSON {"tenancy":"X",...} and legacy "tenancy: X, ..."
@@ -3319,6 +3319,83 @@ async def embed_upload_url(
     _audit(u["id"], u["username"], "embed_url", url, f"{len(documents)} chunks")
     return {"ok": True, "message": f"Embedding de {len(documents)} chunks iniciado", "chunks": len(documents), "url": url}
 
+class ConsultQuery(BaseModel):
+    query: str
+    table_name: str = ""
+    top_k: int = 10
+
+@app.post("/api/embeddings/consult")
+async def consult_embeddings(req: ConsultQuery, u=Depends(current_user)):
+    """Query embeddings via vector search + GenAI to get a formatted answer."""
+    if not req.query.strip():
+        raise HTTPException(400, "Query não pode ser vazia")
+    adb_configs = _get_active_adb_configs(u["id"])
+    if not adb_configs:
+        raise HTTPException(400, "Nenhuma conexão ADB ativa configurada")
+    # Collect results from all active ADB configs + tables
+    all_docs = []
+    for adb_cfg in adb_configs:
+        log.info(f"Consult: processing ADB {adb_cfg['id']} ({adb_cfg.get('config_name','')})")
+        try:
+            emb_genai = _resolve_embed_config(oci_config_id=adb_cfg.get("oci_config_id"))
+            log.info(f"Consult: resolved embed config, compartment={emb_genai.get('compartment_id','?')[:30]}, region={emb_genai.get('genai_region','?')}")
+        except Exception as e:
+            log.warning(f"Consult: resolve config failed for {adb_cfg['id']}: {e}")
+            continue
+        emb_model = adb_cfg.get("embedding_model_id", "")
+        if not emb_model:
+            log.warning(f"Consult: no embedding_model_id for {adb_cfg['id']}")
+            continue
+        try:
+            query_embedding = _embed_text(req.query, emb_genai, emb_model)
+            log.info(f"Consult: embedded query, dims={len(query_embedding)}")
+        except Exception as e:
+            log.warning(f"Consult: embed failed for {adb_cfg['id']}: {e}")
+            continue
+        tables = _get_tables_for_config(adb_cfg["id"], active_only=True)
+        log.info(f"Consult: {len(tables)} active tables, filter='{req.table_name}'")
+        if req.table_name:
+            tables = [t for t in tables if t["table_name"] == req.table_name]
+        for tbl in tables:
+            try:
+                docs = _vector_search(adb_cfg, query_embedding, top_k=req.top_k, table_name=tbl["table_name"])
+                for d in docs:
+                    d["source"] = f"{tbl['table_name']}"
+                all_docs.extend(docs)
+            except Exception as e:
+                log.warning(f"Consult: search failed on {tbl['table_name']}: {type(e).__name__}: {e}")
+    if not all_docs:
+        return {"answer": "Nenhum resultado encontrado nas bases vetoriais.", "documents": [], "total": 0}
+    # Sort by distance and take top results
+    all_docs.sort(key=lambda d: d.get("distance", 999))
+    top_docs = all_docs[:req.top_k]
+    # Build context and call GenAI
+    rag_context = _build_rag_context(top_docs)
+    augmented = RAG_CONTEXT_TEMPLATE.format(context=rag_context, question=req.query)
+    # Get GenAI config for answering
+    with db() as c:
+        gc_row = c.execute("SELECT * FROM genai_configs WHERE is_default=1 ORDER BY created_at DESC").fetchone()
+        if not gc_row:
+            gc_row = c.execute("SELECT * FROM genai_configs ORDER BY created_at DESC").fetchone()
+    if not gc_row:
+        # No GenAI config — return raw documents formatted as answer
+        parts = []
+        for i, d in enumerate(top_docs, 1):
+            content = d.get("content", "")
+            if len(content) > 800: content = content[:800] + "..."
+            parts.append(f"**Documento {i}** — `{d.get('source', '?')}` (distância: {d.get('distance', 0):.4f})\n\n{content}")
+        raw_answer = "**Resultados da busca vetorial** (sem GenAI configurado para sumarizar):\n\n---\n\n" + "\n\n---\n\n".join(parts)
+        doc_list = [{"content": d.get("content", "")[:500], "source": d.get("source", ""), "distance": round(d.get("distance", 0), 4), "metadata": d.get("metadata", "")} for d in top_docs]
+        return {"answer": raw_answer, "documents": doc_list, "total": len(all_docs)}
+    gc = dict(gc_row)
+    try:
+        answer, _, _ = _call_genai(gc, [{"role": "user", "content": augmented}], system_prompt=RAG_DEFAULT_SYSTEM_PROMPT)
+    except Exception as e:
+        log.error(f"Consult GenAI error: {e}")
+        answer = f"Erro ao consultar GenAI: {str(e)[:300]}"
+    doc_list = [{"content": d.get("content", "")[:500], "source": d.get("source", ""), "distance": round(d.get("distance", 0), 4), "metadata": d.get("metadata", "")} for d in top_docs]
+    return {"answer": answer, "documents": doc_list, "total": len(all_docs)}
+
 @app.get("/api/embeddings/{vid}/list")
 async def list_embeddings(vid: str, table_name: str = Query(""), limit: int = Query(50), offset: int = Query(0), u=Depends(current_user)):
     with db() as c: