From 0e8e082b1aecc1e316b9813aa9249ceba3c81fa0 Mon Sep 17 00:00:00 2001
From: nogueiraguh <nogueiraguh@gmail.com>
Date: Wed, 11 Mar 2026 03:20:04 -0300
Subject: [PATCH] feat: auto-resolve GenAI config for consult embeddings
 endpoint

- Build GenAI config from OCI credentials when no genai_configs exist
- Uses GPT-4.1 as default model with RAG system prompt
- Fixes _call_genai signature (system_prompt via gc dict, not kwarg)
---
 backend/app.py | 48 +++++++++++++++++++++++++++++++++++-------------
 1 file changed, 35 insertions(+), 13 deletions(-)

diff --git a/backend/app.py b/backend/app.py
index ca9f313..850f5f2 100644
--- a/backend/app.py
+++ b/backend/app.py
@@ -3390,24 +3390,46 @@ async def consult_embeddings(req: ConsultQuery, u=Depends(current_user)):
     # 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
+    # Get GenAI config for answering — try saved config first, then auto-resolve from OCI
+    gc = None
     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)
+    if gc_row:
+        gc = dict(gc_row)
+    else:
+        # Auto-resolve: build GenAI config from OCI credentials + default model
+        try:
+            resolved = _resolve_embed_config()
+            gc = {
+                "oci_config_id": resolved["oci_config_id"],
+                "endpoint": resolved.get("endpoint", f"https://inference.generativeai.{resolved.get('genai_region','us-ashburn-1')}.oci.oraclecloud.com"),
+                "compartment_id": resolved.get("compartment_id", ""),
+                "genai_region": resolved.get("genai_region", "us-ashburn-1"),
+                "model_id": "openai.gpt-4.1",
+                "model_ocid": "",
+                "serving_type": "ON_DEMAND",
+                "temperature": 0.3,
+                "max_tokens": 4000,
+                "top_p": 0.9,
+                "top_k": 1,
+                "frequency_penalty": 0,
+                "presence_penalty": 0,
+            }
+            log.info(f"Consult: auto-resolved GenAI config from OCI, model=openai.gpt-4.1")
+        except Exception as e:
+            log.warning(f"Consult: no GenAI config available: {e}")
+            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]
+            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}")
+            return {"answer": "\n\n---\n\n".join(parts), "documents": doc_list, "total": len(all_docs)}
     try:
-        answer, _, _ = _call_genai(gc, [{"role": "user", "content": augmented}], system_prompt=RAG_DEFAULT_SYSTEM_PROMPT)
+        gc["system_prompt"] = RAG_DEFAULT_SYSTEM_PROMPT
+        answer, _, _ = _call_genai(gc, augmented)
     except Exception as e:
         log.error(f"Consult GenAI error: {e}")
         answer = f"Erro ao consultar GenAI: {str(e)[:300]}"