GustavoNogueira/A-Team-Security-Infra-Agent-Engineer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: auto-resolve GenAI config for consult embeddings endpoint

Browse Source 
- 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)
This commit is contained in:
nogueiraguh
2026-03-11 03:20:04 -03:00
parent 587a809156
commit 0e8e082b1a
1 changed files with 35 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
backend/app.py
View File

@@ -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]}"