atendentepro 0.6.8__py3-none-any.whl → 0.6.9__py3-none-any.whl

atendentepro/agents/knowledge.py

@@ -115,7 +115,7 @@ async def _find_relevant_chunks(query: str, top_k: int = 3) -> List[dict]:
 
 
 @function_tool
-async def go_to_rag(question: str) -> KnowledgeToolResult:
+async def go_to_rag(question: str) -> dict:
     """
     Utilize RAG to answer the user's question.
     
@@ -123,7 +123,7 @@ async def go_to_rag(question: str) -> KnowledgeToolResult:
         question: The question to answer using RAG.
         
     Returns:
-        KnowledgeToolResult with answer, context, sources, and confidence.
+        Dictionary with answer, context, sources, and confidence (serialized KnowledgeToolResult).
     """
     from atendentepro.utils import get_async_client
     from atendentepro.config import get_config
@@ -138,7 +138,7 @@ async def go_to_rag(question: str) -> KnowledgeToolResult:
             context="",
             sources=[],
             confidence=0.0,
-        )
+        ).model_dump()
     
     context_sections: List[str] = []
     sources: List[str] = []
@@ -215,7 +215,7 @@ async def go_to_rag(question: str) -> KnowledgeToolResult:
         context=context,
         sources=sources,
         confidence=confidence,
-    )
+    ).model_dump()
 
 
 def create_knowledge_agent(

{atendentepro-0.6.8.dist-info → atendentepro-0.6.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: atendentepro
-Version: 0.6.8
+Version: 0.6.9
 Summary: Framework de orquestração de agentes IA com tom e estilo customizáveis. Integra documentos (RAG), APIs e bancos de dados em uma plataforma inteligente multi-agente.
 Author-email: BeMonkAI <contato@monkai.com.br>
 Maintainer-email: BeMonkAI <contato@monkai.com.br>

{atendentepro-0.6.8.dist-info → atendentepro-0.6.9.dist-info}/RECORD

@@ -9,7 +9,7 @@ atendentepro/agents/escalation.py,sha256=pAS1HANW1jMCBZHekVxvuN9NZ_z9IpAYWbfUzH0
 atendentepro/agents/feedback.py,sha256=cQd35y2-u93GRmu36ErAMyQEinxvNUaDGblGTGrWCfw,37486
 atendentepro/agents/flow.py,sha256=8SsAQ_f-daOM25EVBTMKGSUI9ywG3y4B0bFcCnrUfo0,2645
 atendentepro/agents/interview.py,sha256=3eWHUw63OJuVpHH-QYtdL8SadRgevNLv2N8Esa4Za2c,2722
-atendentepro/agents/knowledge.py,sha256=Xew_qhAdBrm3oVRvHhKh2oi6aURyeIKU5CtgfAHBYEI,11054
+atendentepro/agents/knowledge.py,sha256=crBBwOjZYKVtSfRYNIU6wepMsGY4yixc-c_iyzNkGa8,11089
 atendentepro/agents/onboarding.py,sha256=IId7N9VeTvHggjK_piDOAmwzBztj6oHqbZq7YOpVJIg,2687
 atendentepro/agents/triage.py,sha256=pdYCA5AqbGMY0WoJXvdceAz_gnQ7D_fJp7dxxsD-GDg,1958
 atendentepro/agents/usage.py,sha256=tTfbqh3vRIDu0cnB65tv-Z3neEj90COp85nlIVpRLJ8,2183
@@ -36,9 +36,9 @@ atendentepro/utils/__init__.py,sha256=x2yMUueBilWmI2qASSGbFREeyu0a65r3TuDt0euxNA
 atendentepro/utils/openai_client.py,sha256=R0ns7SU36vTgploq14-QJMTke1pPxcAXlENDeoHU0L4,4552
 atendentepro/utils/tracing.py,sha256=kpTPw1PF4rR1qq1RyBnAaPIQIJRka4RF8MfG_JrRJ7U,8486
 atendentepro/utils/user_loader.py,sha256=J8wd-XF2PZg_i1ped8FI8nmGjmUafXROWJa1tYxSDMI,10623
-atendentepro-0.6.8.dist-info/licenses/LICENSE,sha256=TF6CdXxePoT9DXtPnCejiU5mUwWzrFzd1iyWJyoMauA,983
-atendentepro-0.6.8.dist-info/METADATA,sha256=oRNLhZMOr1RrV75bpeyXv_SSvnNStE7IZqhPkNjmqk8,45468
-atendentepro-0.6.8.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-atendentepro-0.6.8.dist-info/entry_points.txt,sha256=OP0upzqJF3MLS6VX-M-5BfUwx5YLJO2sJ3YBAp4e6yI,89
-atendentepro-0.6.8.dist-info/top_level.txt,sha256=BFasD4SMmgDUmWKlTIZ1PeuukoRBhyiMIz8umKWVCcs,13
-atendentepro-0.6.8.dist-info/RECORD,,
+atendentepro-0.6.9.dist-info/licenses/LICENSE,sha256=TF6CdXxePoT9DXtPnCejiU5mUwWzrFzd1iyWJyoMauA,983
+atendentepro-0.6.9.dist-info/METADATA,sha256=kZCsfh6CtvNykwOrGViW6KdaRrxTqhFMpczizVNpwOg,45468
+atendentepro-0.6.9.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+atendentepro-0.6.9.dist-info/entry_points.txt,sha256=OP0upzqJF3MLS6VX-M-5BfUwx5YLJO2sJ3YBAp4e6yI,89
+atendentepro-0.6.9.dist-info/top_level.txt,sha256=BFasD4SMmgDUmWKlTIZ1PeuukoRBhyiMIz8umKWVCcs,13
+atendentepro-0.6.9.dist-info/RECORD,,