youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-03 08:58:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: remove streaming structured output from invoke_llm_with_structured_output

Browse Source 
Signed-off-by: Stream <Stream_2@qq.com>
This commit is contained in:
Stream
2026-01-29 23:41:08 +08:00
parent 749cebe60d
commit edce6d4152
4 changed files with 43 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
api/core/plugin/backwards_invocation/model.py
View File

@ -114,46 +114,32 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
model_instance=model_instance,
prompt_messages=payload.prompt_messages,
json_schema=payload.structured_output_schema,
model_parameters=payload.completion_params,
tools=payload.tools,
stop=payload.stop,
stream=True if payload.stream is None else payload.stream,
user=user_id,
model_parameters=payload.completion_params,
user=user_id
)
if isinstance(response, Generator):
if response.usage:
llm_utils.deduct_llm_quota(tenant_id=tenant.id, model_instance=model_instance, usage=response.usage)
def handle() -> Generator[LLMResultChunkWithStructuredOutput, None, None]:
for chunk in response:
if chunk.delta.usage:
llm_utils.deduct_llm_quota(
tenant_id=tenant.id, model_instance=model_instance, usage=chunk.delta.usage
)
chunk.prompt_messages = []
yield chunk
def handle_non_streaming(
response: LLMResultWithStructuredOutput,
) -> Generator[LLMResultChunkWithStructuredOutput, None, None]:
yield LLMResultChunkWithStructuredOutput(
model=response.model,
prompt_messages=[],
system_fingerprint=response.system_fingerprint,
structured_output=response.structured_output,
delta=LLMResultChunkDelta(
index=0,
message=response.message,
usage=response.usage,
finish_reason="",
),
)
return handle()
else:
if response.usage:
llm_utils.deduct_llm_quota(tenant_id=tenant.id, model_instance=model_instance, usage=response.usage)
def handle_non_streaming(
response: LLMResultWithStructuredOutput,
) -> Generator[LLMResultChunkWithStructuredOutput, None, None]:
yield LLMResultChunkWithStructuredOutput(
model=response.model,
prompt_messages=[],
system_fingerprint=response.system_fingerprint,
structured_output=response.structured_output,
delta=LLMResultChunkDelta(
index=0,
message=response.message,
usage=response.usage,
finish_reason="",
),
)
return handle_non_streaming(response)
return handle_non_streaming(response)
@classmethod
def invoke_text_embedding(cls, user_id: str, tenant: Tenant, payload: RequestInvokeTextEmbedding):