AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-14 03:35:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add llm blocking invoke (#15732)

Browse Source
This commit is contained in:
Novice 2025-03-17 16:47:10 +08:00 committed by GitHub
parent e5d6047fb4
commit 04a0ae3aa9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
api/core/plugin/backwards_invocation/model.py
View File

@ -3,7 +3,7 @@ from binascii import hexlify, unhexlify
from collections.abc import Generator
from core.model_manager import ModelManager
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
from core.model_runtime.entities.message_entities import (
PromptMessage,
SystemPromptMessage,
@ -46,7 +46,7 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
model_parameters=payload.completion_params,
tools=payload.tools,
stop=payload.stop,
stream=payload.stream or True,
stream=True if payload.stream is None else payload.stream,
user=user_id,
)
@ -64,7 +64,21 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
else:
if response.usage:
LLMNode.deduct_llm_quota(tenant_id=tenant.id, model_instance=model_instance, usage=response.usage)
return response
def handle_non_streaming(response: LLMResult) -> Generator[LLMResultChunk, None, None]:
yield LLMResultChunk(
model=response.model,
prompt_messages=response.prompt_messages,
system_fingerprint=response.system_fingerprint,
delta=LLMResultChunkDelta(
index=0,
message=response.message,
usage=response.usage,
finish_reason="",
),
)
return handle_non_streaming(response)
@classmethod
def invoke_text_embedding(cls, user_id: str, tenant: Tenant, payload: RequestInvokeTextEmbedding):