hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-16 06:16:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error (#9326)

Browse Source 
Co-authored-by: wwwc <wwwc@outlook.com>
This commit is contained in:
Warren Wong
2024-10-15 16:26:44 +08:00
committed by GitHub
parent fb32e5ca9a
commit b597a0d31c
9 changed files with 638 additions and 381 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
api/core/model_runtime/model_providers/azure_openai/_constant.py
View File

@@ -1098,6 +1098,14 @@ LLM_BASE_MODELS = [
ModelPropertyKey.CONTEXT_SIZE: 128000,
},
parameter_rules=[
ParameterRule(
name="temperature",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
),
ParameterRule(
name="top_p",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
),
ParameterRule(
name="response_format",
label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
@@ -1135,6 +1143,14 @@ LLM_BASE_MODELS = [
ModelPropertyKey.CONTEXT_SIZE: 128000,
},
parameter_rules=[
ParameterRule(
name="temperature",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
),
ParameterRule(
name="top_p",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
),
ParameterRule(
name="response_format",
label=I18nObject(zh_Hans="回复格式", en_US="response_format"),

10
api/core/model_runtime/model_providers/azure_openai/llm/llm.py
View File

@@ -119,7 +119,15 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
try:
client = AzureOpenAI(**self._to_credential_kwargs(credentials))
if ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
if model.startswith("o1"):
client.chat.completions.create(
messages=[{"role": "user", "content": "ping"}],
model=model,
temperature=1,
max_completion_tokens=20,
stream=False,
)
elif ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
# chat model
client.chat.completions.create(
messages=[{"role": "user", "content": "ping"}],