langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

add OpenAI o3-mini model and reasoning_effort parameter

Browse Source
This commit is contained in:
k-zaku
2025-02-05 01:53:01 +09:00
parent c0d0c63592
commit bff4cc5fe4
10 changed files with 140 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
api/Dockerfile
+4 -2
View File
@@ -52,12 +52,14 @@ RUN apt-get update \
&& apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
# if you located in China, you can use aliyun mirror to speed up
# && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
&& echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
&& echo "deb http://deb.debian.org/debian bookworm main" > /etc/apt/sources.list \
&& apt-get update \
# For Security
&& apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
&& apt-get install -y --no-install-recommends expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
# install a chinese font to support the use of tools like matplotlib
&& apt-get install -y fonts-noto-cjk \
# install libmagic to support the use of python-magic guess MIMETYPE
&& apt-get install -y libmagic1 \
&& apt-get autoremove -y \
&& rm -rf /var/lib/apt/lists/*
api/core/model_runtime/model_providers/openai/llm/_position.yaml
+2
View File
@@ -2,6 +2,8 @@
- o1-2024-12-17
- o1-mini
- o1-mini-2024-09-12
- o3-mini
- o3-mini-2025-01-31
- gpt-4
- gpt-4o
- gpt-4o-2024-05-13
api/core/model_runtime/model_providers/openai/llm/llm.py
+5 -5
View File
@@ -619,9 +619,9 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
# clear illegal prompt messages
prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)
# o1 compatibility
# o1, o3 compatibility
block_as_stream = False
if model.startswith("o1"):
if model.startswith(("o1", "o3")):
if "max_tokens" in model_parameters:
model_parameters["max_completion_tokens"] = model_parameters["max_tokens"]
del model_parameters["max_tokens"]
@@ -941,7 +941,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
]
)
if model.startswith("o1"):
if model.startswith(("o1", "o3")):
system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
if system_message_count > 0:
new_prompt_messages = []
@@ -1053,7 +1053,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
model = model.split(":")[1]
# Currently, we can use gpt4o to calculate chatgpt-4o-latest's token.
if model == "chatgpt-4o-latest" or model.startswith("o1"):
if model == "chatgpt-4o-latest" or model.startswith(("o1", "o3")):
model = "gpt-4o"
try:
@@ -1068,7 +1068,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
tokens_per_message = 4
# if there's a name, the role is omitted
tokens_per_name = -1
elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith("o1"):
elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith(("o1", "o3")):
tokens_per_message = 3
tokens_per_name = 1
else:
api/core/model_runtime/model_providers/openai/llm/o1-2024-12-17.yaml
+13
View File
@@ -16,6 +16,19 @@ parameter_rules:
default: 50000
min: 1
max: 50000
- name: reasoning_effort
label:
zh_Hans: 推理工作
en_US: reasoning_effort
type: string
help:
zh_Hans: 限制推理模型的推理工作
en_US: constrains effort on reasoning for reasoning models
required: false
options:
- low
- medium
- high
- name: response_format
label:
zh_Hans: 回复格式
api/core/model_runtime/model_providers/openai/llm/o1.yaml
+13
View File
@@ -17,6 +17,19 @@ parameter_rules:
default: 50000
min: 1
max: 50000
- name: reasoning_effort
label:
zh_Hans: 推理工作
en_US: reasoning_effort
type: string
help:
zh_Hans: 限制推理模型的推理工作
en_US: constrains effort on reasoning for reasoning models
required: false
options:
- low
- medium
- high
- name: response_format
label:
zh_Hans: 回复格式
api/core/model_runtime/model_providers/openai/llm/o3-mini-2025-01-31.yaml
+46
View File
@@ -0,0 +1,46 @@
model: o3-mini-2025-01-31
label:
zh_Hans: o3-mini-2025-01-31
en_US: o3-mini-2025-01-31
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 200000
parameter_rules:
- name: max_tokens
use_template: max_tokens
default: 100000
min: 1
max: 100000
- name: reasoning_effort
label:
zh_Hans: 推理工作
en_US: reasoning_effort
type: string
help:
zh_Hans: 限制推理模型的推理工作
en_US: constrains effort on reasoning for reasoning models
required: false
options:
- low
- medium
- high
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
type: string
help:
zh_Hans: 指定模型必须输出的格式
en_US: specifying the format that the model must output
required: false
options:
- text
- json_object
pricing:
input: '1.10'
output: '4.40'
unit: '0.000001'
currency: USD
api/core/model_runtime/model_providers/openai/llm/o3-mini.yaml
+46
View File
@@ -0,0 +1,46 @@
model: o3-mini
label:
zh_Hans: o3-mini
en_US: o3-mini
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 200000
parameter_rules:
- name: max_tokens
use_template: max_tokens
default: 100000
min: 1
max: 100000
- name: reasoning_effort
label:
zh_Hans: 推理工作
en_US: reasoning_effort
type: string
help:
zh_Hans: 限制推理模型的推理工作
en_US: constrains effort on reasoning for reasoning models
required: false
options:
- low
- medium
- high
- name: response_format
label:
zh_Hans: 回复格式
en_US: response_format
type: string
help:
zh_Hans: 指定模型必须输出的格式
en_US: specifying the format that the model must output
required: false
options:
- text
- json_object
pricing:
input: '1.10'
output: '4.40'
unit: '0.000001'
currency: USD
api/poetry.lock
Generated
+6 -5
View File
@@ -6562,15 +6562,15 @@ sympy = "*"
[[package]]
name = "openai"
version = "1.52.2"
version = "1.61.0"
description = "The official Python library for the openai API"
optional = false
python-versions = ">=3.7.1"
python-versions = ">=3.8"
groups = ["main"]
markers = "python_version == \"3.11\" or python_version >= \"3.12\""
files = [
{file = "openai-1.52.2-py3-none-any.whl", hash = "sha256:57e9e37bc407f39bb6ec3a27d7e8fb9728b2779936daa1fcf95df17d3edfaccc"},
{file = "openai-1.52.2.tar.gz", hash = "sha256:87b7d0f69d85f5641678d414b7ee3082363647a5c66a462ed7f3ccb59582da0d"},
{file = "openai-1.61.0-py3-none-any.whl", hash = "sha256:e8c512c0743accbdbe77f3429a1490d862f8352045de8dc81969301eb4a4f666"},
{file = "openai-1.61.0.tar.gz", hash = "sha256:216f325a24ed8578e929b0f1b3fb2052165f3b04b0461818adaa51aa29c71f8a"},
]
[package.dependencies]
@@ -6585,6 +6585,7 @@ typing-extensions = ">=4.11,<5"
[package.extras]
datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
realtime = ["websockets (>=13,<15)"]
[[package]]
name = "opencensus"
@@ -12247,4 +12248,4 @@ cffi = ["cffi (>=1.11)"]
[metadata]
lock-version = "2.1"
python-versions = ">=3.11,<3.13"
content-hash = "a8fff72e974a1bd5c28f4ae326d120410a5628ad0bc65d87adca4e943130ec8f"
content-hash = "f1d6822f5b79765cd0fc0cbca173edb4e44a9ff9f9ad615c3ecb7152fd7b683a"
api/pyproject.toml
+1 -1
View File
@@ -58,7 +58,7 @@ nomic = "~3.1.2"
novita-client = "~0.5.7"
numpy = "~1.26.4"
oci = "~2.135.1"
openai = "~1.52.0"
openai = "~1.61.0"
openpyxl = "~3.1.5"
opik = "~1.3.4"
pandas = { version = "~2.2.2", extras = ["performance", "excel"] }
docker/docker-compose.yaml
+4 -1
View File
@@ -393,7 +393,10 @@ x-shared-env: &shared-api-worker-env
services:
# API service
api:
image: langgenius/dify-api:0.15.2
build:
context: ../api
dockerfile: Dockerfile
image: langgenius/dify-api:dev
restart: always
environment:
# Use the shared environment variables.