feat: add parameter "reasoning_effort" and Openai o3-mini

api/Dockerfile

@@ -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

@@ -2,6 +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

@@ -619,9 +619,9 @@ def _chat_generate(
         # 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 @@ def _clear_illegal_prompt_messages(self, model: str, prompt_messages: list[Promp
                                 ]
                             )
 
-        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 @@ def _num_tokens_from_messages(
             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 @@ def _num_tokens_from_messages(
             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

@@ -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

@@ -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

@@ -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

@@ -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/pyproject.toml

@@ -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"] }