chore(github-actions): build docker image on 'release/0.15.2-fix1'

Signed-off-by: -LAN- <laipz8200@outlook.com>
fix(llm): deduct LLM quota after processing usage in invoke result
2025-01-27 18:58:50 +08:00 · 2025-01-27 18:57:47 +08:00
303 changed files with 2250 additions and 5669 deletions
@@ -5,8 +5,7 @@ on:
    branches:
      - "main"
      - "deploy/dev"
-      - "deploy/enterprise"
-      - "e-0154"
+      - "release/0.15.2-fix1"
  release:
    types: [published]

@@ -1,29 +0,0 @@
-name: Deploy Enterprise
-
-permissions:
-  contents: read
-
-on:
-  workflow_run:
-    workflows: ["Build and Push API & Web"]
-    branches:
-      - "deploy/enterprise"
-    types:
-      - completed
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    if: |
-      github.event.workflow_run.conclusion == 'success' &&
-      github.event.workflow_run.head_branch == 'deploy/enterprise'
-
-    steps:
-      - name: Deploy to server
-        uses: appleboy/ssh-action@v0.1.8
-        with:
-          host: ${{ secrets.ENTERPRISE_SSH_HOST }}
-          username: ${{ secrets.ENTERPRISE_SSH_USER }}
-          password: ${{ secrets.ENTERPRISE_SSH_PASSWORD }}
-          script: |
-            ${{ vars.ENTERPRISE_SSH_SCRIPT || secrets.ENTERPRISE_SSH_SCRIPT }}
@@ -1,47 +0,0 @@
-name: Build docker image
-
-on:
-  pull_request:
-    branches:
-      - "main"
-    paths:
-      - api/Dockerfile
-      - web/Dockerfile
-
-concurrency:
-  group: docker-build-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  build-docker:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        include:
-          - service_name: "api-amd64"
-            platform: linux/amd64
-            context: "api"
-          - service_name: "api-arm64"
-            platform: linux/arm64
-            context: "api"
-          - service_name: "web-amd64"
-            platform: linux/amd64
-            context: "web"
-          - service_name: "web-arm64"
-            platform: linux/arm64
-            context: "web"
-    steps:
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build Docker Image
-        uses: docker/build-push-action@v6
-        with:
-          push: false
-          context: "{{defaultContext}}:${{ matrix.context }}"
-          platforms: ${{ matrix.platform }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
@@ -25,9 +25,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="seguir en X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="seguir en LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="suivre sur X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="suivre sur LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="X(Twitter)でフォロー"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="LinkedInでフォロー"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -25,9 +25,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -22,9 +22,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="X(Twitter)'da takip et"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="LinkedIn'da takip et"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -65,6 +62,8 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)


+Özür dilerim, haklısınız. Daha anlamlı ve akıcı bir çeviri yapmaya çalışayım. İşte güncellenmiş çeviri:
+
 **3. Prompt IDE**: 
  Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz.

@@ -151,6 +150,8 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ## Dify'ı Kullanma

 - **Cloud </br>**
+İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
+- 
 Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir.

 - **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma</br>**
@@ -176,6 +177,8 @@ GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun.
 >- RAM >= 4GB

 </br>
+İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
+
 Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun:

 ```bash
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="theo dõi trên X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="theo dõi trên LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -48,18 +48,16 @@ ENV TZ=UTC

 WORKDIR /app/api

-RUN \
-    apt-get update \
-    # Install dependencies
-    && apt-get install -y --no-install-recommends \
-        # basic environment
-        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
-        # For Security
-        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
-        # install a chinese font to support the use of tools like matplotlib
-        fonts-noto-cjk \
-        # install libmagic to support the use of python-magic guess MIMETYPE
-        libmagic1 \
+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 \
+    && 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 \
+    # install a chinese font to support the use of tools like matplotlib
+    && apt-get install -y fonts-noto-cjk \
    && apt-get autoremove -y \
    && rm -rf /var/lib/apt/lists/*

@@ -78,6 +76,7 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh

+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

@@ -1,40 +1,9 @@
 from typing import Optional

-from pydantic import Field, NonNegativeInt, computed_field
+from pydantic import Field, NonNegativeInt
 from pydantic_settings import BaseSettings


-class HostedCreditConfig(BaseSettings):
-    HOSTED_MODEL_CREDIT_CONFIG: str = Field(
-        description="Model credit configuration in format 'model:credits,model:credits', e.g., 'gpt-4:20,gpt-4o:10'",
-        default="",
-    )
-
-    def get_model_credits(self, model_name: str) -> int:
-        """
-        Get credit value for a specific model name.
-        Returns 1 if model is not found in configuration (default credit).
-
-        :param model_name: The name of the model to search for
-        :return: The credit value for the model
-        """
-        if not self.HOSTED_MODEL_CREDIT_CONFIG:
-            return 1
-
-        try:
-            credit_map = dict(
-                item.strip().split(":", 1) for item in self.HOSTED_MODEL_CREDIT_CONFIG.split(",") if ":" in item
-            )
-
-            # Search for matching model pattern
-            for pattern, credit in credit_map.items():
-                if pattern.strip() == model_name:
-                    return int(credit)
-            return 1  # Default quota if no match found
-        except (ValueError, AttributeError):
-            return 1  # Return default quota if parsing fails
-
-
 class HostedOpenAiConfig(BaseSettings):
    """
    Configuration for hosted OpenAI service
@@ -233,7 +202,5 @@ class HostedServiceConfig(
    HostedZhipuAIConfig,
    # moderation
    HostedModerationConfig,
-    # credit config
-    HostedCreditConfig,
 ):
    pass
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.15.4",
+        default="0.15.2",
    )

    COMMIT_SHA: str = Field(
@@ -1,32 +1,12 @@
 import mimetypes
 import os
-import platform
 import re
 import urllib.parse
-import warnings
 from collections.abc import Mapping
 from typing import Any
 from uuid import uuid4

 import httpx
-
-try:
-    import magic
-except ImportError:
-    if platform.system() == "Windows":
-        warnings.warn(
-            "To use python-magic guess MIMETYPE, you need to run `pip install python-magic-bin`", stacklevel=2
-        )
-    elif platform.system() == "Darwin":
-        warnings.warn("To use python-magic guess MIMETYPE, you need to run `brew install libmagic`", stacklevel=2)
-    elif platform.system() == "Linux":
-        warnings.warn(
-            "To use python-magic guess MIMETYPE, you need to run `sudo apt-get install libmagic1`", stacklevel=2
-        )
-    else:
-        warnings.warn("To use python-magic guess MIMETYPE, you need to install `libmagic`", stacklevel=2)
-    magic = None  # type: ignore
-
 from pydantic import BaseModel

 from configs import dify_config
@@ -67,13 +47,6 @@ def guess_file_info_from_response(response: httpx.Response):
        # If guessing fails, use Content-Type from response headers
        mimetype = response.headers.get("Content-Type", "application/octet-stream")

-    # Use python-magic to guess MIME type if still unknown or generic
-    if mimetype == "application/octet-stream" and magic is not None:
-        try:
-            mimetype = magic.from_buffer(response.content[:1024], mime=True)
-        except magic.MagicException:
-            pass
-
    extension = os.path.splitext(filename)[1]

    # Ensure filename has an extension
@@ -620,6 +620,7 @@ class DatasetRetrievalSettingApi(Resource):
        match vector_type:
            case (
                VectorType.RELYT
+                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
                | VectorType.TENCENT
@@ -50,7 +50,7 @@ class MessageListApi(InstalledAppResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -39,17 +39,6 @@ def only_edition_cloud(view):
    return decorated


-def only_enterprise_edition(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        if not dify_config.ENTERPRISE_ENABLED:
-            abort(404)
-
-        return view(*args, **kwargs)
-
-    return decorated
-
-
 def only_edition_self_hosted(view):
    @wraps(view)
    def decorated(*args, **kwargs):
@@ -1,5 +1,3 @@
-import json
-
 from flask_restful import Resource, reqparse  # type: ignore

 from controllers.console.wraps import setup_required
@@ -31,34 +29,4 @@ class EnterpriseWorkspace(Resource):
        return {"message": "enterprise workspace created."}


-class EnterpriseWorkspaceNoOwnerEmail(Resource):
-    @setup_required
-    @inner_api_only
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("name", type=str, required=True, location="json")
-        args = parser.parse_args()
-
-        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
-
-        tenant_was_created.send(tenant)
-
-        resp = {
-            "id": tenant.id,
-            "name": tenant.name,
-            "encrypt_public_key": tenant.encrypt_public_key,
-            "plan": tenant.plan,
-            "status": tenant.status,
-            "custom_config": json.loads(tenant.custom_config) if tenant.custom_config else {},
-            "created_at": tenant.created_at.isoformat() if tenant.created_at else None,
-            "updated_at": tenant.updated_at.isoformat() if tenant.updated_at else None,
-        }
-
-        return {
-            "message": "enterprise workspace created.",
-            "tenant": resp,
-        }
-
-
 api.add_resource(EnterpriseWorkspace, "/enterprise/workspace")
-api.add_resource(EnterpriseWorkspaceNoOwnerEmail, "/enterprise/workspace/ownerless")
@@ -18,7 +18,6 @@ from controllers.service_api.app.error import (
 from controllers.service_api.dataset.error import (
    ArchivedDocumentImmutableError,
    DocumentIndexingError,
-    InvalidMetadataError,
 )
 from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
@@ -51,9 +50,6 @@ class DocumentAddByTextApi(DatasetApiResource):
            "indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
        )
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
-
        args = parser.parse_args()
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -65,28 +61,6 @@ class DocumentAddByTextApi(DatasetApiResource):
        if not dataset.indexing_technique and not args["indexing_technique"]:
            raise ValueError("indexing_technique is required.")

-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        text = args.get("text")
        name = args.get("name")
        if text is None or name is None:
@@ -133,8 +107,6 @@ class DocumentUpdateByTextApi(DatasetApiResource):
            "doc_language", type=str, default="English", required=False, nullable=False, location="json"
        )
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
        args = parser.parse_args()
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -143,32 +115,6 @@ class DocumentUpdateByTextApi(DatasetApiResource):
        if not dataset:
            raise ValueError("Dataset is not exist.")

-        # indexing_technique is already set in dataset since this is an update
-        args["indexing_technique"] = dataset.indexing_technique
-
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        if args["text"]:
            text = args.get("text")
            name = args.get("name")
@@ -215,30 +161,6 @@ class DocumentAddByFileApi(DatasetApiResource):
            args["doc_form"] = "text_model"
        if "doc_language" not in args:
            args["doc_language"] = "English"
-
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        # get dataset info
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -306,29 +228,6 @@ class DocumentUpdateByFileApi(DatasetApiResource):
        if "doc_language" not in args:
            args["doc_language"] = "English"

-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        # get dataset info
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -91,7 +91,7 @@ class MessageListApi(WebApiResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -202,7 +202,7 @@ class AgentChatAppRunner(AppRunner):
        # change function call strategy based on LLM model
        llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
        model_schema = llm_model.get_model_schema(model_instance.model, model_instance.credentials)
-        if not model_schema:
+        if not model_schema or not model_schema.features:
            raise ValueError("Model schema not found")

        if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
@@ -11,6 +11,15 @@ from configs import dify_config

 SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES

+proxy_mounts = (
+    {
+        "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
+        "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
+    }
+    if dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL
+    else None
+)
+
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]

@@ -42,11 +51,7 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
            if dify_config.SSRF_PROXY_ALL_URL:
                with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL) as client:
                    response = client.request(method=method, url=url, **kwargs)
-            elif dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
-                proxy_mounts = {
-                    "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
-                    "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
-                }
+            elif proxy_mounts:
                with httpx.Client(mounts=proxy_mounts) as client:
                    response = client.request(method=method, url=url, **kwargs)
            else:
@@ -1,4 +1,4 @@
-from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
    AssistantPromptMessage,
    AudioPromptMessageContent,
@@ -23,7 +23,6 @@ __all__ = [
    "AudioPromptMessageContent",
    "DocumentPromptMessageContent",
    "ImagePromptMessageContent",
-    "LLMMode",
    "LLMResult",
    "LLMResultChunk",
    "LLMResultChunkDelta",
@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import StrEnum
+from enum import Enum
 from typing import Optional

 from pydantic import BaseModel
@@ -8,7 +8,7 @@ from core.model_runtime.entities.message_entities import AssistantPromptMessage,
 from core.model_runtime.entities.model_entities import ModelUsage, PriceInfo


-class LLMMode(StrEnum):
+class LLMMode(Enum):
    """
    Enum class for large language model mode.
    """
@@ -221,12 +221,13 @@ class AIModel(ABC):
        :param credentials: model credentials
        :return: model schema
        """
-        # Try to get model schema from predefined models
-        for predefined_model in self.predefined_models():
-            if model == predefined_model.model:
-                return predefined_model
+        # get predefined models (predefined_models)
+        models = self.predefined_models()
+
+        model_map = {model.model: model for model in models}
+        if model in model_map:
+            return model_map[model]

-        # Try to get model schema from credentials
        if credentials:
            model_schema = self.get_customizable_model_schema_from_credentials(model, credentials)
            if model_schema:
@@ -30,11 +30,6 @@ from core.model_runtime.model_providers.__base.ai_model import AIModel

 logger = logging.getLogger(__name__)

-HTML_THINKING_TAG = (
-    '<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> '
-    "<summary> Thinking... </summary>"
-)
-

 class LargeLanguageModel(AIModel):
    """
@@ -405,40 +400,6 @@ if you are not sure about the structure.
                    ),
                )

-    def _wrap_thinking_by_reasoning_content(self, delta: dict, is_reasoning: bool) -> tuple[str, bool]:
-        """
-        If the reasoning response is from delta.get("reasoning_content"), we wrap
-        it with HTML details tag.
-
-        :param delta: delta dictionary from LLM streaming response
-        :param is_reasoning: is reasoning
-        :return: tuple of (processed_content, is_reasoning)
-        """
-
-        content = delta.get("content") or ""
-        reasoning_content = delta.get("reasoning_content")
-
-        if reasoning_content:
-            if not is_reasoning:
-                content = HTML_THINKING_TAG + reasoning_content
-                is_reasoning = True
-            else:
-                content = reasoning_content
-        elif is_reasoning:
-            content = "</details>" + content
-            is_reasoning = False
-        return content, is_reasoning
-
-    def _wrap_thinking_by_tag(self, content: str) -> str:
-        """
-        if the reasoning response is a <think>...</think> block from delta.get("content"),
-        we replace <think> to <detail>.
-
-        :param content: delta.get("content")
-        :return: processed_content
-        """
-        return content.replace("<think>", HTML_THINKING_TAG).replace("</think>", "</details>")
-
    def _invoke_result_generator(
        self,
        model: str,
@@ -1,5 +1,4 @@
 - openai
- deepseek
 - anthropic
 - azure_openai
 - google
@@ -33,6 +32,7 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
+- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud
@@ -51,40 +51,6 @@ model_credential_schema:
      show_on:
        - variable: __model_type
          value: llm
-    - variable: mode
-      show_on:
-        - variable: __model_type
-          value: llm
-      label:
-        en_US: Completion mode
-      type: select
-      required: false
-      default: chat
-      placeholder:
-        zh_Hans: 选择对话类型
-        en_US: Select completion mode
-      options:
-        - value: completion
-          label:
-            en_US: Completion
-            zh_Hans: 补全
-        - value: chat
-          label:
-            en_US: Chat
-            zh_Hans: 对话
-    - variable: context_size
-      label:
-        zh_Hans: 模型上下文长度
-        en_US: Model context size
-      required: true
-      show_on:
-        - variable: __model_type
-          value: llm
-      type: text-input
-      default: "4096"
-      placeholder:
-        zh_Hans: 在此输入您的模型上下文长度
-        en_US: Enter your Model context size
    - variable: jwt_token
      required: true
      label:
@@ -1,9 +1,9 @@
 import logging
-from collections.abc import Generator, Sequence
+from collections.abc import Generator
 from typing import Any, Optional, Union

 from azure.ai.inference import ChatCompletionsClient
-from azure.ai.inference.models import StreamingChatCompletionsUpdate, SystemMessage, UserMessage
+from azure.ai.inference.models import StreamingChatCompletionsUpdate
 from azure.core.credentials import AzureKeyCredential
 from azure.core.exceptions import (
    ClientAuthenticationError,
@@ -20,7 +20,7 @@ from azure.core.exceptions import (
 )

 from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
    AssistantPromptMessage,
    PromptMessage,
@@ -30,7 +30,6 @@ from core.model_runtime.entities.model_entities import (
    AIModelEntity,
    FetchFrom,
    I18nObject,
-    ModelPropertyKey,
    ModelType,
    ParameterRule,
    ParameterType,
@@ -61,10 +60,10 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        self,
        model: str,
        credentials: dict,
-        prompt_messages: Sequence[PromptMessage],
+        prompt_messages: list[PromptMessage],
        model_parameters: dict,
-        tools: Optional[Sequence[PromptMessageTool]] = None,
-        stop: Optional[Sequence[str]] = None,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[list[str]] = None,
        stream: bool = True,
        user: Optional[str] = None,
    ) -> Union[LLMResult, Generator]:
@@ -83,8 +82,8 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        """

        if not self.client:
-            endpoint = str(credentials.get("endpoint"))
-            api_key = str(credentials.get("api_key"))
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("api_key")
            self.client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))

        messages = [{"role": msg.role.value, "content": msg.content} for msg in prompt_messages]
@@ -95,7 +94,6 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            "temperature": model_parameters.get("temperature", 0),
            "top_p": model_parameters.get("top_p", 1),
            "stream": stream,
-            "model": model,
        }

        if stop:
@@ -257,16 +255,10 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        :return:
        """
        try:
-            endpoint = str(credentials.get("endpoint"))
-            api_key = str(credentials.get("api_key"))
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("api_key")
            client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))
-            client.complete(
-                messages=[
-                    SystemMessage(content="I say 'ping', you say 'pong'"),
-                    UserMessage(content="ping"),
-                ],
-                model=model,
-            )
+            client.get_model_info()
        except Exception as ex:
            raise CredentialsValidateFailedError(str(ex))

@@ -335,10 +327,7 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
            model_type=ModelType.LLM,
            features=[],
-            model_properties={
-                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", "4096")),
-                ModelPropertyKey.MODE: credentials.get("mode", LLMMode.CHAT),
-            },
+            model_properties={},
            parameter_rules=rules,
        )

@@ -53,9 +53,6 @@ model_credential_schema:
      type: select
      required: true
      options:
-        - label:
-            en_US: 2024-12-01-preview
-          value: 2024-12-01-preview
        - label:
            en_US: 2024-10-01-preview
          value: 2024-10-01-preview
@@ -138,18 +135,6 @@ model_credential_schema:
          show_on:
            - variable: __model_type
              value: llm
-        - label:
-            en_US: o3-mini
-          value: o3-mini
-          show_on:
-            - variable: __model_type
-              value: llm
-        - label:
-            en_US: o3-mini-2025-01-31
-          value: o3-mini-2025-01-31
-          show_on:
-            - variable: __model_type
-              value: llm
        - label:
            en_US: o1-preview
          value: o1-preview
@@ -44,7 +44,6 @@ provider_credential_schema:
      label:
        en_US: AWS Region
        zh_Hans: AWS 地区
-        ja_JP: AWS リージョン
      type: select
      default: us-east-1
      options:
@@ -52,86 +51,62 @@ provider_credential_schema:
          label:
            en_US: US East (N. Virginia)
            zh_Hans: 美国东部 (弗吉尼亚北部)
-            ja_JP: 米国 (バージニア北部)
        - value: us-east-2
          label:
            en_US: US East (Ohio)
-            zh_Hans: 美国东部 (俄亥俄)
-            ja_JP: 米国 (オハイオ)
+            zh_Hans: 美国东部 (弗吉尼亚北部)
        - value: us-west-2
          label:
            en_US: US West (Oregon)
            zh_Hans: 美国西部 (俄勒冈州)
-            ja_JP: 米国 (オレゴン)
        - value: ap-south-1
          label:
            en_US: Asia Pacific (Mumbai)
            zh_Hans: 亚太地区（孟买）
-            ja_JP: アジアパシフィック (ムンバイ)
        - value: ap-southeast-1
          label:
            en_US: Asia Pacific (Singapore)
            zh_Hans: 亚太地区 (新加坡)
-            ja_JP: アジアパシフィック (シンガポール)
        - value: ap-southeast-2
          label:
            en_US: Asia Pacific (Sydney)
            zh_Hans: 亚太地区 (悉尼)
-            ja_JP: アジアパシフィック (シドニー)
        - value: ap-northeast-1
          label:
            en_US: Asia Pacific (Tokyo)
            zh_Hans: 亚太地区 (东京)
-            ja_JP: アジアパシフィック (東京)
        - value: ap-northeast-2
          label:
            en_US: Asia Pacific (Seoul)
            zh_Hans: 亚太地区（首尔）
-            ja_JP: アジアパシフィック (ソウル)
        - value: ca-central-1
          label:
            en_US: Canada (Central)
            zh_Hans: 加拿大（中部）
-            ja_JP: カナダ (中部)
        - value: eu-central-1
          label:
            en_US: Europe (Frankfurt)
            zh_Hans: 欧洲 (法兰克福)
-            ja_JP: 欧州 (フランクフルト)
        - value: eu-west-1
          label:
            en_US: Europe (Ireland)
            zh_Hans: 欧洲（爱尔兰）
-            ja_JP: 欧州 (アイルランド)
        - value: eu-west-2
          label:
            en_US: Europe (London)
            zh_Hans: 欧洲西部 (伦敦)
-            ja_JP: 欧州 (ロンドン)
        - value: eu-west-3
          label:
            en_US: Europe (Paris)
            zh_Hans: 欧洲（巴黎）
-            ja_JP: 欧州 (パリ)
        - value: sa-east-1
          label:
            en_US: South America (São Paulo)
            zh_Hans: 南美洲（圣保罗）
-            ja_JP: 南米 (サンパウロ)
        - value: us-gov-west-1
          label:
            en_US: AWS GovCloud (US-West)
            zh_Hans: AWS GovCloud (US-West)
-            ja_JP: AWS GovCloud (米国西部)
-    - variable: bedrock_endpoint_url
-      label:
-        zh_Hans: Bedrock Endpoint URL
-        en_US: Bedrock Endpoint URL
-      type: text-input
-      required: false
-      placeholder:
-        zh_Hans: 在此输入您的 Bedrock Endpoint URL, 如：https://123456.cloudfront.net
-        en_US: Enter your Bedrock Endpoint URL, e.g. https://123456.cloudfront.net
    - variable: model_for_validation
      required: false
      label:
@@ -13,7 +13,6 @@ def get_bedrock_client(service_name: str, credentials: Mapping[str, str]):
    client_config = Config(region_name=region_name)
    aws_access_key_id = credentials.get("aws_access_key_id")
    aws_secret_access_key = credentials.get("aws_secret_access_key")
-    bedrock_endpoint_url = credentials.get("bedrock_endpoint_url")

    if aws_access_key_id and aws_secret_access_key:
        # use aksk to call bedrock
@@ -22,7 +21,6 @@ def get_bedrock_client(service_name: str, credentials: Mapping[str, str]):
            config=client_config,
            aws_access_key_id=aws_access_key_id,
            aws_secret_access_key=aws_secret_access_key,
-            **({"endpoint_url": bedrock_endpoint_url} if bedrock_endpoint_url else {}),
        )
    else:
        # use iam without aksk to call
@@ -677,17 +677,16 @@ class CohereLargeLanguageModel(LargeLanguageModel):

        :return: model schema
        """
-        mode = credentials.get("mode")
-        base_model_schema = None
-        for predefined_model in self.predefined_models():
-            if (
-                mode == "chat" and predefined_model.model == "command-light-chat"
-            ) or predefined_model.model == "command-light":
-                base_model_schema = predefined_model
-                break
+        # get model schema
+        models = self.predefined_models()
+        model_map = {model.model: model for model in models}

-        if not base_model_schema:
-            raise ValueError("Model not found")
+        mode = credentials.get("mode")
+
+        if mode == "chat":
+            base_model_schema = model_map["command-light-chat"]
+        else:
+            base_model_schema = model_map["command-light"]

        base_model_schema = cast(AIModelEntity, base_model_schema)

@@ -1,6 +1,4 @@
- gemini-2.0-flash-001
 - gemini-2.0-flash-exp
- gemini-2.0-pro-exp-02-05
 - gemini-2.0-flash-thinking-exp-1219
 - gemini-2.0-flash-thinking-exp-01-21
 - gemini-1.5-pro
@@ -1,41 +0,0 @@
-model: gemini-2.0-flash-001
-label:
-  en_US: Gemini 2.0 Flash 001
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 1048576
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: gemini-2.0-pro-exp-02-05
-label:
-  en_US: Gemini 2.0 pro exp 02-05
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 1048576
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,4 +1,3 @@
- deepseek-r1-distill-llama-70b
 - llama-3.1-405b-reasoning
 - llama-3.3-70b-versatile
 - llama-3.1-70b-versatile
@@ -1,36 +0,0 @@
-model: deepseek-r1-distill-llama-70b
-label:
-  en_US: DeepSeek R1 Distill Llama 70b
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 8192
-  - 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: '3.00'
-  output: '3.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,11 +1,19 @@
-<svg width="88" height="24" viewBox="0 0 88 24" fill="none" xmlns="http://www.w3.org/2000/svg">
-<g clip-path="url(#clip0_1923_1287)">
-<path d="M24 18.8323V18.8326H14.3246L9.16716 13.6751V18.8326H0V18.8314L9.16716 9.66422V4H9.16774L24 18.8323Z" fill="black"/>
-</g>
-<path fill-rule="evenodd" clip-rule="evenodd" d="M73.2505 16.8061H76.5869V18.9145H73.9391C72.0857 18.9145 70.9202 17.8952 70.9202 15.9977V10.3921H69.0316V8.26609H70.9202L71.4677 5.47209H73.2329V8.26609H76.5869V10.3921H73.2505V16.8061ZM33.8133 4.85699L38.6679 15.681H38.809V4.85699H41.3333V18.9145H37.52L32.6654 8.09046H32.5243V18.9145H30V4.85699H33.8133ZM47.812 19.1254C44.7225 19.1254 42.7457 16.9641 42.7457 13.6079C42.7457 10.2517 44.6873 8.05518 47.812 8.05518C50.9367 8.05518 52.8429 10.1635 52.8429 13.6079C52.8429 17.0523 50.9014 19.1254 47.812 19.1254ZM47.812 17.017C49.1891 17.017 50.3363 16.5423 50.3715 15.1894V12.0265C50.3715 10.6383 49.2068 10.1635 47.812 10.1635C46.4172 10.1635 45.2171 10.6383 45.2171 12.0265V15.1894C45.2524 16.5599 46.4348 17.017 47.812 17.017ZM55.5444 8.24846L58.2979 16.6826H58.439L61.1926 8.24846H63.7346L59.9389 18.8968H56.7966L53.0186 8.24846H55.5429H55.5444ZM65.0419 8.26609H67.3722V18.9145H65.0419V8.26609ZM64.9001 4.85699H67.5126V6.86027H64.9001V4.85699ZM82.3064 19.143C79.4639 19.143 77.6458 16.9817 77.6458 13.6079C77.6458 10.2341 79.4286 8.07282 82.3064 8.07282C83.6483 8.07282 84.7425 8.59973 85.3958 9.58373H85.5369L85.9962 8.26609H87.7614V18.9145H85.9962L85.5369 17.6314H85.3958C84.6896 18.5625 83.5072 19.1423 82.3064 19.1423V19.143ZM82.7826 17.017C84.1774 17.017 85.3951 16.5776 85.4304 15.1894V12.0265C85.4304 10.603 84.159 10.1988 82.7297 10.1988C81.3004 10.1988 80.1172 10.6383 80.1172 12.0265V15.1894C80.1525 16.5952 81.3709 17.017 82.7826 17.017Z" fill="black"/>
+<svg width="162" height="36" viewBox="0 0 162 36" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="white"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="url(#paint0_linear_1473_71)"/>
+<path d="M55.9397 27.8804H59.0566V19.0803C59.0566 14.9105 56.381 12.7172 52.8228 12.7172C51.0023 12.7172 49.3197 13.4483 48.2991 14.6668V12.9609H45.1546V27.8804H48.2991V19.5406C48.2991 16.8059 49.8162 15.3978 52.1332 15.3978C54.4226 15.3978 55.9397 16.8059 55.9397 19.5406V27.8804Z" fill="#11101A"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M69.7881 12.7172C74.1187 12.7172 77.539 15.7228 77.539 20.4071C77.539 25.0915 74.0083 28.1241 69.6502 28.1241C65.3196 28.1241 62.0372 25.0915 62.0372 20.4071C62.0372 15.7228 65.4575 12.7172 69.7881 12.7172ZM69.7342 15.3979C67.362 15.3979 65.2381 17.0225 65.2381 20.4071C65.2381 23.7918 67.2793 25.4435 69.6514 25.4435C71.996 25.4435 74.313 23.7918 74.313 20.4071C74.313 17.0225 72.0788 15.3979 69.7342 15.3979Z" fill="#11101A"/>
+<path d="M78.861 12.9609L84.6259 27.8804H88.3772L94.1697 12.9609H90.8321L86.5291 25.1185L82.2261 12.9609H78.861Z" fill="#11101A"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M100.13 9.00761C100.13 10.1178 99.2477 10.9842 98.1443 10.9842C97.0134 10.9842 96.1308 10.1178 96.1308 9.00761C96.1308 7.89745 97.0134 7.03098 98.1443 7.03098C99.2477 7.03098 100.13 7.89745 100.13 9.00761ZM99.6882 27.8804H96.5437V12.9609H99.6882V27.8804Z" fill="#11101A"/>
+<path d="M104.322 23.7376C104.322 26.7702 106.004 27.8804 108.708 27.8804H111.19V25.308H109.259C107.935 25.308 107.494 24.8477 107.494 23.7376V15.479H111.19V12.9609H107.494V9.25128H104.322V12.9609H102.529V15.479H104.322V23.7376Z" fill="#11101A"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M120.154 28.1241C116.209 28.1241 113.037 24.9561 113.037 20.353C113.037 15.7498 116.209 12.7172 120.209 12.7172C122.774 12.7172 124.539 13.9086 125.477 15.1271V12.9609H128.649V27.8804H125.477V25.6601C124.512 26.9327 122.691 28.1241 120.154 28.1241ZM120.87 25.4435C123.242 25.4435 125.476 23.6293 125.476 20.4071C125.476 17.212 123.242 15.3979 120.87 15.3979C118.526 15.3979 116.264 17.1308 116.264 20.353C116.264 23.5752 118.526 25.4435 120.87 25.4435Z" fill="#11101A"/>
+<path d="M136.043 26.0933C136.043 24.9832 135.16 24.1167 134.057 24.1167C132.926 24.1167 132.043 24.9832 132.043 26.0933C132.043 27.2035 132.926 28.07 134.057 28.07C135.16 28.07 136.043 27.2035 136.043 26.0933Z" fill="#11101A"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M145.502 28.1241C141.558 28.1241 138.386 24.9561 138.386 20.353C138.386 15.7498 141.558 12.7172 145.557 12.7172C148.123 12.7172 149.888 13.9086 150.826 15.1271V12.9609H153.998V27.8804H150.826V25.6601C149.86 26.9327 148.04 28.1241 145.502 28.1241ZM146.219 25.4435C148.591 25.4435 150.825 23.6293 150.825 20.4071C150.825 17.212 148.591 15.3979 146.219 15.3979C143.874 15.3979 141.612 17.1308 141.612 20.353C141.612 23.5752 143.874 25.4435 146.219 25.4435Z" fill="#11101A"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M161.722 9.00761C161.722 10.1178 160.84 10.9842 159.736 10.9842C158.605 10.9842 157.723 10.1178 157.723 9.00761C157.723 7.89745 158.605 7.03098 159.736 7.03098C160.84 7.03098 161.722 7.89745 161.722 9.00761ZM161.28 27.8804H158.136V12.9609H161.28V27.8804Z" fill="#11101A"/>
 <defs>
-<clipPath id="clip0_1923_1287">
-<rect width="24" height="14.8326" fill="white" transform="translate(0 4)"/>
-</clipPath>
+<linearGradient id="paint0_linear_1473_71" x1="31" y1="-2" x2="0.975591" y2="14.2625" gradientUnits="userSpaceOnUse">
+<stop stop-color="#2622FF"/>
+<stop offset="1" stop-color="#A717FF"/>
+</linearGradient>
 </defs>
 </svg>
@@ -1,3 +1,10 @@
-<svg width="24" height="15" viewBox="0 0 24 15" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M24 14.8323V14.8326H14.3246L9.16716 9.67507V14.8326H0V14.8314L9.16716 5.66422V0H9.16774L24 14.8323Z" fill="black"/>
+<svg width="32" height="36" viewBox="0 0 32 36" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="white"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M2 0C0.895431 0 0 0.895432 0 2V29.1891C0 30.2937 0.895433 31.1891 2 31.1891H5.51171L16.0608 35.1377C16.7145 35.3824 17.4114 34.8991 17.4114 34.2012V11.3669C17.4114 10.533 16.894 9.78665 16.1131 9.49405L5.51171 5.52152H25.58V31.1891H29.0917C30.1963 31.1891 31.0917 30.2937 31.0917 29.1891V2C31.0917 0.895431 30.1963 0 29.0917 0H2ZM14.6022 23.7351C15.0558 23.956 15.4239 23.6812 15.4239 23.1185C15.4239 22.5557 15.0558 21.9204 14.6022 21.6995C14.1486 21.4775 13.7804 21.7545 13.7804 22.3161C13.7804 22.8777 14.1486 23.513 14.6022 23.7351Z" fill="url(#paint0_linear_1473_97)"/>
+<defs>
+<linearGradient id="paint0_linear_1473_97" x1="31" y1="-2" x2="0.975591" y2="14.2625" gradientUnits="userSpaceOnUse">
+<stop stop-color="#2622FF"/>
+<stop offset="1" stop-color="#A717FF"/>
+</linearGradient>
+</defs>
 </svg>
@@ -1,41 +0,0 @@
-model: Sao10K/L3-8B-Stheno-v3.2
-label:
-  zh_Hans: L3 8B Stheno V3.2
-  en_US: L3 8B Stheno V3.2
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0005'
-  output: '0.0005'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
-model: qwen/qwen-2-vl-72b-instruct
+model: Nous-Hermes-2-Mixtral-8x7B-DPO
 label:
-  zh_Hans: Qwen 2 VL 72B Instruct
-  en_US: Qwen 2 VL 72B Instruct
+  zh_Hans: Nous-Hermes-2-Mixtral-8x7B-DPO
+  en_US: Nous-Hermes-2-Mixtral-8x7B-DPO
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0045'
-  output: '0.0045'
+  input: '0.0027'
+  output: '0.0027'
  unit: '0.0001'
  currency: USD
@@ -1,41 +0,0 @@
-# Deepseek Models
- deepseek/deepseek-r1
- deepseek/deepseek_v3
-
-# LLaMA Models
- meta-llama/llama-3.3-70b-instruct
- meta-llama/llama-3.2-11b-vision-instruct
- meta-llama/llama-3.2-3b-instruct
- meta-llama/llama-3.2-1b-instruct
- meta-llama/llama-3.1-70b-instruct
- meta-llama/llama-3.1-8b-instruct
- meta-llama/llama-3.1-8b-instruct-max
- meta-llama/llama-3.1-8b-instruct-bf16
- meta-llama/llama-3-70b-instruct
- meta-llama/llama-3-8b-instruct
-
-# Mistral Models
- mistralai/mistral-nemo
- mistralai/mistral-7b-instruct
-
-# Qwen Models
- qwen/qwen-2.5-72b-instruct
- qwen/qwen-2-72b-instruct
- qwen/qwen-2-vl-72b-instruct
- qwen/qwen-2-7b-instruct
-
-# Other Models
- sao10k/L3-8B-Stheno-v3.2
- sao10k/l3-70b-euryale-v2.1
- sao10k/l31-70b-euryale-v2.2
- sao10k/l3-8b-lunaris
- jondurbin/airoboros-l2-70b
- cognitivecomputations/dolphin-mixtral-8x22b
- google/gemma-2-9b-it
- nousresearch/hermes-2-pro-llama-3-8b
- sophosympatheia/midnight-rose-70b
- gryphe/mythomax-l2-13b
- nousresearch/nous-hermes-llama2-13b
- openchat/openchat-7b
- teknium/openhermes-2.5-mistral-7b
- microsoft/wizardlm-2-8x22b
@@ -1,7 +1,7 @@
 model: jondurbin/airoboros-l2-70b
 label:
-  zh_Hans: Airoboros L2 70B
-  en_US: Airoboros L2 70B
+  zh_Hans: jondurbin/airoboros-l2-70b
+  en_US: jondurbin/airoboros-l2-70b
 model_type: llm
 features:
  - agent-thought
@@ -1,41 +0,0 @@
-model: deepseek/deepseek-r1
-label:
-  zh_Hans: DeepSeek R1
-  en_US: DeepSeek R1
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 64000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.04'
-  output: '0.04'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: deepseek/deepseek_v3
-label:
-  zh_Hans: DeepSeek V3
-  en_US: DeepSeek V3
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 64000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0089'
-  output: '0.0089'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
 model: cognitivecomputations/dolphin-mixtral-8x22b
 label:
-  zh_Hans: Dolphin Mixtral 8x22B
-  en_US: Dolphin Mixtral 8x22B
+  zh_Hans: cognitivecomputations/dolphin-mixtral-8x22b
+  en_US: cognitivecomputations/dolphin-mixtral-8x22b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: google/gemma-2-9b-it
 label:
-  zh_Hans: Gemma 2 9B
-  en_US: Gemma 2 9B
+  zh_Hans: google/gemma-2-9b-it
+  en_US: google/gemma-2-9b-it
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: nousresearch/hermes-2-pro-llama-3-8b
 label:
-  zh_Hans: Hermes 2 Pro Llama 3 8B
-  en_US: Hermes 2 Pro Llama 3 8B
+  zh_Hans: nousresearch/hermes-2-pro-llama-3-8b
+  en_US: nousresearch/hermes-2-pro-llama-3-8b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sao10k/l3-70b-euryale-v2.1
 label:
-  zh_Hans: "L3 70B Euryale V2.1\t"
-  en_US: "L3 70B Euryale V2.1\t"
+  zh_Hans: sao10k/l3-70b-euryale-v2.1
+  en_US: sao10k/l3-70b-euryale-v2.1
 model_type: llm
 features:
  - agent-thought
@@ -1,41 +0,0 @@
-model: sao10k/l3-8b-lunaris
-label:
-  zh_Hans: "Sao10k L3 8B Lunaris"
-  en_US: "Sao10k L3 8B Lunaris"
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0005'
-  output: '0.0005'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: sao10k/l31-70b-euryale-v2.2
-label:
-  zh_Hans: L31 70B Euryale V2.2
-  en_US: L31 70B Euryale V2.2
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 16000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0148'
-  output: '0.0148'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-70b-instruct
 label:
-  zh_Hans: Llama3 70b Instruct
-  en_US: Llama3 70b Instruct
+  zh_Hans: meta-llama/llama-3-70b-instruct
+  en_US: meta-llama/llama-3-70b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-8b-instruct
 label:
-  zh_Hans: Llama 3 8B Instruct
-  en_US: Llama 3 8B Instruct
+  zh_Hans: meta-llama/llama-3-8b-instruct
+  en_US: meta-llama/llama-3-8b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0004'
-  output: '0.0004'
+  input: '0.00063'
+  output: '0.00063'
  unit: '0.0001'
  currency: USD
@@ -1,7 +1,7 @@
-model: meta-llama/llama-3.2-3b-instruct
+model: meta-llama/llama-3.1-405b-instruct
 label:
-  zh_Hans: Llama 3.2 3B Instruct
-  en_US: Llama 3.2 3B Instruct
+  zh_Hans: meta-llama/llama-3.1-405b-instruct
+  en_US: meta-llama/llama-3.1-405b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0003'
-  output: '0.0005'
+  input: '0.03'
+  output: '0.05'
  unit: '0.0001'
  currency: USD
@@ -1,13 +1,13 @@
 model: meta-llama/llama-3.1-70b-instruct
 label:
-  zh_Hans: Llama 3.1 70B Instruct
-  en_US: Llama 3.1 70B Instruct
+  zh_Hans: meta-llama/llama-3.1-70b-instruct
+  en_US: meta-llama/llama-3.1-70b-instruct
 model_type: llm
 features:
  - agent-thought
 model_properties:
  mode: chat
-  context_size: 32768
+  context_size: 8192
 parameter_rules:
  - name: temperature
    use_template: temperature
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0034'
-  output: '0.0039'
+  input: '0.0055'
+  output: '0.0076'
  unit: '0.0001'
  currency: USD
@@ -1,41 +0,0 @@
-model: meta-llama/llama-3.1-8b-instruct-bf16
-label:
-  zh_Hans: Llama 3.1 8B Instruct BF16
-  en_US: Llama 3.1 8B Instruct BF16
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0006'
-  output: '0.0006'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: meta-llama/llama-3.1-8b-instruct-max
-label:
-  zh_Hans: "Llama3.1 8B Instruct Max\t"
-  en_US: "Llama3.1 8B Instruct Max\t"
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 16384
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0005'
-  output: '0.0005'
-  unit: '0.0001'
-  currency: USD
@@ -1,13 +1,13 @@
 model: meta-llama/llama-3.1-8b-instruct
 label:
-  zh_Hans: Llama 3.1 8B Instruct
-  en_US: Llama 3.1 8B Instruct
+  zh_Hans: meta-llama/llama-3.1-8b-instruct
+  en_US: meta-llama/llama-3.1-8b-instruct
 model_type: llm
 features:
  - agent-thought
 model_properties:
  mode: chat
-  context_size: 16384
+  context_size: 8192
 parameter_rules:
  - name: temperature
    use_template: temperature
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0005'
-  output: '0.0005'
+  input: '0.001'
+  output: '0.001'
  unit: '0.0001'
  currency: USD
@@ -1,41 +0,0 @@
-model: meta-llama/llama-3.2-11b-vision-instruct
-label:
-  zh_Hans: "Llama 3.2 11B Vision Instruct\t"
-  en_US: "Llama 3.2 11B Vision Instruct\t"
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32768
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0006'
-  output: '0.0006'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: meta-llama/llama-3.2-1b-instruct
-label:
-  zh_Hans: "Llama 3.2 1B Instruct\t"
-  en_US: "Llama 3.2 1B Instruct\t"
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0002'
-  output: '0.0002'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: meta-llama/llama-3.3-70b-instruct
-label:
-  zh_Hans: Llama 3.3 70B Instruct
-  en_US: Llama 3.3 70B Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0039'
-  output: '0.0039'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
-model: openchat/openchat-7b
+model: lzlv_70b
 label:
-  zh_Hans: OpenChat 7B
-  en_US: OpenChat 7B
+  zh_Hans: lzlv_70b
+  en_US: lzlv_70b
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0006'
-  output: '0.0006'
+  input: '0.0058'
+  output: '0.0078'
  unit: '0.0001'
  currency: USD
@@ -1,7 +1,7 @@
 model: sophosympatheia/midnight-rose-70b
 label:
-  zh_Hans: Midnight Rose 70B
-  en_US: Midnight Rose 70B
+  zh_Hans: sophosympatheia/midnight-rose-70b
+  en_US: sophosympatheia/midnight-rose-70b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: mistralai/mistral-7b-instruct
 label:
-  zh_Hans: Mistral 7B Instruct
-  en_US: Mistral 7B Instruct
+  zh_Hans: mistralai/mistral-7b-instruct
+  en_US: mistralai/mistral-7b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,41 +0,0 @@
-model: mistralai/mistral-nemo
-label:
-  zh_Hans: Mistral Nemo
-  en_US: Mistral Nemo
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0017'
-  output: '0.0017'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
 model: gryphe/mythomax-l2-13b
 label:
-  zh_Hans: Mythomax L2 13B
-  en_US: Mythomax L2 13B
+  zh_Hans: gryphe/mythomax-l2-13b
+  en_US: gryphe/mythomax-l2-13b
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0009'
-  output: '0.0009'
+  input: '0.00119'
+  output: '0.00119'
  unit: '0.0001'
  currency: USD
@@ -1,7 +1,7 @@
 model: nousresearch/nous-hermes-llama2-13b
 label:
-  zh_Hans: Nous Hermes Llama2 13B
-  en_US: Nous Hermes Llama2 13B
+  zh_Hans: nousresearch/nous-hermes-llama2-13b
+  en_US: nousresearch/nous-hermes-llama2-13b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: teknium/openhermes-2.5-mistral-7b
 label:
-  zh_Hans: Openhermes2.5 Mistral 7B
-  en_US: Openhermes2.5 Mistral 7B
+  zh_Hans: teknium/openhermes-2.5-mistral-7b
+  en_US: teknium/openhermes-2.5-mistral-7b
 model_type: llm
 features:
  - agent-thought
@@ -1,41 +0,0 @@
-model: qwen/qwen-2-72b-instruct
-label:
-  zh_Hans: Qwen2 72B Instruct
-  en_US: Qwen2 72B Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32768
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0034'
-  output: '0.0039'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: qwen/qwen-2-7b-instruct
-label:
-  zh_Hans: Qwen 2 7B Instruct
-  en_US: Qwen 2 7B Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32768
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.00054'
-  output: '0.00054'
-  unit: '0.0001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: qwen/qwen-2.5-72b-instruct
-label:
-  zh_Hans: Qwen 2.5 72B Instruct
-  en_US: Qwen 2.5 72B Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.0038'
-  output: '0.004'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
 model: microsoft/wizardlm-2-8x22b
 label:
-  zh_Hans: Wizardlm 2 8x22B
-  en_US: Wizardlm 2 8x22B
+  zh_Hans: microsoft/wizardlm-2-8x22b
+  en_US: microsoft/wizardlm-2-8x22b
 model_type: llm
 features:
  - agent-thought
@@ -35,7 +35,7 @@ parameter_rules:
    max: 2
    default: 0
 pricing:
-  input: '0.0062'
-  output: '0.0062'
+  input: '0.0064'
+  output: '0.0064'
  unit: '0.0001'
  currency: USD
@@ -1,6 +1,6 @@
 provider: novita
 label:
-  en_US: Novita AI
+  en_US: novita.ai
 description:
  en_US: An LLM API that matches various application scenarios with high cost-effectiveness.
  zh_Hans: 适配多种海外应用场景的高性价比 LLM API
@@ -8,13 +8,13 @@ icon_small:
  en_US: icon_s_en.svg
 icon_large:
  en_US: icon_l_en.svg
-background: "#c7fce2"
+background: "#eadeff"
 help:
  title:
-    en_US: Get your API key from Novita AI
-    zh_Hans: 从 Novita AI 获取 API Key
+    en_US: Get your API key from novita.ai
+    zh_Hans: 从 novita.ai 获取 API Key
  url:
-    en_US: https://novita.ai/settings/key-management?utm_source=dify&utm_medium=ch&utm_campaign=api
+    en_US: https://novita.ai/settings#key-management?utm_source=dify&utm_medium=ch&utm_campaign=api
 supported_model_types:
  - llm
 configurate_methods:
@@ -1,4 +1,3 @@
- deepseek-ai/deepseek-r1
 - google/gemma-7b
 - google/codegemma-7b
 - google/recurrentgemma-2b
@@ -1,35 +0,0 @@
-model: deepseek-ai/deepseek-r1
-label:
-  en_US: deepseek-ai/deepseek-r1
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 1
-    default: 0.5
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 1024
-    default: 1024
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
@@ -83,7 +83,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
    def _add_custom_parameters(self, credentials: dict, model: str) -> None:
        credentials["mode"] = "chat"

-        if self.MODEL_SUFFIX_MAP.get(model):
+        if self.MODEL_SUFFIX_MAP[model]:
            credentials["server_url"] = f"https://ai.api.nvidia.com/v1/{self.MODEL_SUFFIX_MAP[model]}"
            credentials.pop("endpoint_url")
        else:
@@ -1,52 +0,0 @@
-model: cohere.command-r-08-2024
-label:
-  en_US: cohere.command-r-08-2024 v1.7
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    max: 1.0
-  - name: topP
-    use_template: top_p
-    default: 0.75
-    min: 0
-    max: 1
-  - name: topK
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-    default: 0
-    min: 0
-    max: 500
-  - name: presencePenalty
-    use_template: presence_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: frequencyPenalty
-    use_template: frequency_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: maxTokens
-    use_template: max_tokens
-    default: 600
-    max: 4000
-pricing:
-  input: '0.0009'
-  output: '0.0009'
-  unit: '0.0001'
-  currency: USD
@@ -50,4 +50,3 @@ pricing:
  output: '0.004'
  unit: '0.0001'
  currency: USD
-deprecated: true
@@ -1,52 +0,0 @@
-model: cohere.command-r-plus-08-2024
-label:
-  en_US: cohere.command-r-plus-08-2024 v1.6
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    max: 1.0
-  - name: topP
-    use_template: top_p
-    default: 0.75
-    min: 0
-    max: 1
-  - name: topK
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-    default: 0
-    min: 0
-    max: 500
-  - name: presencePenalty
-    use_template: presence_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: frequencyPenalty
-    use_template: frequency_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: maxTokens
-    use_template: max_tokens
-    default: 600
-    max: 4000
-pricing:
-  input: '0.0156'
-  output: '0.0156'
-  unit: '0.0001'
-  currency: USD
@@ -50,4 +50,3 @@ pricing:
  output: '0.0219'
  unit: '0.0001'
  currency: USD
-deprecated: true
@@ -33,7 +33,7 @@ logger = logging.getLogger(__name__)

 request_template = {
    "compartmentId": "",
-    "servingMode": {"modelId": "cohere.command-r-plus-08-2024", "servingType": "ON_DEMAND"},
+    "servingMode": {"modelId": "cohere.command-r-plus", "servingType": "ON_DEMAND"},
    "chatRequest": {
        "apiFormat": "COHERE",
        # "preambleOverride": "You are a helpful assistant.",
@@ -60,19 +60,19 @@ oci_config_template = {
 class OCILargeLanguageModel(LargeLanguageModel):
    # https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm
    _supported_models = {
-        "meta.llama-3.1-70b-instruct": {
+        "meta.llama-3-70b-instruct": {
            "system": True,
            "multimodal": False,
            "tool_call": False,
            "stream_tool_call": False,
        },
-        "cohere.command-r-08-2024": {
+        "cohere.command-r-16k": {
            "system": True,
            "multimodal": False,
            "tool_call": True,
            "stream_tool_call": False,
        },
-        "cohere.command-r-plus-08-2024": {
+        "cohere.command-r-plus": {
            "system": True,
            "multimodal": False,
            "tool_call": True,
@@ -49,4 +49,3 @@ pricing:
  output: '0.015'
  unit: '0.0001'
  currency: USD
-deprecated: true
@@ -1,51 +0,0 @@
-model: meta.llama-3.1-70b-instruct
-label:
-  zh_Hans: meta.llama-3.1-70b-instruct
-  en_US: meta.llama-3.1-70b-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    max: 2.0
-  - name: topP
-    use_template: top_p
-    default: 0.75
-    min: 0
-    max: 1
-  - name: topK
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-    default: 0
-    min: 0
-    max: 500
-  - name: presencePenalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: frequencyPenalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: maxTokens
-    use_template: max_tokens
-    default: 600
-    max: 4000
-pricing:
-  input: '0.0075'
-  output: '0.0075'
-  unit: '0.0001'
-  currency: USD
@@ -19,8 +19,8 @@ class OCIGENAIProvider(ModelProvider):
        try:
            model_instance = self.get_model_instance(ModelType.LLM)

-            # Use `cohere.command-r-plus-08-2024` model for validate,
-            model_instance.validate_credentials(model="cohere.command-r-plus-08-2024", credentials=credentials)
+            # Use `cohere.command-r-plus` model for validate,
+            model_instance.validate_credentials(model="cohere.command-r-plus", credentials=credentials)
        except CredentialsValidateFailedError as ex:
            raise ex
        except Exception as ex:
@@ -367,7 +367,6 @@ class OllamaLargeLanguageModel(LargeLanguageModel):

                # transform assistant message to prompt message
                text = chunk_json["response"]
-            text = self._wrap_thinking_by_tag(text)

            assistant_prompt_message = AssistantPromptMessage(content=text)

@@ -2,8 +2,6 @@
 - 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
@@ -341,6 +341,9 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
        :param credentials: provider credentials
        :return:
        """
+        # get predefined models
+        predefined_models = self.predefined_models()
+        predefined_models_map = {model.model: model for model in predefined_models}

        # transform credentials to kwargs for model instance
        credentials_kwargs = self._to_credential_kwargs(credentials)
@@ -356,10 +359,9 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
            base_model = model.id.split(":")[1]

            base_model_schema = None
-            for predefined_model in self.predefined_models():
-                if predefined_model.model in base_model:
+            for predefined_model_name, predefined_model in predefined_models_map.items():
+                if predefined_model_name in base_model:
                    base_model_schema = predefined_model
-                    break

            if not base_model_schema:
                continue
@@ -619,9 +621,9 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
        # clear illegal prompt messages
        prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)

-        # o1, o3 compatibility
+        # o1 compatibility
        block_as_stream = False
-        if model.startswith(("o1", "o3")):
+        if model.startswith("o1"):
            if "max_tokens" in model_parameters:
                model_parameters["max_completion_tokens"] = model_parameters["max_tokens"]
                del model_parameters["max_tokens"]
@@ -941,7 +943,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
                                ]
                            )

-        if model.startswith(("o1", "o3")):
+        if model.startswith("o1"):
            system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
            if system_message_count > 0:
                new_prompt_messages = []
@@ -1053,7 +1055,7 @@ 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", "o3")):
+        if model == "chatgpt-4o-latest" or model.startswith("o1"):
            model = "gpt-4o"

        try:
@@ -1068,7 +1070,7 @@ 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", "o3")):
+        elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith("o1"):
            tokens_per_message = 3
            tokens_per_name = 1
        else:
@@ -1184,15 +1186,13 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
            base_model = model.split(":")[1]

        # get model schema
-        base_model_schema = None
-        for predefined_model in self.predefined_models():
-            if base_model == predefined_model.model:
-                base_model_schema = predefined_model
-                break
-
-        if not base_model_schema:
+        models = self.predefined_models()
+        model_map = {model.model: model for model in models}
+        if base_model not in model_map:
            raise ValueError(f"Base model {base_model} not found")

+        base_model_schema = model_map[base_model]
+
        base_model_schema_features = base_model_schema.features or []
        base_model_schema_model_properties = base_model_schema.model_properties
        base_model_schema_parameters_rules = base_model_schema.parameter_rules
@@ -16,19 +16,6 @@ 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
@@ -17,19 +17,6 @@ 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
@@ -1,46 +0,0 @@
-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
@@ -1,46 +0,0 @@
-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
@@ -1,5 +1,5 @@
-import codecs
 import json
+import logging
 from collections.abc import Generator
 from decimal import Decimal
 from typing import Optional, Union, cast
@@ -38,6 +38,8 @@ from core.model_runtime.model_providers.__base.large_language_model import Large
 from core.model_runtime.model_providers.openai_api_compatible._common import _CommonOaiApiCompat
 from core.model_runtime.utils import helper

+logger = logging.getLogger(__name__)
+

 class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
    """
@@ -97,7 +99,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
        :param tools: tools for tool calling
        :return:
        """
-        return self._num_tokens_from_messages(prompt_messages, tools, credentials)
+        return self._num_tokens_from_messages(model, prompt_messages, tools, credentials)

    def validate_credentials(self, model: str, credentials: dict) -> None:
        """
@@ -396,73 +398,6 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

        return self._handle_generate_response(model, credentials, response, prompt_messages)

-    def _create_final_llm_result_chunk(
-        self,
-        index: int,
-        message: AssistantPromptMessage,
-        finish_reason: str,
-        usage: dict,
-        model: str,
-        prompt_messages: list[PromptMessage],
-        credentials: dict,
-        full_content: str,
-    ) -> LLMResultChunk:
-        # calculate num tokens
-        prompt_tokens = usage and usage.get("prompt_tokens")
-        if prompt_tokens is None:
-            prompt_tokens = self._num_tokens_from_string(text=prompt_messages[0].content)
-        completion_tokens = usage and usage.get("completion_tokens")
-        if completion_tokens is None:
-            completion_tokens = self._num_tokens_from_string(text=full_content)
-
-        # transform usage
-        usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
-
-        return LLMResultChunk(
-            model=model,
-            prompt_messages=prompt_messages,
-            delta=LLMResultChunkDelta(index=index, message=message, finish_reason=finish_reason, usage=usage),
-        )
-
-    def _get_tool_call(self, tool_call_id: str, tools_calls: list[AssistantPromptMessage.ToolCall]):
-        """
-        Get or create a tool call by ID
-
-        :param tool_call_id: tool call ID
-        :param tools_calls: list of existing tool calls
-        :return: existing or new tool call, updated tools_calls
-        """
-        if not tool_call_id:
-            return tools_calls[-1], tools_calls
-
-        tool_call = next((tool_call for tool_call in tools_calls if tool_call.id == tool_call_id), None)
-        if tool_call is None:
-            tool_call = AssistantPromptMessage.ToolCall(
-                id=tool_call_id,
-                type="function",
-                function=AssistantPromptMessage.ToolCall.ToolCallFunction(name="", arguments=""),
-            )
-            tools_calls.append(tool_call)
-
-        return tool_call, tools_calls
-
-    def _increase_tool_call(
-        self, new_tool_calls: list[AssistantPromptMessage.ToolCall], tools_calls: list[AssistantPromptMessage.ToolCall]
-    ) -> list[AssistantPromptMessage.ToolCall]:
-        for new_tool_call in new_tool_calls:
-            # get tool call
-            tool_call, tools_calls = self._get_tool_call(new_tool_call.function.name, tools_calls)
-            # update tool call
-            if new_tool_call.id:
-                tool_call.id = new_tool_call.id
-            if new_tool_call.type:
-                tool_call.type = new_tool_call.type
-            if new_tool_call.function.name:
-                tool_call.function.name = new_tool_call.function.name
-            if new_tool_call.function.arguments:
-                tool_call.function.arguments += new_tool_call.function.arguments
-        return tools_calls
-
    def _handle_generate_stream_response(
        self, model: str, credentials: dict, response: requests.Response, prompt_messages: list[PromptMessage]
    ) -> Generator:
@@ -475,15 +410,69 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
        :param prompt_messages: prompt messages
        :return: llm response chunk generator
        """
-        chunk_index = 0
        full_assistant_content = ""
-        tools_calls: list[AssistantPromptMessage.ToolCall] = []
-        finish_reason = None
-        usage = None
-        is_reasoning_started = False
+        chunk_index = 0
+
+        def create_final_llm_result_chunk(
+            id: Optional[str], index: int, message: AssistantPromptMessage, finish_reason: str, usage: dict
+        ) -> LLMResultChunk:
+            # calculate num tokens
+            prompt_tokens = usage and usage.get("prompt_tokens")
+            if prompt_tokens is None:
+                prompt_tokens = self._num_tokens_from_string(model, prompt_messages[0].content)
+            completion_tokens = usage and usage.get("completion_tokens")
+            if completion_tokens is None:
+                completion_tokens = self._num_tokens_from_string(model, full_assistant_content)
+
+            # transform usage
+            usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
+
+            return LLMResultChunk(
+                id=id,
+                model=model,
+                prompt_messages=prompt_messages,
+                delta=LLMResultChunkDelta(index=index, message=message, finish_reason=finish_reason, usage=usage),
+            )
+
        # delimiter for stream response, need unicode_escape
+        import codecs
+
        delimiter = credentials.get("stream_mode_delimiter", "\n\n")
        delimiter = codecs.decode(delimiter, "unicode_escape")
+
+        tools_calls: list[AssistantPromptMessage.ToolCall] = []
+
+        def increase_tool_call(new_tool_calls: list[AssistantPromptMessage.ToolCall]):
+            def get_tool_call(tool_call_id: str):
+                if not tool_call_id:
+                    return tools_calls[-1]
+
+                tool_call = next((tool_call for tool_call in tools_calls if tool_call.id == tool_call_id), None)
+                if tool_call is None:
+                    tool_call = AssistantPromptMessage.ToolCall(
+                        id=tool_call_id,
+                        type="function",
+                        function=AssistantPromptMessage.ToolCall.ToolCallFunction(name="", arguments=""),
+                    )
+                    tools_calls.append(tool_call)
+
+                return tool_call
+
+            for new_tool_call in new_tool_calls:
+                # get tool call
+                tool_call = get_tool_call(new_tool_call.function.name)
+                # update tool call
+                if new_tool_call.id:
+                    tool_call.id = new_tool_call.id
+                if new_tool_call.type:
+                    tool_call.type = new_tool_call.type
+                if new_tool_call.function.name:
+                    tool_call.function.name = new_tool_call.function.name
+                if new_tool_call.function.arguments:
+                    tool_call.function.arguments += new_tool_call.function.arguments
+
+        finish_reason = None  # The default value of finish_reason is None
+        message_id, usage = None, None
        for chunk in response.iter_lines(decode_unicode=True, delimiter=delimiter):
            chunk = chunk.strip()
            if chunk:
@@ -498,15 +487,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                    chunk_json: dict = json.loads(decoded_chunk)
                # stream ended
                except json.JSONDecodeError as e:
-                    yield self._create_final_llm_result_chunk(
+                    yield create_final_llm_result_chunk(
+                        id=message_id,
                        index=chunk_index + 1,
                        message=AssistantPromptMessage(content=""),
                        finish_reason="Non-JSON encountered.",
                        usage=usage,
-                        model=model,
-                        credentials=credentials,
-                        prompt_messages=prompt_messages,
-                        full_content=full_assistant_content,
                    )
                    break
                # handle the error here. for issue #11629
@@ -521,14 +507,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

                choice = chunk_json["choices"][0]
                finish_reason = chunk_json["choices"][0].get("finish_reason")
+                message_id = chunk_json.get("id")
                chunk_index += 1

                if "delta" in choice:
                    delta = choice["delta"]
-                    delta_content, is_reasoning_started = self._wrap_thinking_by_reasoning_content(
-                        delta, is_reasoning_started
-                    )
-                    delta_content = self._wrap_thinking_by_tag(delta_content)
+                    delta_content = delta.get("content")

                    assistant_message_tool_calls = None

@@ -542,10 +526,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                            {"id": "tool_call_id", "type": "function", "function": delta.get("function_call", {})}
                        ]

+                    # assistant_message_function_call = delta.delta.function_call
+
                    # extract tool calls from response
                    if assistant_message_tool_calls:
                        tool_calls = self._extract_response_tool_calls(assistant_message_tool_calls)
-                        tools_calls = self._increase_tool_call(tool_calls, tools_calls)
+                        increase_tool_call(tool_calls)

                    if delta_content is None or delta_content == "":
                        continue
@@ -570,6 +556,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                    continue

                yield LLMResultChunk(
+                    id=message_id,
                    model=model,
                    prompt_messages=prompt_messages,
                    delta=LLMResultChunkDelta(
@@ -582,6 +569,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

        if tools_calls:
            yield LLMResultChunk(
+                id=message_id,
                model=model,
                prompt_messages=prompt_messages,
                delta=LLMResultChunkDelta(
@@ -590,15 +578,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                ),
            )

-        yield self._create_final_llm_result_chunk(
+        yield create_final_llm_result_chunk(
+            id=message_id,
            index=chunk_index,
            message=AssistantPromptMessage(content=""),
            finish_reason=finish_reason,
            usage=usage,
-            model=model,
-            credentials=credentials,
-            prompt_messages=prompt_messages,
-            full_content=full_assistant_content,
        )

    def _handle_generate_response(
@@ -712,11 +697,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
        return message_dict

    def _num_tokens_from_string(
-        self, text: Union[str, list[PromptMessageContent]], tools: Optional[list[PromptMessageTool]] = None
+        self, model: str, text: Union[str, list[PromptMessageContent]], tools: Optional[list[PromptMessageTool]] = None
    ) -> int:
        """
        Approximate num tokens for model with gpt2 tokenizer.

+        :param model: model name
        :param text: prompt text
        :param tools: tools for tool calling
        :return: number of tokens
@@ -739,6 +725,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

    def _num_tokens_from_messages(
        self,
+        model: str,
        messages: list[PromptMessage],
        tools: Optional[list[PromptMessageTool]] = None,
        credentials: Optional[dict] = None,
@@ -1,7 +1,5 @@
 - openai/o1-preview
 - openai/o1-mini
- openai/o3-mini
- openai/o3-mini-2025-01-31
 - openai/gpt-4o
 - openai/gpt-4o-mini
 - openai/gpt-4
@@ -30,6 +28,5 @@
 - mistralai/mistral-7b-instruct
 - qwen/qwen-2.5-72b-instruct
 - qwen/qwen-2-72b-instruct
- deepseek/deepseek-r1
 - deepseek/deepseek-chat
 - deepseek/deepseek-coder
@@ -53,7 +53,7 @@ parameter_rules:
      zh_Hans: 介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。
      en_US: A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.
 pricing:
-  input: "0.49"
-  output: "0.89"
+  input: "0.14"
+  output: "0.28"
  unit: "0.000001"
  currency: USD
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
-LAN-	8cbf72785f	chore(github-actions): build docker image on 'release/0.15.2-fix1' Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-01-27 18:58:50 +08:00
-LAN-	f97f82a3e4	fix(llm): deduct LLM quota after processing usage in invoke result Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-01-27 18:57:47 +08:00