chore: Bump version

Signed-off-by: -LAN- <laipz8200@outlook.com>
fix: Refactor web reader to use readabilipy (#19789 )
2025-05-30 16:25:40 +08:00 · 2025-05-30 16:23:17 +08:00 · 2025-05-15 14:47:15 +08:00 · 2025-05-14 18:03:05 +08:00 · 2025-05-14 18:02:32 +08:00 · 2025-05-14 14:08:05 +08:00
255 changed files with 12513 additions and 10540 deletions
@@ -5,8 +5,8 @@ on:
    branches:
      - "main"
      - "deploy/dev"
-  release:
-    types: [published]
+    tags:
+      - "*"

 concurrency:
  group: build-push-${{ github.head_ref || github.run_id }}
@@ -0,0 +1,47 @@
+name: Build docker image
+
+on:
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - api/Dockerfile
+      - web/Dockerfile
+
+concurrency:
+  group: docker-build-${{ 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
@@ -0,0 +1,4 @@
+{
+    "MD024": false,
+    "MD013": false
+}
@@ -0,0 +1,45 @@
+# Changelog
+
+All notable changes to Dify will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.15.8] - 2025-05-30
+
+### Added
+
+- Added gunicorn keepalive setting (#19537)
+
+### Fixed
+
+- Fixed database configuration to allow DB_EXTRAS to set search_path via options (#16a4f77)
+- Fixed frontend third-party package security issues (#19655)
+- Updated dependencies: huggingface-hub (~0.16.4 to ~0.31.0), transformers (~4.35.0 to ~4.39.0), and resend (~0.7.0 to ~2.9.0) (#19563)
+- Downgrade boto3 from 1.36 to 1.35 (#19736)
+
+## [0.15.7] - 2025-04-27
+
+### Added
+
+- Added support for GPT-4.1 in model providers (#18912)
+- Added support for Amazon Bedrock DeepSeek-R1 model (#18908)
+- Added support for Amazon Bedrock Claude Sonnet 3.7 model (#18788)
+- Refined version compatibility logic in app DSL service
+
+### Fixed
+
+- Fixed issue with creating apps from template categories (#18807, #18868)
+- Fixed DSL version check when creating apps from explore templates (#18872, #18878)
+
+## [0.15.6] - 2025-04-22
+
+### Security
+
+- Fixed clickjacking vulnerability (#18552)
+- Fixed reset password security issue (#18366)
+- Updated reset password token when email code verification succeeds (#18362)
+
+### Fixed
+
+- Fixed Vertex AI Gemini 2.0 Flash 001 schema (#18405)
@@ -25,6 +25,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -25,6 +25,9 @@
    <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">
@@ -22,6 +22,9 @@
    <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">
@@ -21,6 +21,9 @@
    <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">
@@ -62,8 +65,6 @@ 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.

@@ -150,8 +151,6 @@ 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>**
@@ -177,8 +176,6 @@ 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
@@ -21,6 +21,9 @@
    <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">
@@ -430,4 +430,7 @@ CREATE_TIDB_SERVICE_JOB_ENABLED=false
 # Maximum number of submitted thread count in a ThreadPool for parallel node execution
 MAX_SUBMIT_COUNT=100
 # Lockout duration in seconds
-LOGIN_LOCKOUT_DURATION=86400
+LOGIN_LOCKOUT_DURATION=86400
+
+# Prevent Clickjacking
+ALLOW_EMBED=false
@@ -48,16 +48,18 @@ ENV TZ=UTC

 WORKDIR /app/api

-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 \
+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 \
    && apt-get autoremove -y \
    && rm -rf /var/lib/apt/lists/*

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

-
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

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

-from pydantic import Field, NonNegativeInt
+from pydantic import Field, NonNegativeInt, computed_field
 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
@@ -202,5 +233,7 @@ class HostedServiceConfig(
    HostedZhipuAIConfig,
    # moderation
    HostedModerationConfig,
+    # credit config
+    HostedCreditConfig,
 ):
    pass
@@ -1,5 +1,5 @@
 from typing import Any, Literal, Optional
-from urllib.parse import quote_plus
+from urllib.parse import parse_qsl, quote_plus

 from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
@@ -166,14 +166,28 @@ class DatabaseConfig(BaseSettings):
        default=False,
    )

-    @computed_field
+    @computed_field  # type: ignore[misc]
+    @property
    def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
+        # Parse DB_EXTRAS for 'options'
+        db_extras_dict = dict(parse_qsl(self.DB_EXTRAS))
+        options = db_extras_dict.get("options", "")
+        # Always include timezone
+        timezone_opt = "-c timezone=UTC"
+        if options:
+            # Merge user options and timezone
+            merged_options = f"{options} {timezone_opt}"
+        else:
+            merged_options = timezone_opt
+
+        connect_args = {"options": merged_options}
+
        return {
            "pool_size": self.SQLALCHEMY_POOL_SIZE,
            "max_overflow": self.SQLALCHEMY_MAX_OVERFLOW,
            "pool_recycle": self.SQLALCHEMY_POOL_RECYCLE,
            "pool_pre_ping": self.SQLALCHEMY_POOL_PRE_PING,
-            "connect_args": {"options": "-c timezone=UTC"},
+            "connect_args": connect_args,
        }


@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.15.2",
+        default="0.15.8",
    )

    COMMIT_SHA: str = Field(
@@ -1,12 +1,32 @@
 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
@@ -47,6 +67,13 @@ 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
@@ -8,7 +8,7 @@ from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import EmailCodeError, InvalidEmailError, InvalidTokenError, PasswordMismatchError
 from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
-from controllers.console.wraps import setup_required
+from controllers.console.wraps import email_password_login_enabled, setup_required
 from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import email, extract_remote_ip
@@ -22,6 +22,7 @@ from services.feature_service import FeatureService

 class ForgotPasswordSendEmailApi(Resource):
    @setup_required
+    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=email, required=True, location="json")
@@ -53,6 +54,7 @@ class ForgotPasswordSendEmailApi(Resource):

 class ForgotPasswordCheckApi(Resource):
    @setup_required
+    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=str, required=True, location="json")
@@ -72,11 +74,20 @@ class ForgotPasswordCheckApi(Resource):
        if args["code"] != token_data.get("code"):
            raise EmailCodeError()

-        return {"is_valid": True, "email": token_data.get("email")}
+        # Verified, revoke the first token
+        AccountService.revoke_reset_password_token(args["token"])
+
+        # Refresh token data by generating a new token
+        _, new_token = AccountService.generate_reset_password_token(
+            user_email, code=args["code"], additional_data={"phase": "reset"}
+        )
+
+        return {"is_valid": True, "email": token_data.get("email"), "token": new_token}


 class ForgotPasswordResetApi(Resource):
    @setup_required
+    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("token", type=str, required=True, nullable=False, location="json")
@@ -95,6 +106,9 @@ class ForgotPasswordResetApi(Resource):

        if reset_data is None:
            raise InvalidTokenError()
+        # Must use token in reset phase
+        if reset_data.get("phase", "") != "reset":
+            raise InvalidTokenError()

        AccountService.revoke_reset_password_token(token)

@@ -22,7 +22,7 @@ from controllers.console.error import (
    EmailSendIpLimitError,
    NotAllowedCreateWorkspace,
 )
-from controllers.console.wraps import setup_required
+from controllers.console.wraps import email_password_login_enabled, setup_required
 from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
@@ -38,6 +38,7 @@ class LoginApi(Resource):
    """Resource for user login."""

    @setup_required
+    @email_password_login_enabled
    def post(self):
        """Authenticate user and login."""
        parser = reqparse.RequestParser()
@@ -110,6 +111,7 @@ class LogoutApi(Resource):

 class ResetPasswordSendEmailApi(Resource):
    @setup_required
+    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=email, required=True, location="json")
@@ -620,7 +620,6 @@ 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"], "desc"
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -154,3 +154,16 @@ def enterprise_license_required(view):
        return view(*args, **kwargs)

    return decorated
+
+
+def email_password_login_enabled(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        features = FeatureService.get_system_features()
+        if features.enable_email_password_login:
+            return view(*args, **kwargs)
+
+        # otherwise, return 403
+        abort(403)
+
+    return decorated
@@ -1,3 +1,5 @@
+import json
+
 from flask_restful import Resource, reqparse  # type: ignore

 from controllers.console.wraps import setup_required
@@ -29,4 +31,34 @@ 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")
@@ -18,6 +18,7 @@ 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
@@ -50,6 +51,9 @@ 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)
@@ -61,6 +65,28 @@ 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:
@@ -107,6 +133,8 @@ 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)
@@ -115,6 +143,32 @@ 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")
@@ -161,6 +215,30 @@ 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)
@@ -228,6 +306,29 @@ 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"], "desc"
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -104,7 +104,6 @@ class CotAgentRunner(BaseAgentRunner, ABC):

            # recalc llm max tokens
            prompt_messages = self._organize_prompt_messages()
-            self.recalc_llm_max_tokens(self.model_config, prompt_messages)
            # invoke model
            chunks = model_instance.invoke_llm(
                prompt_messages=prompt_messages,
@@ -84,7 +84,6 @@ class FunctionCallAgentRunner(BaseAgentRunner):

            # recalc llm max tokens
            prompt_messages = self._organize_prompt_messages()
-            self.recalc_llm_max_tokens(self.model_config, prompt_messages)
            # invoke model
            chunks: Union[Generator[LLMResultChunk, None, None], LLMResult] = model_instance.invoke_llm(
                prompt_messages=prompt_messages,
@@ -55,20 +55,6 @@ class AgentChatAppRunner(AppRunner):
        query = application_generate_entity.query
        files = application_generate_entity.files

-        # Pre-calculate the number of tokens of the prompt messages,
-        # and return the rest number of tokens by model context token size limit and max token size limit.
-        # If the rest number of tokens is not enough, raise exception.
-        # Include: prompt template, inputs, query(optional), files(optional)
-        # Not Include: memory, external data, dataset context
-        self.get_pre_calculate_rest_tokens(
-            app_record=app_record,
-            model_config=application_generate_entity.model_conf,
-            prompt_template_entity=app_config.prompt_template,
-            inputs=inputs,
-            files=files,
-            query=query,
-        )
-
        memory = None
        if application_generate_entity.conversation_id:
            # get memory of conversation (read-only)
@@ -202,7 +188,7 @@ 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 or not model_schema.features:
+        if not model_schema:
            raise ValueError("Model schema not found")

        if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
@@ -15,10 +15,8 @@ from core.app.features.annotation_reply.annotation_reply import AnnotationReplyF
 from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature
 from core.external_data_tool.external_data_fetch import ExternalDataFetch
 from core.memory.token_buffer_memory import TokenBufferMemory
-from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage
-from core.model_runtime.entities.model_entities import ModelPropertyKey
 from core.model_runtime.errors.invoke import InvokeBadRequestError
 from core.moderation.input_moderation import InputModeration
 from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
@@ -31,106 +29,6 @@ if TYPE_CHECKING:


 class AppRunner:
-    def get_pre_calculate_rest_tokens(
-        self,
-        app_record: App,
-        model_config: ModelConfigWithCredentialsEntity,
-        prompt_template_entity: PromptTemplateEntity,
-        inputs: Mapping[str, str],
-        files: Sequence["File"],
-        query: Optional[str] = None,
-    ) -> int:
-        """
-        Get pre calculate rest tokens
-        :param app_record: app record
-        :param model_config: model config entity
-        :param prompt_template_entity: prompt template entity
-        :param inputs: inputs
-        :param files: files
-        :param query: query
-        :return:
-        """
-        # Invoke model
-        model_instance = ModelInstance(
-            provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
-        )
-
-        model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
-
-        max_tokens = 0
-        for parameter_rule in model_config.model_schema.parameter_rules:
-            if parameter_rule.name == "max_tokens" or (
-                parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
-            ):
-                max_tokens = (
-                    model_config.parameters.get(parameter_rule.name)
-                    or model_config.parameters.get(parameter_rule.use_template or "")
-                ) or 0
-
-        if model_context_tokens is None:
-            return -1
-
-        if max_tokens is None:
-            max_tokens = 0
-
-        # get prompt messages without memory and context
-        prompt_messages, stop = self.organize_prompt_messages(
-            app_record=app_record,
-            model_config=model_config,
-            prompt_template_entity=prompt_template_entity,
-            inputs=inputs,
-            files=files,
-            query=query,
-        )
-
-        prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
-
-        rest_tokens: int = model_context_tokens - max_tokens - prompt_tokens
-        if rest_tokens < 0:
-            raise InvokeBadRequestError(
-                "Query or prefix prompt is too long, you can reduce the prefix prompt, "
-                "or shrink the max token, or switch to a llm with a larger token limit size."
-            )
-
-        return rest_tokens
-
-    def recalc_llm_max_tokens(
-        self, model_config: ModelConfigWithCredentialsEntity, prompt_messages: list[PromptMessage]
-    ):
-        # recalc max_tokens if sum(prompt_token +  max_tokens) over model token limit
-        model_instance = ModelInstance(
-            provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
-        )
-
-        model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
-
-        max_tokens = 0
-        for parameter_rule in model_config.model_schema.parameter_rules:
-            if parameter_rule.name == "max_tokens" or (
-                parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
-            ):
-                max_tokens = (
-                    model_config.parameters.get(parameter_rule.name)
-                    or model_config.parameters.get(parameter_rule.use_template or "")
-                ) or 0
-
-        if model_context_tokens is None:
-            return -1
-
-        if max_tokens is None:
-            max_tokens = 0
-
-        prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
-
-        if prompt_tokens + max_tokens > model_context_tokens:
-            max_tokens = max(model_context_tokens - prompt_tokens, 16)
-
-            for parameter_rule in model_config.model_schema.parameter_rules:
-                if parameter_rule.name == "max_tokens" or (
-                    parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
-                ):
-                    model_config.parameters[parameter_rule.name] = max_tokens
-
    def organize_prompt_messages(
        self,
        app_record: App,
@@ -50,20 +50,6 @@ class ChatAppRunner(AppRunner):
        query = application_generate_entity.query
        files = application_generate_entity.files

-        # Pre-calculate the number of tokens of the prompt messages,
-        # and return the rest number of tokens by model context token size limit and max token size limit.
-        # If the rest number of tokens is not enough, raise exception.
-        # Include: prompt template, inputs, query(optional), files(optional)
-        # Not Include: memory, external data, dataset context
-        self.get_pre_calculate_rest_tokens(
-            app_record=app_record,
-            model_config=application_generate_entity.model_conf,
-            prompt_template_entity=app_config.prompt_template,
-            inputs=inputs,
-            files=files,
-            query=query,
-        )
-
        memory = None
        if application_generate_entity.conversation_id:
            # get memory of conversation (read-only)
@@ -194,9 +180,6 @@ class ChatAppRunner(AppRunner):
        if hosting_moderation_result:
            return

-        # Re-calculate the max tokens if sum(prompt_token +  max_tokens) over model token limit
-        self.recalc_llm_max_tokens(model_config=application_generate_entity.model_conf, prompt_messages=prompt_messages)
-
        # Invoke model
        model_instance = ModelInstance(
            provider_model_bundle=application_generate_entity.model_conf.provider_model_bundle,
@@ -43,20 +43,6 @@ class CompletionAppRunner(AppRunner):
        query = application_generate_entity.query
        files = application_generate_entity.files

-        # Pre-calculate the number of tokens of the prompt messages,
-        # and return the rest number of tokens by model context token size limit and max token size limit.
-        # If the rest number of tokens is not enough, raise exception.
-        # Include: prompt template, inputs, query(optional), files(optional)
-        # Not Include: memory, external data, dataset context
-        self.get_pre_calculate_rest_tokens(
-            app_record=app_record,
-            model_config=application_generate_entity.model_conf,
-            prompt_template_entity=app_config.prompt_template,
-            inputs=inputs,
-            files=files,
-            query=query,
-        )
-
        # organize all inputs and template to prompt messages
        # Include: prompt template, inputs, query(optional), files(optional)
        prompt_messages, stop = self.organize_prompt_messages(
@@ -152,9 +138,6 @@ class CompletionAppRunner(AppRunner):
        if hosting_moderation_result:
            return

-        # Re-calculate the max tokens if sum(prompt_token +  max_tokens) over model token limit
-        self.recalc_llm_max_tokens(model_config=application_generate_entity.model_conf, prompt_messages=prompt_messages)
-
        # Invoke model
        model_instance = ModelInstance(
            provider_model_bundle=application_generate_entity.model_conf.provider_model_bundle,
@@ -11,15 +11,6 @@ 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]

@@ -51,7 +42,11 @@ 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 proxy_mounts:
+            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),
+                }
                with httpx.Client(mounts=proxy_mounts) as client:
                    response = client.request(method=method, url=url, **kwargs)
            else:
@@ -26,7 +26,7 @@ class TokenBufferMemory:
        self.model_instance = model_instance

    def get_history_prompt_messages(
-        self, max_token_limit: int = 2000, message_limit: Optional[int] = None
+        self, max_token_limit: int = 100000, message_limit: Optional[int] = None
    ) -> Sequence[PromptMessage]:
        """
        Get history prompt messages.
@@ -1,4 +1,4 @@
-from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
    AssistantPromptMessage,
    AudioPromptMessageContent,
@@ -23,6 +23,7 @@ __all__ = [
    "AudioPromptMessageContent",
    "DocumentPromptMessageContent",
    "ImagePromptMessageContent",
+    "LLMMode",
    "LLMResult",
    "LLMResultChunk",
    "LLMResultChunkDelta",
@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import Enum
+from enum import StrEnum
 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(Enum):
+class LLMMode(StrEnum):
    """
    Enum class for large language model mode.
    """
@@ -221,13 +221,12 @@ class AIModel(ABC):
        :param credentials: model credentials
        :return: model schema
        """
-        # 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 predefined models
+        for predefined_model in self.predefined_models():
+            if model == predefined_model.model:
+                return predefined_model

+        # Try to get model schema from credentials
        if credentials:
            model_schema = self.get_customizable_model_schema_from_credentials(model, credentials)
            if model_schema:
@@ -30,6 +30,11 @@ 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):
    """
@@ -400,6 +405,40 @@ 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,
@@ -1,4 +1,5 @@
 - openai
+- deepseek
 - anthropic
 - azure_openai
 - google
@@ -32,7 +33,6 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud
@@ -51,6 +51,40 @@ 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
+from collections.abc import Generator, Sequence
 from typing import Any, Optional, Union

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

        if not self.client:
-            endpoint = credentials.get("endpoint")
-            api_key = credentials.get("api_key")
+            endpoint = str(credentials.get("endpoint"))
+            api_key = str(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]
@@ -94,6 +95,7 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            "temperature": model_parameters.get("temperature", 0),
            "top_p": model_parameters.get("top_p", 1),
            "stream": stream,
+            "model": model,
        }

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

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

@@ -53,6 +53,9 @@ 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
@@ -135,6 +138,18 @@ 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
@@ -123,6 +123,15 @@ provider_credential_schema:
            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:
@@ -13,6 +13,7 @@ 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
@@ -21,6 +22,7 @@ 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
@@ -0,0 +1,115 @@
+model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+label:
+  en_US: Claude 3.7 Sonnet(US.Cross Region Inference)
+icon: icon_s_en.svg
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: enable_cache
+    label:
+      zh_Hans: 启用提示缓存
+      en_US: Enable Prompt Cache
+    type: boolean
+    required: false
+    default: true
+    help:
+      zh_Hans: 启用提示缓存可以提高性能并降低成本。Claude 3.7 Sonnet支持在system、messages和tools字段中使用缓存检查点。
+      en_US: Enable prompt caching to improve performance and reduce costs. Claude 3.7 Sonnet supports cache checkpoints in system, messages, and tools fields.
+  - name: reasoning_type
+    label:
+      zh_Hans: 推理配置
+      en_US: Reasoning Type
+    type: boolean
+    required: false
+    default: false
+    placeholder:
+      zh_Hans: 设置推理配置
+      en_US: Set reasoning configuration
+    help:
+      zh_Hans: 控制模型的推理能力。启用时，temperature将固定为1且top_p将被禁用。
+      en_US: Controls the model's reasoning capability. When enabled, temperature will be fixed to 1 and top_p will be disabled.
+  - name: reasoning_budget
+    show_on:
+      - variable: reasoning_type
+        value: true
+    label:
+      zh_Hans: 推理预算
+      en_US: Reasoning Budget
+    type: int
+    default: 1024
+    min: 0
+    max: 128000
+    help:
+      zh_Hans: 推理的预算限制（最小1024），必须小于max_tokens。仅在推理类型为enabled时可用。
+      en_US: Budget limit for reasoning (minimum 1024), must be less than max_tokens. Only available when reasoning type is enabled.
+
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    label:
+      zh_Hans: 最大token数
+      en_US: Max Tokens
+    type: int
+    default: 8192
+    min: 1
+    max: 128000
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    label:
+      zh_Hans: 模型温度
+      en_US: Model Temperature
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。当推理功能启用时，该值将被固定为1。
+      en_US: The amount of randomness injected into the response. When reasoning is enabled, this value will be fixed to 1.
+  - name: top_p
+    show_on:
+      - variable: reasoning_type
+        value: disabled
+    use_template: top_p
+    label:
+      zh_Hans: Top P
+      en_US: Top P
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中的概率阈值。当推理功能启用时，该参数将被禁用。
+      en_US: The probability threshold in nucleus sampling. When reasoning is enabled, this parameter will be disabled.
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD
@@ -58,6 +58,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
    # TODO There is invoke issue: context limit on Cohere Model, will add them after fixed.
    CONVERSE_API_ENABLED_MODEL_INFO = [
        {"prefix": "anthropic.claude-v2", "support_system_prompts": True, "support_tool_use": False},
+        {"prefix": "us.deepseek", "support_system_prompts": True, "support_tool_use": False},
        {"prefix": "anthropic.claude-v1", "support_system_prompts": True, "support_tool_use": False},
        {"prefix": "us.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
        {"prefix": "eu.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
@@ -0,0 +1,63 @@
+model: us.deepseek.r1-v1:0
+label:
+  en_US: DeepSeek-R1(US.Cross Region Inference)
+icon: icon_s_en.svg
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    label:
+      zh_Hans: 最大token数
+      en_US: Max Tokens
+    type: int
+    default: 8192
+    min: 1
+    max: 128000
+    help:
+      zh_Hans: 停止前生成的最大令牌数。
+      en_US: The maximum number of tokens to generate before stopping.
+  - name: temperature
+    use_template: temperature
+    required: false
+    label:
+      zh_Hans: 模型温度
+      en_US: Model Temperature
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。当推理功能启用时，该值将被固定为1。
+      en_US: The amount of randomness injected into the response. When reasoning is enabled, this value will be fixed to 1.
+  - name: top_p
+    show_on:
+      - variable: reasoning_type
+        value: disabled
+    use_template: top_p
+    label:
+      zh_Hans: Top P
+      en_US: Top P
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中的概率阈值。当推理功能启用时，该参数将被禁用。
+      en_US: The probability threshold in nucleus sampling. When reasoning is enabled, this parameter will be disabled.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.001'
+  output: '0.005'
+  unit: '0.001'
+  currency: USD
@@ -677,16 +677,17 @@ class CohereLargeLanguageModel(LargeLanguageModel):

        :return: model schema
        """
-        # get model schema
-        models = self.predefined_models()
-        model_map = {model.model: model for model in models}
-
        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

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

        base_model_schema = cast(AIModelEntity, base_model_schema)

@@ -1,13 +1,10 @@
-import json
 from collections.abc import Generator
 from typing import Optional, Union

-import requests
 from yarl import URL

-from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
 from core.model_runtime.entities.message_entities import (
-    AssistantPromptMessage,
    PromptMessage,
    PromptMessageTool,
 )
@@ -39,208 +36,3 @@ class DeepseekLargeLanguageModel(OAIAPICompatLargeLanguageModel):
        credentials["mode"] = LLMMode.CHAT.value
        credentials["function_calling_type"] = "tool_call"
        credentials["stream_function_calling"] = "support"
-
-    def _handle_generate_stream_response(
-        self, model: str, credentials: dict, response: requests.Response, prompt_messages: list[PromptMessage]
-    ) -> Generator:
-        """
-        Handle llm stream response
-
-        :param model: model name
-        :param credentials: model credentials
-        :param response: streamed response
-        :param prompt_messages: prompt messages
-        :return: llm response chunk generator
-        """
-        full_assistant_content = ""
-        chunk_index = 0
-        is_reasoning_started = False  # Add flag to track reasoning state
-
-        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:
-                # ignore sse comments
-                if chunk.startswith(":"):
-                    continue
-                decoded_chunk = chunk.strip().removeprefix("data:").lstrip()
-                if decoded_chunk == "[DONE]":  # Some provider returns "data: [DONE]"
-                    continue
-
-                try:
-                    chunk_json: dict = json.loads(decoded_chunk)
-                # stream ended
-                except json.JSONDecodeError as e:
-                    yield create_final_llm_result_chunk(
-                        id=message_id,
-                        index=chunk_index + 1,
-                        message=AssistantPromptMessage(content=""),
-                        finish_reason="Non-JSON encountered.",
-                        usage=usage,
-                    )
-                    break
-                # handle the error here. for issue #11629
-                if chunk_json.get("error") and chunk_json.get("choices") is None:
-                    raise ValueError(chunk_json.get("error"))
-
-                if chunk_json:
-                    if u := chunk_json.get("usage"):
-                        usage = u
-                if not chunk_json or len(chunk_json["choices"]) == 0:
-                    continue
-
-                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"]
-                    is_reasoning = delta.get("reasoning_content")
-                    delta_content = delta.get("content") or delta.get("reasoning_content")
-
-                    assistant_message_tool_calls = None
-
-                    if "tool_calls" in delta and credentials.get("function_calling_type", "no_call") == "tool_call":
-                        assistant_message_tool_calls = delta.get("tool_calls", None)
-                    elif (
-                        "function_call" in delta
-                        and credentials.get("function_calling_type", "no_call") == "function_call"
-                    ):
-                        assistant_message_tool_calls = [
-                            {"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)
-                        increase_tool_call(tool_calls)
-
-                    if delta_content is None or delta_content == "":
-                        continue
-
-                    # Add markdown quote markers for reasoning content
-                    if is_reasoning:
-                        if not is_reasoning_started:
-                            delta_content = "> 💭 " + delta_content
-                            is_reasoning_started = True
-                        elif "\n\n" in delta_content:
-                            delta_content = delta_content.replace("\n\n", "\n> ")
-                        elif "\n" in delta_content:
-                            delta_content = delta_content.replace("\n", "\n> ")
-                    elif is_reasoning_started:
-                        # If we were in reasoning mode but now getting regular content,
-                        # add \n\n to close the reasoning block
-                        delta_content = "\n\n" + delta_content
-                        is_reasoning_started = False
-
-                    # transform assistant message to prompt message
-                    assistant_prompt_message = AssistantPromptMessage(
-                        content=delta_content,
-                    )
-
-                    # reset tool calls
-                    tool_calls = []
-                    full_assistant_content += delta_content
-                elif "text" in choice:
-                    choice_text = choice.get("text", "")
-                    if choice_text == "":
-                        continue
-
-                    # transform assistant message to prompt message
-                    assistant_prompt_message = AssistantPromptMessage(content=choice_text)
-                    full_assistant_content += choice_text
-                else:
-                    continue
-
-                yield LLMResultChunk(
-                    id=message_id,
-                    model=model,
-                    prompt_messages=prompt_messages,
-                    delta=LLMResultChunkDelta(
-                        index=chunk_index,
-                        message=assistant_prompt_message,
-                    ),
-                )
-
-            chunk_index += 1
-
-        if tools_calls:
-            yield LLMResultChunk(
-                id=message_id,
-                model=model,
-                prompt_messages=prompt_messages,
-                delta=LLMResultChunkDelta(
-                    index=chunk_index,
-                    message=AssistantPromptMessage(tool_calls=tools_calls, content=""),
-                ),
-            )
-
-        yield create_final_llm_result_chunk(
-            id=message_id,
-            index=chunk_index,
-            message=AssistantPromptMessage(content=""),
-            finish_reason=finish_reason,
-            usage=usage,
-        )
@@ -19,8 +19,8 @@ class GoogleProvider(ModelProvider):
        try:
            model_instance = self.get_model_instance(ModelType.LLM)

-            # Use `gemini-pro` model for validate,
-            model_instance.validate_credentials(model="gemini-pro", credentials=credentials)
+            # Use `gemini-2.0-flash` model for validate,
+            model_instance.validate_credentials(model="gemini-2.0-flash", credentials=credentials)
        except CredentialsValidateFailedError as ex:
            raise ex
        except Exception as ex:
@@ -1,4 +1,6 @@
+- 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
@@ -17,5 +19,3 @@
 - gemini-exp-1206
 - gemini-exp-1121
 - gemini-exp-1114
- gemini-pro
- gemini-pro-vision
@@ -0,0 +1,41 @@
+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
@@ -0,0 +1,41 @@
+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
@@ -1,3 +1,4 @@
+- deepseek-r1-distill-llama-70b
 - llama-3.1-405b-reasoning
 - llama-3.3-70b-versatile
 - llama-3.1-70b-versatile
@@ -0,0 +1,36 @@
+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
@@ -1,7 +1,7 @@
 model: Sao10K/L3-8B-Stheno-v3.2
 label:
-  zh_Hans: Sao10K/L3-8B-Stheno-v3.2
-  en_US: Sao10K/L3-8B-Stheno-v3.2
+  zh_Hans: L3 8B Stheno V3.2
+  en_US: L3 8B Stheno V3.2
 model_type: llm
 features:
  - agent-thought
@@ -1,4 +1,5 @@
 # Deepseek Models
+- deepseek/deepseek-r1
 - deepseek/deepseek_v3

 # LLaMA Models
@@ -1,7 +1,7 @@
 model: jondurbin/airoboros-l2-70b
 label:
-  zh_Hans: jondurbin/airoboros-l2-70b
-  en_US: jondurbin/airoboros-l2-70b
+  zh_Hans: Airoboros L2 70B
+  en_US: Airoboros L2 70B
 model_type: llm
 features:
  - agent-thought
@@ -0,0 +1,41 @@
+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
@@ -1,7 +1,7 @@
 model: deepseek/deepseek_v3
 label:
-  zh_Hans: deepseek/deepseek_v3
-  en_US: deepseek/deepseek_v3
+  zh_Hans: DeepSeek V3
+  en_US: DeepSeek V3
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: cognitivecomputations/dolphin-mixtral-8x22b
 label:
-  zh_Hans: cognitivecomputations/dolphin-mixtral-8x22b
-  en_US: cognitivecomputations/dolphin-mixtral-8x22b
+  zh_Hans: Dolphin Mixtral 8x22B
+  en_US: Dolphin Mixtral 8x22B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: google/gemma-2-9b-it
 label:
-  zh_Hans: google/gemma-2-9b-it
-  en_US: google/gemma-2-9b-it
+  zh_Hans: Gemma 2 9B
+  en_US: Gemma 2 9B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: nousresearch/hermes-2-pro-llama-3-8b
 label:
-  zh_Hans: nousresearch/hermes-2-pro-llama-3-8b
-  en_US: nousresearch/hermes-2-pro-llama-3-8b
+  zh_Hans: Hermes 2 Pro Llama 3 8B
+  en_US: 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: sao10k/l3-70b-euryale-v2.1
-  en_US: sao10k/l3-70b-euryale-v2.1
+  zh_Hans: "L3 70B Euryale V2.1\t"
+  en_US: "L3 70B Euryale V2.1\t"
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sao10k/l3-8b-lunaris
 label:
-  zh_Hans: sao10k/l3-8b-lunaris
-  en_US: sao10k/l3-8b-lunaris
+  zh_Hans: "Sao10k L3 8B Lunaris"
+  en_US: "Sao10k L3 8B Lunaris"
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sao10k/l31-70b-euryale-v2.2
 label:
-  zh_Hans: sao10k/l31-70b-euryale-v2.2
-  en_US: sao10k/l31-70b-euryale-v2.2
+  zh_Hans: L31 70B Euryale V2.2
+  en_US: L31 70B Euryale V2.2
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-70b-instruct
 label:
-  zh_Hans: meta-llama/llama-3-70b-instruct
-  en_US: meta-llama/llama-3-70b-instruct
+  zh_Hans: Llama3 70b Instruct
+  en_US: Llama3 70b Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-8b-instruct
 label:
-  zh_Hans: meta-llama/llama-3-8b-instruct
-  en_US: meta-llama/llama-3-8b-instruct
+  zh_Hans: Llama 3 8B Instruct
+  en_US: Llama 3 8B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-70b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.1-70b-instruct
-  en_US: meta-llama/llama-3.1-70b-instruct
+  zh_Hans: Llama 3.1 70B Instruct
+  en_US: Llama 3.1 70B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-8b-instruct-bf16
 label:
-  zh_Hans: meta-llama/llama-3.1-8b-instruct-bf16
-  en_US: meta-llama/llama-3.1-8b-instruct-bf16
+  zh_Hans: Llama 3.1 8B Instruct BF16
+  en_US: Llama 3.1 8B Instruct BF16
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-8b-instruct-max
 label:
-  zh_Hans: meta-llama/llama-3.1-8b-instruct-max
-  en_US: meta-llama/llama-3.1-8b-instruct-max
+  zh_Hans: "Llama3.1 8B Instruct Max\t"
+  en_US: "Llama3.1 8B Instruct Max\t"
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-8b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.1-8b-instruct
-  en_US: meta-llama/llama-3.1-8b-instruct
+  zh_Hans: Llama 3.1 8B Instruct
+  en_US: Llama 3.1 8B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.2-11b-vision-instruct
 label:
-  zh_Hans: meta-llama/llama-3.2-11b-vision-instruct
-  en_US: meta-llama/llama-3.2-11b-vision-instruct
+  zh_Hans: "Llama 3.2 11B Vision Instruct\t"
+  en_US: "Llama 3.2 11B Vision Instruct\t"
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.2-1b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.2-1b-instruct
-  en_US: meta-llama/llama-3.2-1b-instruct
+  zh_Hans: "Llama 3.2 1B Instruct\t"
+  en_US: "Llama 3.2 1B Instruct\t"
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.2-3b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.2-3b-instruct
-  en_US: meta-llama/llama-3.2-3b-instruct
+  zh_Hans: Llama 3.2 3B Instruct
+  en_US: Llama 3.2 3B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.3-70b-instruct
 label:
-  zh_Hans: meta-llama/llama-3.3-70b-instruct
-  en_US: meta-llama/llama-3.3-70b-instruct
+  zh_Hans: Llama 3.3 70B Instruct
+  en_US: Llama 3.3 70B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sophosympatheia/midnight-rose-70b
 label:
-  zh_Hans: sophosympatheia/midnight-rose-70b
-  en_US: sophosympatheia/midnight-rose-70b
+  zh_Hans: Midnight Rose 70B
+  en_US: Midnight Rose 70B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: mistralai/mistral-7b-instruct
 label:
-  zh_Hans: mistralai/mistral-7b-instruct
-  en_US: mistralai/mistral-7b-instruct
+  zh_Hans: Mistral 7B Instruct
+  en_US: Mistral 7B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: mistralai/mistral-nemo
 label:
-  zh_Hans: mistralai/mistral-nemo
-  en_US: mistralai/mistral-nemo
+  zh_Hans: Mistral Nemo
+  en_US: Mistral Nemo
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: gryphe/mythomax-l2-13b
 label:
-  zh_Hans: gryphe/mythomax-l2-13b
-  en_US: gryphe/mythomax-l2-13b
+  zh_Hans: Mythomax L2 13B
+  en_US: Mythomax L2 13B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: nousresearch/nous-hermes-llama2-13b
 label:
-  zh_Hans: nousresearch/nous-hermes-llama2-13b
-  en_US: nousresearch/nous-hermes-llama2-13b
+  zh_Hans: Nous Hermes Llama2 13B
+  en_US: Nous Hermes Llama2 13B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: openchat/openchat-7b
 label:
-  zh_Hans: openchat/openchat-7b
-  en_US: openchat/openchat-7b
+  zh_Hans: OpenChat 7B
+  en_US: OpenChat 7B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: teknium/openhermes-2.5-mistral-7b
 label:
-  zh_Hans: teknium/openhermes-2.5-mistral-7b
-  en_US: teknium/openhermes-2.5-mistral-7b
+  zh_Hans: Openhermes2.5 Mistral 7B
+  en_US: Openhermes2.5 Mistral 7B
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2-72b-instruct
 label:
-  zh_Hans: qwen/qwen-2-72b-instruct
-  en_US: qwen/qwen-2-72b-instruct
+  zh_Hans: Qwen2 72B Instruct
+  en_US: Qwen2 72B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2-7b-instruct
 label:
-  zh_Hans: qwen/qwen-2-7b-instruct
-  en_US: qwen/qwen-2-7b-instruct
+  zh_Hans: Qwen 2 7B Instruct
+  en_US: Qwen 2 7B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2-vl-72b-instruct
 label:
-  zh_Hans: qwen/qwen-2-vl-72b-instruct
-  en_US: qwen/qwen-2-vl-72b-instruct
+  zh_Hans: Qwen 2 VL 72B Instruct
+  en_US: Qwen 2 VL 72B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2.5-72b-instruct
 label:
-  zh_Hans: qwen/qwen-2.5-72b-instruct
-  en_US: qwen/qwen-2.5-72b-instruct
+  zh_Hans: Qwen 2.5 72B Instruct
+  en_US: Qwen 2.5 72B Instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: microsoft/wizardlm-2-8x22b
 label:
-  zh_Hans: microsoft/wizardlm-2-8x22b
-  en_US: microsoft/wizardlm-2-8x22b
+  zh_Hans: Wizardlm 2 8x22B
+  en_US: Wizardlm 2 8x22B
 model_type: llm
 features:
  - agent-thought
@@ -8,7 +8,7 @@ icon_small:
  en_US: icon_s_en.svg
 icon_large:
  en_US: icon_l_en.svg
-background: "#eadeff"
+background: "#c7fce2"
 help:
  title:
    en_US: Get your API key from Novita AI
@@ -1,3 +1,4 @@
+- deepseek-ai/deepseek-r1
 - google/gemma-7b
 - google/codegemma-7b
 - google/recurrentgemma-2b
@@ -0,0 +1,35 @@
+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[model]:
+        if self.MODEL_SUFFIX_MAP.get(model):
            credentials["server_url"] = f"https://ai.api.nvidia.com/v1/{self.MODEL_SUFFIX_MAP[model]}"
            credentials.pop("endpoint_url")
        else:
@@ -0,0 +1,52 @@
+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
@@ -50,3 +50,4 @@ pricing:
  output: '0.004'
  unit: '0.0001'
  currency: USD
+deprecated: true
@@ -0,0 +1,52 @@
+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
@@ -50,3 +50,4 @@ pricing:
  output: '0.0219'
  unit: '0.0001'
  currency: USD
+deprecated: true
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
-LAN-	4b938ab18d	chore: Bump version Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-30 16:25:40 +08:00
-LAN-	88356de923	fix: Refactor web reader to use readabilipy (#19789 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-30 16:23:17 +08:00
-LAN-andGitHub	5f09900dca	chore(api): Upgrade dependencies (#19736 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-15 14:47:15 +08:00
-LAN-	9ac99abf20	docs(CHANGELOG): Update CHANGELOG Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-14 18:03:05 +08:00
-LAN-	32588f562e	feat(model): fix and re-add gpt-4.1. Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-14 18:02:32 +08:00
JoelandGitHub	36f8bd3f1a	chore: frontend third-part package security issue (#19655 )	2025-05-14 14:08:05 +08:00
-LAN-	c919074e06	docs(CHANGELOG.md): Update CHANGELOG.md Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-13 10:31:40 +08:00
kelvintsim GitHub crazywoola Bowen Liang	88cd9aedb7	add gunicorn keepalive setting (#19537 ) Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: Bowen Liang <liang.bowen.123@qq.com>	2025-05-13 10:28:13 +08:00
-LAN-	16a4f77fb4	fix(config): Allow DB_EXTRAS to set search_path via options Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-13 10:19:08 +08:00
-LAN-andGitHub	3401c52665	chore(pyproject.toml): Upgrade huggingface-hub, transformers and resend (#19563 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-05-12 23:21:57 +08:00
Zixuan ChengandGitHub	4fa3d78ed8	Revert "feat : add GPT4.1 in the model providers" (#19002 )	2025-04-28 18:15:24 +08:00
-LAN-	5f7f851b17	fix: Refines None checks in result transformation Simplifies the code by replacing type checks for None with direct comparisons, improving readability and consistency in handling None values during output validation. Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-28 15:40:14 +08:00
-LAN-	559ab46ee1	fix: Removes redundant token calculations and updates dependencies Eliminates unnecessary pre-calculation of token limits and recalculation of max tokens across multiple app runners, simplifying the logic for prompt handling. Updates tiktoken library from version 0.8.0 to 0.9.0 for improved tokenization performance. Increases default token limit in TokenBufferMemory to accommodate larger prompt messages. These changes streamline the token management process and leverage the latest improvements in the tiktoken library. Fixes potential token overflow issues and prepares the system for handling larger inputs more efficiently. Relates to internal optimization tasks. Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-28 15:39:12 +08:00
-LAN-	df98223c8c	chore: Updates to version 0.15.7 with new model support Adds support for GPT-4.1 and Amazon Bedrock DeepSeek-R1 models. Fixes issues with app creation from template categories and DSL version checks. Updates version numbers in configuration files and Docker setup to 0.15.7 for consistency. Addresses issues #18807, #18868, #18872, #18878, and #18912. Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-28 14:19:07 +08:00
Zixuan ChengandGitHub	144f9507f8	feat : add GPT4.1 in the model providers (#18912 )	2025-04-27 19:31:20 +08:00
kelvintsimandGitHub	2e097a1ac0	add bedrock deepseek-r1 (#18908 )	2025-04-27 19:30:42 +08:00
NFishandGitHub	9f7d8a981f	Patch: hotfix/create from template category (#18807 ) (#18868 )	2025-04-27 14:47:18 +08:00
zxhlyhandGitHub	40b31bafd5	fix: check dsl version when create app from explore template (#18872 ) (#18878 )	2025-04-27 14:21:45 +08:00
-LAN-	d38a2c95fb	docs(CHANGELOG): Update CHANGELOG.md Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-25 18:31:08 +08:00
-LAN-	7d18e2a0ef	feat(app_dsl_service): Refines version compatibility logic Updates logic to handle various version comparisons, ensuring more precise status returns based on version differences. Improves handling of older and newer versions to prevent mismatches and ensure appropriate compatibility status. Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-25 18:27:31 +08:00
kelvintsimandGitHub	024f242251	add bedrock claude-sonnet-3.7 (#18788 )	2025-04-25 17:35:12 +08:00
-LAN-	bfdce78ca5	chore(*): Bump up to 0.15.6 Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-23 14:06:46 +08:00
-LAN-	00c2258352	CHANGELOG): Adds initial changelog for version 0.15.6 Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-04-23 13:55:33 +08:00
JoelandGitHub	a1b3d41712	fix: clickjacking (#18552 )	2025-04-22 17:08:52 +08:00
kautsar_masuara GitHub achmad-kautsar	b26e20fe34	fix: fix vertex gemini 2.0 flash 001 schema (#18405 ) Co-authored-by: achmad-kautsar <achmad.kautsar@insignia.co.id>	2025-04-19 22:04:13 +08:00
NFishandGitHub	161ff432f1	fix: update reset password token when email code verify success (#18362 )	2025-04-18 17:15:15 +08:00
Xiyuan ChenandGitHub	99a9def623	fix: reset_password security issue (#18366 )	2025-04-18 05:04:44 -04:00
Alexi.FandGitHub	fe1846c437	fix: change gemini-2.0-flash to validate google api #17082 (#17115 )	2025-03-30 13:04:12 +08:00
-LAN-	8e75eb5c63	fix: update version to 0.15.5 in packaging and docker-compose files Sgned-off-by: -LAN- <lapz8200@outlook.com>	2025-03-24 16:47:06 +08:00
-LAN-	970508fcb6	fix: update GitHub Actions workflow to trigger on tags Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-03-24 16:45:29 +08:00
NFish	9283a5414f	fix: update yarn.lock	2025-03-24 16:41:07 +08:00
-LAN-	2a2a0e9be9	fix: update DifySandbox image version to 0.2.11 in docker-compose files Sgned-off-by: -LAN- <laipz8200@outlook.com>	2025-03-24 15:37:55 +08:00
JoelandGitHub	061a765b7d	fix: sanitizer svg to avoid xss (#16608 )	2025-03-24 14:48:40 +08:00
-LAN-	acd7fead87	feat: remove Vanna provider and associated assets from the project Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-03-24 14:34:03 +08:00
NFish	bbb080d5b2	fix: update chatbot help doc link on the create app form	2025-03-24 11:28:35 +08:00
NFish	c01d8a70f3	fix: upgrade nextjs to v14.2.25. a security patch for CVE-2025-29927.	2025-03-24 10:32:18 +08:00
-LAN-	1ca15989e0	chore: update version to 0.15.4 in configuration and docker files Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-03-21 16:39:06 +08:00
-LAN-	8b5a3a9424	Merge branch 'release/0.15.4' of github.com:langgenius/dify into release/0.15.4	2025-03-21 16:31:06 +08:00
-LAN-	42ddcf1edd	chore: remove 0.15.3 branch config in the build action Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-03-21 16:30:33 +08:00
JoelandGitHub	21561df10f	fix: xss in render svg (#16437 )	2025-03-21 15:24:58 +08:00
crazywoola	0e33a3aa5f	chore: add ci	2025-02-19 14:34:36 +08:00
Hash Brownandcrazywoola	d3895bcd6b	revert	2025-02-19 14:32:28 +08:00
Hash Brownandcrazywoola	eeb390650b	fix: build failed	2025-02-19 14:32:28 +08:00
-LAN-andGitHub	ca19bd31d4	chore(*): Bump version to 0.15.3 (#13308 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 15:20:05 +08:00
-LAN-andGitHub	413dfd5628	feat: add completion mode and context size options for LLM configuration (#13325 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 15:08:53 +08:00
-LAN-andGitHub	f9515901cc	fix: Azure AI Foundry model cannot be used in the workflow (#13323 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 14:52:57 +08:00
呆萌闷油瓶andGitHub	3f42fabff8	chore:improve thinking display for llm from xinference and ollama pro… (#13318 )	2025-02-07 14:29:29 +08:00
-LAN-andGitHub	1caa578771	chore(*): Update style of thinking (#13319 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 14:06:35 +08:00
Lazy_Frog GitHub Novice Lee	b7c11c1818	Fix the problem of Workflow terminates after parallel tasks execution, merge node not triggered (#12498 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-02-07 13:56:08 +08:00
非法操作andGitHub	3eb3db0663	chore: refactor the OpenAICompatible and improve thinking display (#13299 )	2025-02-07 13:28:46 +08:00
-LAN-andGitHub	be46f32056	fix(credits): require model name equals (#13314 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 13:28:17 +08:00
sinoandGitHub	6e5c915f96	feat(model): add deepseek-r1 for openrouter (#13312 )	2025-02-07 12:39:13 +08:00
-LAN-andGitHub	04d13a8116	feat(credits): Allow to configure model-credit mapping (#13274 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-07 11:01:31 +08:00
KemalandGitHub	e638ede3f2	Update README_TR.md (#13294 )	2025-02-07 09:11:39 +08:00
Riddhimaan-SenapatiandGitHub	2348abe4bf	feat: added a couple of models not defined in vertex ai, that were already … (#13296 )	2025-02-07 09:11:25 +08:00
呆萌闷油瓶andGitHub	f7e7a399d9	feat:add think tag display for xinference deepseek r1 (#13291 )	2025-02-06 22:04:58 +08:00
le0zhandGitHub	ba91f34636	fix: incorrect transferMethod assignment for remote file (#13286 )	2025-02-06 19:32:21 +08:00
zhu-an GitHub zhaoqingyu.1075	16865d43a8	feat: add deepseek models for volcengine provider (#13283 ) Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>	2025-02-06 18:20:03 +08:00
呆萌闷油瓶andGitHub	0d13aee15c	feat:add deepseek r1 think display for ollama provider (#13272 )	2025-02-06 15:32:10 +08:00
Wu TianweiandGitHub	49b4144ffd	fix: add dataset edit permissions (#13223 )	2025-02-06 14:26:16 +08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	186e2d972e	chore(deps): bump katex from 0.16.10 to 0.16.21 in /web (#13270 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-02-06 13:27:07 +08:00
engchina GitHub engchina	40dd63ecef	Upgrade oracle models (#13174 ) Co-authored-by: engchina <atjapan2015@gmail.com>	2025-02-06 13:24:27 +08:00
-LAN-andGitHub	6d66d6da15	feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-06 13:03:19 +08:00
weiwenyan-dev GitHub ex_wenyan.wei	03ec3513f3	Fix bug large data no render (#12683 ) Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com>	2025-02-06 13:00:04 +08:00
-LAN-andGitHub	87763fc234	feat(model_providers): Support deepseek for Azure AI Foundry (#13267 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-06 12:45:48 +08:00
JasonVVandGitHub	f6c44cae2e	feat(model): add gemini-2.0 model (#13266 )	2025-02-06 12:28:59 +08:00
xheandGitHub	da2ee04fce	fix: correct linewrap think display in generic openai api (#13260 ) Signed-off-by: xhe <xw897002528@gmail.com>	2025-02-06 10:53:08 +08:00
JasonVVandGitHub	7673c36af3	feat(model): add gemini-2.0-flash-thinking-exp-01-21 (#13230 )	2025-02-06 10:01:00 +08:00
Riddhimaan-SenapatiandGitHub	9457b2af2f	feat: added models :gemini 2.0 flash 001 and gemini 2.0 pro exp 02-05 (#13247 )	2025-02-06 09:58:39 +08:00
k-zakuandGitHub	7203991032	feat: add parameter "reasoning_effort" and Openai o3-mini (#13243 )	2025-02-06 09:29:48 +08:00
xheandGitHub	5a685f7156	feat: add think display for volcengine and generic openapi (#13234 ) Signed-off-by: xhe <xw897002528@gmail.com>	2025-02-06 09:24:40 +08:00
Riddhimaan-SenapatiandGitHub	a6a25030ad	fix: updated _position.yaml to include the latest model already integ… (#13245 )	2025-02-06 09:21:51 +08:00
Riddhimaan-SenapatiandGitHub	00458a31d5	feat: added deepseek r1 and v3 to siliconflow (#13238 )	2025-02-05 21:59:18 +08:00
-LAN-andGitHub	c6ddf6d6cc	feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-05 19:15:29 +08:00
Joshbly GitHub crazywoola	34b21b3065	feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129 ) Co-authored-by: crazywoola <427733928@qq.com>	2025-02-05 17:04:45 +08:00
Bowen LiangandGitHub	8fbb355cd2	chore: squash system dependencies installation steps (#13206 )	2025-02-05 16:42:53 +08:00
HQideaandGitHub	e8b3b7e578	Fix new variables in the conversation opener would override prompt_variables (#13191 )	2025-02-05 16:16:00 +08:00
-LAN-andGitHub	59ca44f493	chore(model_runtime): Move deepseek ahead in the providers list. (#13197 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-05 16:08:28 +08:00
Bowen LiangandGitHub	9e1457c2c3	fix: mypy checks violation in AzureBlobStorage (#13215 )	2025-02-05 15:56:23 +08:00
te-chanandGitHub	fac83e14bc	Use DefaultAzureCredential for managed identity in azure blob extention (#11559 )	2025-02-05 13:43:43 +08:00
Nam VuandGitHub	a97cec57e4	fix: SSRF proxy file descriptor leak in concurrent requests (#13108 )	2025-02-05 13:10:27 +08:00
Riddhimaan-SenapatiandGitHub	38c10b47d3	Feat: add linkedin to readme (#13203 )	2025-02-05 12:27:58 +08:00
MaFee921andGitHub	1a2523fd15	feat: bedrock_endpoint_url (#12838 )	2025-02-05 12:24:24 +08:00
Warren ChenandGitHub	03243cb422	Modify params for bedrock retrieve generate (#13182 )	2025-02-05 12:17:42 +08:00
Bowen LiangandGitHub	2ad7ee0344	chore: add tests for build docker image when dockerfile changed (#10732 )	2025-02-05 11:40:22 +08:00
Riddhimaan-Senapati GitHub crazywoola	55ce3618ce	fix: Dollar Sign Handling in Markdown (#13178 ) Co-authored-by: crazywoola <427733928@qq.com>	2025-02-05 11:00:56 +08:00
TechnoHouseandGitHub	e9e34c1ab2	Install apt dependencies using bookworm source, consistent with base image. Remove unnecessary, error-prone pins (#13176 )	2025-02-05 10:07:22 +08:00
-LAN-andGitHub	d4c916b496	chore(pyproject): Add type stubs into `pyproject.toml` (#13145 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-04 12:01:28 +08:00
Obada KhaliliandGitHub	8fbc9c9342	Solve circular dependency issue between `workflow/constants.ts` file and `default.ts` file (#13165 )	2025-02-04 09:26:01 +08:00
aplioandGitHub	1b6fd9dfe8	fix: set indexing technique from dataset during update-by-text (#13155 )	2025-02-03 11:06:03 +08:00
非法操作andGitHub	304467e3f5	fix: not install libmagic raise error (#13146 )	2025-02-03 11:05:20 +08:00
Kei YAMAZAKIandGitHub	7452032d81	add azure openai api version 2024-12-01-preview (#13135 )	2025-02-03 11:04:20 +08:00
aplioandGitHub	87e2048f1b	nitpick: fix small typos in template.en.mdx (#13156 )	2025-02-03 11:03:11 +08:00
Nam VuandGitHub	d876084392	chore: upgrade libldap2 (#13158 )	2025-02-03 11:02:14 +08:00
非法操作andGitHub	840729afa5	feat: the think tag display of siliconflow's deepseek r1 (#13153 )	2025-02-02 21:55:13 +08:00
Obada KhaliliandGitHub	941ad03f3c	pass model and cost so that langfuse can show cost (#13117 )	2025-02-02 15:27:27 +08:00
aplioandGitHub	d73d191f99	feature. add feat to modify metadata via dataset api (#13116 )	2025-02-02 15:27:12 +08:00
Masashi TomookaandGitHub	c2664e0283	chore: fix wrong VectorType match case (#13123 )	2025-02-02 15:26:59 +08:00
-LAN-andGitHub	ee61cede4e	test(huggingface_hub): Skip the failed test temporarily. (#13142 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-02 14:47:26 +08:00
-LAN-andGitHub	b47669b80b	fix: deduct LLM quota after processing invoke result (#13075 ) Signed-off-by: -LAN- <laipz8200@outlook.com>	2025-02-02 12:05:11 +08:00
Hash Brown GitHub zuodongxu	c0d0c63592	feat: switch to chat messages before regenerated (#11301 ) Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com>	2025-01-31 13:05:10 +08:00
Yingchun LaiandGitHub	b09c39c8dc	refactor: avoid to use extra space when finding model by name (#13043 )	2025-01-30 15:08:29 +08:00
heysztandGitHub	b4b09ddc3c	add tongyi qwen2.5-14b/7b-instruct-1m model (#13089 )	2025-01-29 11:58:01 +08:00
Ademílson TonatoandGitHub	d0a21086bd	refactor: Update Firecrawl API parameters and default settings (#13082 )	2025-01-29 11:21:05 +08:00
Yingchun LaiandGitHub	d44882c1b5	refactor: reduce duplciate code by inheritance (#13073 )	2025-01-28 10:52:01 +08:00
Yingchun LaiandGitHub	23c68efa2d	fix: fix the formatter is not applied on log file (#12704 )	2025-01-28 10:49:58 +08:00
JasonandGitHub	560c5de1b7	Fixed Novita AI color and added DeepSeek R1 model (#13074 )	2025-01-28 10:38:54 +08:00
Abdullah AlOsaimi GitHub Abdullah AlOsaimi	5d91dbd000	Set default LOG_LEVEL to INFO for celery workers and beat (#13066 ) Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com>	2025-01-27 17:09:41 +08:00
heysztandGitHub	6c31ee36cd	fix qwen-vl blocking mode (#13052 )	2025-01-27 11:35:23 +08:00
jiandanfengandGitHub	edc29780ed	fix: "Model schema not found" error only in agents (#12655 ) (#12760 )	2025-01-27 11:33:13 +08:00
yjc980121andGitHub	aad7e4dd1c	fix:Improve MIME type detection for remote URL uploads using python-magic (#12693 )	2025-01-27 11:33:03 +08:00
Xin ZhangandGitHub	a6a727e8a4	feat: add inner API to create workspace without requiring email (#13021 )	2025-01-26 15:36:56 +08:00
NFishandGitHub	d1fc65fabc	fix: adjust iteration node dark style (#13051 )	2025-01-26 11:19:41 +08:00