Merge branch 'langgenius:main' into main

langgenius · Aug 8, 2024 · 92b6862 · 92b6862
2 parents d5953d1 + ad682c3
commit 92b6862
Show file tree

Hide file tree

Showing 143 changed files with 4,605 additions and 151 deletions.
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
   <a href="https://docs.dify.ai">Documentation</a> ·
-  <a href="https://cal.com/guchenhe/60-min-meeting">Enterprise inquiry</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Enterprise inquiry</a>
 </p>
 
 <p align="center">

diff --git a/README_AR.md b/README_AR.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">الاستضافة الذاتية</a> ·
   <a href="https://docs.dify.ai">التوثيق</a> ·
-  <a href="https://cal.com/guchenhe/60-min-meeting">استفسارات الشركات</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">استفسار الشركات (للإنجليزية فقط)</a>
 </p>
 
 <p align="center">

diff --git a/README_CN.md b/README_CN.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify 云服务</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">自托管</a> ·
   <a href="https://docs.dify.ai">文档</a> ·
-  <a href="https://cal.com/guchenhe/dify-demo">预约演示</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">（需用英文）常见问题解答 / 联系团队</a>
 </div>
 
 <p align="center">

diff --git a/README_ES.md b/README_ES.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-alojamiento</a> ·
   <a href="https://docs.dify.ai">Documentación</a> ·
-  <a href="https://cal.com/guchenhe/dify-demo">Programar demostración</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Consultas empresariales (en inglés)</a>
 </p>
 
 <p align="center">

diff --git a/README_FR.md b/README_FR.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-hébergement</a> ·
   <a href="https://docs.dify.ai">Documentation</a> ·
-  <a href="https://cal.com/guchenhe/dify-demo">Planifier une démo</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Demande d’entreprise (en anglais seulement)</a>
 </p>
 
 <p align="center">

diff --git a/README_JA.md b/README_JA.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">セルフホスティング</a> ·
   <a href="https://docs.dify.ai">ドキュメント</a> ·
-  <a href="https://cal.com/guchenhe/dify-demo">デモの予約</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">企業のお問い合わせ（英語のみ）</a>
 </p>
 
 <p align="center">

diff --git a/README_KR.md b/README_KR.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify 클라우드</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">셀프-호스팅</a> ·
   <a href="https://docs.dify.ai">문서</a> ·
-  <a href="https://cal.com/guchenhe/60-min-meeting">기업 문의</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">기업 문의 (영어만 가능)</a>
 </p>
 
 <p align="center">

diff --git a/README_TR.md b/README_TR.md
@@ -4,7 +4,7 @@
   <a href="https://cloud.dify.ai">Dify Bulut</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Kendi Sunucunuzda Barındırma</a> ·
   <a href="https://docs.dify.ai">Dokümantasyon</a> ·
-  <a href="https://cal.com/guchenhe/60-min-meeting">Kurumsal Sorgu</a>
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Yalnızca İngilizce: Kurumsal Sorgulama</a>
 </p>
 
 <p align="center">

diff --git a/api/Dockerfile b/api/Dockerfile
@@ -12,6 +12,7 @@ ENV POETRY_CACHE_DIR=/tmp/poetry_cache
 ENV POETRY_NO_INTERACTION=1
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 ENV POETRY_VIRTUALENVS_CREATE=true
+ENV POETRY_REQUESTS_TIMEOUT=15
 
 FROM base AS packages
 
@@ -54,6 +55,9 @@ ENV VIRTUAL_ENV=/app/api/.venv
 COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
+# Download nltk data
+RUN python -c "import nltk; nltk.download('punkt')"
+
 # Copy source code
 COPY . /app/api/
 

diff --git a/api/constants/__init__.py b/api/constants/__init__.py
@@ -1,2 +1 @@
-# TODO: Update all string in code to use this constant
-HIDDEN_VALUE = '[__HIDDEN__]'
+HIDDEN_VALUE = '[__HIDDEN__]'
diff --git a/api/constants/languages.py b/api/constants/languages.py
@@ -16,6 +16,7 @@
     'pl-PL': 'Europe/Warsaw',
     'hi-IN': 'Asia/Kolkata',
     'tr-TR': 'Europe/Istanbul',
+    'fa-IR': 'Asia/Tehran',
 }
 
 languages = list(language_timezone_mapping.keys())

diff --git a/api/controllers/console/extension.py b/api/controllers/console/extension.py
@@ -1,6 +1,7 @@
 from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
 
+from constants import HIDDEN_VALUE
 from controllers.console import api
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
@@ -89,7 +90,7 @@ def post(self, id):
         extension_data_from_db.name = args['name']
         extension_data_from_db.api_endpoint = args['api_endpoint']
 
-        if args['api_key'] != '[__HIDDEN__]':
+        if args['api_key'] != HIDDEN_VALUE:
             extension_data_from_db.api_key = args['api_key']
 
         return APIBasedExtensionService.save(extension_data_from_db)

diff --git a/api/core/app/apps/advanced_chat/generate_task_pipeline.py b/api/core/app/apps/advanced_chat/generate_task_pipeline.py
@@ -244,7 +244,11 @@ def _process_stream_response(
         :return:
         """
         for message in self._queue_manager.listen():
-            if hasattr(message.event, 'metadata') and message.event.metadata.get('is_answer_previous_node', False) and publisher:
+            if (message.event
+                    and hasattr(message.event, 'metadata')
+                    and message.event.metadata
+                    and message.event.metadata.get('is_answer_previous_node', False)
+                    and publisher):
                 publisher.publish(message=message)
             elif (hasattr(message.event, 'execution_metadata')
                   and message.event.execution_metadata

diff --git a/api/core/app/segments/factory.py b/api/core/app/segments/factory.py
@@ -75,8 +75,7 @@ def build_segment(value: Any, /) -> Segment:
         return FloatSegment(value=value)
     if isinstance(value, dict):
         # TODO: Limit the depth of the object
-        obj = {k: build_segment(v) for k, v in value.items()}
-        return ObjectSegment(value=obj)
+        return ObjectSegment(value=value)
     if isinstance(value, list):
         # TODO: Limit the depth of the array
         elements = [build_segment(v) for v in value]

diff --git a/api/core/app/segments/segments.py b/api/core/app/segments/segments.py
@@ -85,26 +85,20 @@ def markdown(self) -> str:
 
 class ObjectSegment(Segment):
     value_type: SegmentType = SegmentType.OBJECT
-    value: Mapping[str, Segment]
+    value: Mapping[str, Any]
 
     @property
     def text(self) -> str:
-        # TODO: Process variables.
         return json.dumps(self.model_dump()['value'], ensure_ascii=False)
 
     @property
     def log(self) -> str:
-        # TODO: Process variables.
         return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
 
     @property
     def markdown(self) -> str:
-        # TODO: Use markdown code block
         return json.dumps(self.model_dump()['value'], ensure_ascii=False, indent=2)
 
-    def to_object(self):
-        return {k: v.to_object() for k, v in self.value.items()}
-
 
 class ArraySegment(Segment):
     @property

diff --git a/api/core/entities/provider_configuration.py b/api/core/entities/provider_configuration.py
@@ -8,6 +8,7 @@
 
 from pydantic import BaseModel, ConfigDict
 
+from constants import HIDDEN_VALUE
 from core.entities.model_entities import ModelStatus, ModelWithProviderEntity, SimpleModelProviderEntity
 from core.entities.provider_entities import (
     CustomConfiguration,
@@ -202,7 +203,7 @@ def custom_credentials_validate(self, credentials: dict) -> tuple[Provider, dict
             for key, value in credentials.items():
                 if key in provider_credential_secret_variables:
                     # if send [__HIDDEN__] in secret input, it will be same as original value
-                    if value == '[__HIDDEN__]' and key in original_credentials:
+                    if value == HIDDEN_VALUE and key in original_credentials:
                         credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])
 
         credentials = model_provider_factory.provider_credentials_validate(
@@ -345,7 +346,7 @@ def custom_model_credentials_validate(self, model_type: ModelType, model: str, c
             for key, value in credentials.items():
                 if key in provider_credential_secret_variables:
                     # if send [__HIDDEN__] in secret input, it will be same as original value
-                    if value == '[__HIDDEN__]' and key in original_credentials:
+                    if value == HIDDEN_VALUE and key in original_credentials:
                         credentials[key] = encrypter.decrypt_token(self.tenant_id, original_credentials[key])
 
         credentials = model_provider_factory.model_credentials_validate(

diff --git a/api/core/model_runtime/model_providers/_position.yaml b/api/core/model_runtime/model_providers/_position.yaml
@@ -36,3 +36,4 @@
 - hunyuan
 - siliconflow
 - perfxcloud
+- zhinao
diff --git a/api/core/model_runtime/model_providers/hunyuan/llm/llm.py b/api/core/model_runtime/model_providers/hunyuan/llm/llm.py
@@ -214,7 +214,7 @@ def _handle_stream_chat_response(self, model, credentials, prompt_messages, resp
     def _handle_chat_response(self, credentials, model, prompt_messages, response):
         usage = self._calc_response_usage(model, credentials, response.Usage.PromptTokens,
                                           response.Usage.CompletionTokens)
-        assistant_prompt_message = PromptMessage(role="assistant")
+        assistant_prompt_message = AssistantPromptMessage()
         assistant_prompt_message.content = response.Choices[0].Message.Content
         result = LLMResult(
             model=model,

diff --git a/api/core/model_runtime/model_providers/jina/rerank/jina-reranker-v2-base-multilingual.yaml b/api/core/model_runtime/model_providers/jina/rerank/jina-reranker-v2-base-multilingual.yaml
@@ -1,4 +1,4 @@
 model: jina-reranker-v2-base-multilingual
 model_type: rerank
 model_properties:
-  context_size: 8192
+  context_size: 1024
diff --git a/api/core/model_runtime/model_providers/openai/llm/_position.yaml b/api/core/model_runtime/model_providers/openai/llm/_position.yaml
@@ -1,6 +1,7 @@
 - gpt-4
 - gpt-4o
 - gpt-4o-2024-05-13
+- gpt-4o-2024-08-06
 - gpt-4o-mini
 - gpt-4o-mini-2024-07-18
 - gpt-4-turbo

diff --git a/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml b/api/core/model_runtime/model_providers/openai/llm/gpt-4o-2024-08-06.yaml
@@ -0,0 +1,44 @@
+model: gpt-4o-2024-08-06
+label:
+  zh_Hans: gpt-4o-2024-08-06
+  en_US: gpt-4o-2024-08-06
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 512
+    min: 1
+    max: 16384
+  - 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: '2.50'
+  output: '10.00'
+  unit: '0.000001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml
@@ -1,8 +1,20 @@
-- deepseek-v2-chat
-- qwen2-72b-instruct
-- qwen2-57b-a14b-instruct
-- qwen2-7b-instruct
-- yi-1.5-34b-chat
-- yi-1.5-9b-chat
-- yi-1.5-6b-chat
-- glm4-9B-chat
+- Qwen/Qwen2-72B-Instruct
+- Qwen/Qwen2-57B-A14B-Instruct
+- Qwen/Qwen2-7B-Instruct
+- Qwen/Qwen2-1.5B-Instruct
+- 01-ai/Yi-1.5-34B-Chat
+- 01-ai/Yi-1.5-9B-Chat-16K
+- 01-ai/Yi-1.5-6B-Chat
+- THUDM/glm-4-9b-chat
+- deepseek-ai/DeepSeek-V2-Chat
+- deepseek-ai/DeepSeek-Coder-V2-Instruct
+- internlm/internlm2_5-7b-chat
+- google/gemma-2-27b-it
+- google/gemma-2-9b-it
+- meta-llama/Meta-Llama-3-70B-Instruct
+- meta-llama/Meta-Llama-3-8B-Instruct
+- meta-llama/Meta-Llama-3.1-405B-Instruct
+- meta-llama/Meta-Llama-3.1-70B-Instruct
+- meta-llama/Meta-Llama-3.1-8B-Instruct
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+- mistralai/Mistral-7B-Instruct-v0.2
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v2-chat.yaml
@@ -1,4 +1,4 @@
-model: deepseek-ai/deepseek-v2-chat
+model: deepseek-ai/DeepSeek-V2-Chat
 label:
   en_US: deepseek-ai/DeepSeek-V2-Chat
 model_type: llm

diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-27b-it.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-27b-it.yaml
@@ -0,0 +1,30 @@
+model: google/gemma-2-27b-it
+label:
+  en_US: google/gemma-2-27b-it
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8196
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1.26'
+  output: '1.26'
+  unit: '0.000001'
+  currency: RMB
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-9b-it.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/gemma-2-9b-it.yaml
@@ -0,0 +1,30 @@
+model: google/gemma-2-9b-it
+label:
+  en_US: google/gemma-2-9b-it
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8196
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB
diff --git a/api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml b/api/core/model_runtime/model_providers/siliconflow/llm/glm4-9b-chat.yaml
@@ -1,4 +1,4 @@
-model: zhipuai/glm4-9B-chat
+model: THUDM/glm-4-9b-chat
 label:
   en_US: THUDM/glm-4-9b-chat
 model_type: llm
@@ -24,7 +24,7 @@ parameter_rules:
   - name: frequency_penalty
     use_template: frequency_penalty
 pricing:
-  input: '0.6'
-  output: '0.6'
+  input: '0'
+  output: '0'
   unit: '0.000001'
   currency: RMB
-Original file line number
+Diff line change
@@ Expand Up / @@ -36,3 +36,4 @@ @@
     - hunyuan
     - siliconflow
     - perfxcloud
+    - zhinao