Merge branch 'baidubce:master' into master

README.md

@@ -111,7 +111,7 @@ template_str = "你扮演{role}, 请回答我的问题。\n\n问题：{question}
 # 定义输入，调用playground组件
 input = appbuilder.Message({"role": "java工程师", "question": "请简要回答java语言的内存回收机制是什么，要求100字以内"})
 
-playground = appbuilder.Playground(prompt_template=template_str, model="Qianfan-Agent-Speed-8k")
+playground = appbuilder.Playground(prompt_template=template_str, model="Qianfan-Agent-Speed-8K")
 
 # 以打字机的方式，流式展示大模型回答内容
 output = playground(input, stream=True, temperature=1e-10)

cookbooks/components/agent_runtime.ipynb

@@ -429,7 +429,7 @@
     "class PlaygroundWithHistory(Component):\n",
     "    def __init__(self):\n",
     "        super().__init__()\n",
-    "        self.query_rewrite = QueryRewrite(model=\"Qianfan-Agent-Speed-8k\")\n",
+    "        self.query_rewrite = QueryRewrite(model=\"Qianfan-Agent-Speed-8K\")\n",
     "        self.playground = Playground(\n",
     "            prompt_template=\"{query}\",\n",
     "            model=\"ERNIE-Bot\"\n",

cookbooks/components/rag_with_baidusearch.ipynb

@@ -82,8 +82,8 @@
     "friendly = False # 友好度提升\n",
     "cite = True # 溯源\n",
     "\n",
-    "# 使用 Qianfan-Agent-Speed-8k 模型\n",
-    "component = appbuilder.RAGWithBaiduSearch(model=\"Qianfan-Agent-Speed-8k\")\n",
+    "# 使用 Qianfan-Agent-Speed-8K 模型\n",
+    "component = appbuilder.RAGWithBaiduSearch(model=\"Qianfan-Agent-Speed-8K\")\n",
     "query = appbuilder.Message(\"海淀区的面积是多少\")\n",
     "\n",
     "answer = component.run(\n",

cookbooks/components/text_generation.ipynb

@@ -101,7 +101,7 @@
     "商品信息：\n",
     "'''\n",
     "# 创建商品信息生成组件\n",
-    "product_information_generation = Playground(prompt_template=prompt_template, model='Qianfan-Agent-Speed-8k')\n",
+    "product_information_generation = Playground(prompt_template=prompt_template, model='Qianfan-Agent-Speed-8K')\n",
     "\n",
     "# 获取商品信息\n",
     "# 填充prompt_template参数的参数映射表，需要与prompt_template对应\n",
@@ -152,7 +152,7 @@
     "from appbuilder import QAPairMining\n",
     "\n",
     "# 初始化问答对生成组件\n",
-    "qa_pair_mining = QAPairMining(model='Qianfan-Agent-Speed-8k')\n",
+    "qa_pair_mining = QAPairMining(model='Qianfan-Agent-Speed-8K')\n",
     "\n",
     "# 获取问答对\n",
     "response = qa_pair_mining(Message(product_information), stream=False, temperature=1e-10)\n",
@@ -210,7 +210,7 @@
     "'''\n",
     "\n",
     "# 初始化风格写作组件\n",
-    "style_writing = StyleWriting(model='Qianfan-Agent-Speed-8k')\n",
+    "style_writing = StyleWriting(model='Qianfan-Agent-Speed-8K')\n",
     "\n",
     "# 获取小红书文案\n",
     "response = style_writing(Message(query), style_query='小红书', length=300)\n",
@@ -260,7 +260,7 @@
     "from appbuilder import TagExtraction\n",
     "\n",
     "# 初始化标签抽取组件\n",
-    "tag_extraction = TagExtraction(model='Qianfan-Agent-Speed-8k')\n",
+    "tag_extraction = TagExtraction(model='Qianfan-Agent-Speed-8K')\n",
     "\n",
     "# 获取标签\n",
     "response = tag_extraction(Message(copywriting), stream=False, temperature=1e-10)\n",

cookbooks/end2end_application/rag/rag.ipynb

@@ -171,7 +171,7 @@
     "具备团队协作精神，能够与团队成员有效沟通，共同推进项目进展。'''\n",
     "\n",
     "# 标签抽取的组件\n",
-    "tagger = appbuilder.TagExtraction(model=\"Qianfan-Agent-Speed-8k\")\n",
+    "tagger = appbuilder.TagExtraction(model=\"Qianfan-Agent-Speed-8K\")\n",
     "\n",
     "# 从JD抽取标签并打印\n",
     "tags = tagger(appbuilder.Message(job_desc))\n",
@@ -234,7 +234,7 @@
     "\n",
     "play = appbuilder.Playground(\n",
     "    prompt_template=\"基于候选人姓名、职责描述和简历内容，概括一下{name}的推荐理由。\\n候选人姓名: {name}\\n职责描述: {JD}\\n简历内容: {resume}\\n推荐理由: \",\n",
-    "    model=\"Qianfan-Agent-Speed-8k\"\n",
+    "    model=\"Qianfan-Agent-Speed-8K\"\n",
     ")\n",
     "\n",
     "resume_summary = play(appbuilder.Message({\"JD\": job_desc, \"name\": sorted_resumes[0][0], \"resume\": \"\\n\".join(list(resume_content[sorted_resumes[0][0]]))}))\n",

docs/BasisModule/Components/gbi/nl2sql/README.md

@@ -59,7 +59,7 @@ print(f"llm result: {nl2sql_result_message.content.llm_result}")
 ## 参数说明
 
 ### 初始化参数
-- model_name:  支持的模型名字 ERNIE-Bot 4.0, ERNIE-Bot, ERNIE-Bot-turbo, Qianfan-Agent-Speed-8k
+- model_name:  支持的模型名字 ERNIE-Bot 4.0, ERNIE-Bot, ERNIE-Bot-turbo, Qianfan-Agent-Speed-8K
 - table_schemas: 表的 schema，例如:
 
 ```

docs/BasisModule/Components/gbi/select_table/README.md

@@ -51,7 +51,7 @@ print(f"选的表是: {select_table_result_message.content}")
 
 ## 参数说明
 ### 初始化参数
-- model_name: 支持的模型名字 ERNIE-Bot 4.0, ERNIE-Bot, ERNIE-Bot-turbo, Qianfan-Agent-Speed-8k
+- model_name: 支持的模型名字 ERNIE-Bot 4.0, ERNIE-Bot, ERNIE-Bot-turbo, Qianfan-Agent-Speed-8K
 - table_descriptions: 表的描述是个字典，key: 是表的名字, value: 是表的描述，例如:
 
 ```

docs/BasisModule/Components/llms/dialog_summary/README.md

@@ -23,7 +23,7 @@ import os
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = "bce-YOURTOKEN"
 
-dialog_summary = appbuilder.DialogSummary("Qianfan-Agent-Speed-8k")
+dialog_summary = appbuilder.DialogSummary("Qianfan-Agent-Speed-8K")
 text = "用户:喂我想查一下我的话费\n坐席:好的女士您话费余的话还有87.49元钱\n用户:好的知道了谢谢\n坐席:嗯不客气祝您生活愉快再见"
 answer = dialog_summary(appbuilder.Message(text))
 print(answer)

docs/BasisModule/Components/llms/hallucination_detection/README.md

@@ -37,8 +37,8 @@ context = \
 很多怕胖的女生看到猪皮就怕怕，但其实猪皮含有大量胶原蛋白，营养价值很高呢！这里红通通的猪皮还经过韩国秘制酱汁处理过，会有一点点辣味。烤猪皮的时候也需特别注意火侯，这样吃起来才会有外脆内Q的口感！'''
 answer = '澳门新麻蒲烤肉店并不是每天开门。'
 
-#! 该组件推荐使用Qianfan-Agent-Speed-8k模型。
-hallucination_detection = appbuilder.HallucinationDetection('Qianfan-Agent-Speed-8k')
+#! 该组件推荐使用Qianfan-Agent-Speed-8K模型。
+hallucination_detection = appbuilder.HallucinationDetection('Qianfan-Agent-Speed-8K')
 inputs = {'query': query, 'context': context, 'answer': answer}
 msg = appbuilder.Message(inputs)
 result = hallucination_detection.run(msg)
@@ -58,7 +58,7 @@ os.environ["APPBUILDER_TOKEN"] = "bce-YOURTOKEN"
 ### 初始化参数
 | 参数名称 | 参数类型 | 是否必须 | 描述 | 示例值 |
 | ------- | ------- | -------- | -------- | -------- |
-| `model` | str | 是 | 模型名称，用于指定要使用的千帆模型。推荐使用Qianfan-Agent-Speed-8k模型。 | Qianfan-Agent-Speed-8k |
+| `model` | str | 是 | 模型名称，用于指定要使用的千帆模型。推荐使用Qianfan-Agent-Speed-8K模型。 | Qianfan-Agent-Speed-8K |
 | `secret_key` | str | 否 | 用户鉴权token，默认从环境变量中获取: `os.getenv("APPBUILDER_TOKEN", "")` | bce-v3/XXX |
 | `gateway` | str | 否 | 后端网关服务地址，默认从环境变量中获取: `os.getenv("GATEWAY_URL", "")` | https://appbuilder.baidu.com |
 | `lazy_certification` | bool | 否 | 延迟认证，为True时在第一次运行时认证。默认为False。 | False |

docs/BasisModule/Components/llms/is_complex_query/README.md

@@ -21,7 +21,7 @@ import appbuilder
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = "..."
 
-is_complex_query = appbuilder.IsComplexQuery(model="Qianfan-Agent-Speed-8k")
+is_complex_query = appbuilder.IsComplexQuery(model="Qianfan-Agent-Speed-8K")
 
 msg = "吸塑包装盒在工业化生产和物流运输中分别有什么重要性？"
 msg = appbuilder.Message(msg)
@@ -42,7 +42,7 @@ os.environ["APPBUILDER_TOKEN"] = "bce-YOURTOKEN"
 ### 初始化参数
 |参数名称 |参数类型 |是否必须 |描述 |示例值|
 |--------|--------|--------|----|------|
-|model |str  |是 |模型名称，用于指定要使用的千帆模型|Qianfan-Agent-Speed-8k|
+|model |str  |是 |模型名称，用于指定要使用的千帆模型|Qianfan-Agent-Speed-8K|
 
 ### 调用参数
 |参数名称 |参数类型 |是否必须 |描述 |示例值|

docs/BasisModule/Components/llms/mrc/README.md

@@ -9,7 +9,7 @@ MRC（阅读理解问答模块）是一项先进的自然语言处理功能，
 ### 特色优势
 我们的MRC模块，基于百度自研的先进语言模型文新一言，提供了一系列强大的阅读理解问答功能。在保持文本理解和问题回答的高精度的同时，
 我们特别强调了答案的质量和交互体验。以下是我们MRC模块的几个主要功能特色：
- - 1.多版本模型支持：我们的MRC模块包括不同版本的文新一言大模型，Erniebot 4.0、Qianfan-Agent-Speed-8k等，每个版本都针对特定的应用场景进行了优化。 用户可以根据自己的需求选择最适合的模型版本，以获得最佳的性能。
+ - 1.多版本模型支持：我们的MRC模块包括不同版本的文新一言大模型，Erniebot 4.0、Qianfan-Agent-Speed-8K等，每个版本都针对特定的应用场景进行了优化。 用户可以根据自己的需求选择最适合的模型版本，以获得最佳的性能。
  - 2.答案格式的多样性：
    - 拒答功能：当问题超出模型知识范围或不具体时，模型可以选择不回答，避免提供误导性信息。
    - 澄清功能：对于模棱两可或含糊的问题，模型可以请求更多信息或对问题进行澄清，以确保答案的准确性。
@@ -41,7 +41,7 @@ import os
 os.environ["APPBUILDER_TOKEN"] = "..."
 
 # 创建MRC对象
-mrc_component = appbuilder.MRC(model="Qianfan-Agent-Speed-8k")
+mrc_component = appbuilder.MRC(model="Qianfan-Agent-Speed-8K")
 
 # 初始化参数
 msg = "残疾人怎么办相关证件"
@@ -119,7 +119,7 @@ import os
 os.environ["APPBUILDER_TOKEN"] = '...'
 
 # 创建MRC对象
-mrc_component = appbuilder.MRC(model="Qianfan-Agent-Speed-8k")
+mrc_component = appbuilder.MRC(model="Qianfan-Agent-Speed-8K")
 
 # 初始化参数
 msg = "残疾人怎么办相关证件"

docs/BasisModule/Components/llms/nl2pandas/README.md

@@ -30,7 +30,7 @@ query = "海淀区有哪些学校"
 query = appbuilder.Message(query)
 
 #定义并运行Nl2pandas实例，得到结果
-nl2pandas = appbuilder.Nl2pandasComponent(model="Qianfan-Agent-Speed-8k")
+nl2pandas = appbuilder.Nl2pandasComponent(model="Qianfan-Agent-Speed-8K")
 answer = nl2pandas(query, table_info = table_info)
 ```
 

docs/BasisModule/Components/llms/oral_query_generation/README.md

@@ -28,8 +28,8 @@ text = ('文档标题：在OPPO Reno5上使用视频超级防抖\n'
         '防抖后手机屏幕将出现超级防抖Pro开关，点击即可开启或关闭。 除此之外，前置视频同样加持防抖算法，边走边拍也能稳定聚焦脸部'
         '，实时视频分享您的生活。')
 
-#! 该组件推荐使用Qianfan-Agent-Speed-8k模型。
-oral_query_generation = appbuilder.OralQueryGeneration(model='Qianfan-Agent-Speed-8k')
+#! 该组件推荐使用Qianfan-Agent-Speed-8K模型。
+oral_query_generation = appbuilder.OralQueryGeneration(model='Qianfan-Agent-Speed-8K')
 result = oral_query_generation(appbuilder.Message(text), query_type='全部', output_format='str')
 
 print(result)
@@ -47,7 +47,7 @@ os.environ["APPBUILDER_TOKEN"] = "bce-YOURTOKEN"
 
 | 参数名称 | 参数类型 | 是否必须 | 描述 | 示例值 |
 | ------- | ------- | -------- | -------- | -------- |
-| `model` | str | 是 | 模型名称，用于指定要使用的千帆模型。推荐使用Qianfan-Agent-Speed-8k模型。 | Qianfan-Agent-Speed-8k |
+| `model` | str | 是 | 模型名称，用于指定要使用的千帆模型。推荐使用Qianfan-Agent-Speed-8K模型。 | Qianfan-Agent-Speed-8K |
 | `secret_key` | str | 否 | 用户鉴权token，默认从环境变量中获取: `os.getenv("APPBUILDER_TOKEN", "")` | bce-v3/XXX |
 | `gateway` | str | 否 | 后端网关服务地址，默认从环境变量中获取: `os.getenv("GATEWAY_URL", "")` | https://appbuilder.baidu.com |
 | `lazy_certification` | bool | 否 | 延迟认证，为True时在第一次运行时认证。默认为False。 | False |

docs/BasisModule/Components/llms/playground/README.md

@@ -26,7 +26,7 @@ os.environ["APPBUILDER_TOKEN"] = "..."
 
 play = appbuilder.Playground(
     prompt_template="你好，{name}，我是{bot_name}，{bot_name}是一个{bot_type}，我可以{bot_function}，你可以问我{bot_question}。",
-    model="Qianfan-Agent-Speed-8k"
+    model="Qianfan-Agent-Speed-8K"
 )
 play(appbuilder.Message({"name": "小明", "bot_name": "小红", "bot_type": "聊天机器人", "bot_function": "聊天", "bot_question": "你好吗？"}), stream=False)
 ```

docs/BasisModule/Components/llms/qa_pair_mining/README.md

@@ -23,7 +23,7 @@ import appbuilder
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = "..."
 
-qa_mining = appbuilder.QAPairMining(model="Qianfan-Agent-Speed-8k")
+qa_mining = appbuilder.QAPairMining(model="Qianfan-Agent-Speed-8K")
 # 输入文本（对此文本挖掘问答对）
 msg = '2017年，工商银行根据外部宏观环境变化，及时调整业务策略，优化资产负债结构，' + \
     '保持存贷款业务协调发展，提升资产负债配置效率。' + \
@@ -110,7 +110,7 @@ split_result = splitter(parse_result)
 
 # 每个段落抽取问答对，并返回结果
 for doc_segment in split_result.content["paragraphs"]:
-    qa_mining = QAPairMining(model="Qianfan-Agent-Speed-8k")
+    qa_mining = QAPairMining(model="Qianfan-Agent-Speed-8K")
     text = doc_segment.get("text", "")
     if text == "":
         logger.error("Text is null. break")

docs/BasisModule/Components/llms/query_decomposition/README.md

@@ -21,7 +21,7 @@ import appbuilder
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = "..."
 
-query_decomposition = appbuilder.QueryDecomposition(model="Qianfan-Agent-Speed-8k")
+query_decomposition = appbuilder.QueryDecomposition(model="Qianfan-Agent-Speed-8K")
 
 msg = "吸塑包装盒在工业化生产和物流运输中分别有什么重要性？"
 msg = appbuilder.Message(msg)
@@ -42,7 +42,7 @@ os.environ["APPBUILDER_TOKEN"] = "bce-YOURTOKEN"
 ### 初始化参数
 |参数名称 |参数类型 |是否必须 |描述 |示例值|
 |--------|--------|--------|----|------|
-|model |str  |是 |模型名称，用于指定要使用的千帆模型|Qianfan-Agent-Speed-8k|
+|model |str  |是 |模型名称，用于指定要使用的千帆模型|Qianfan-Agent-Speed-8K|
 
 ### 调用参数
 |参数名称 |参数类型 |是否必须 |描述 |示例值|

docs/BasisModule/Components/llms/query_rewrite/README.md

@@ -24,7 +24,7 @@ import appbuilder
 os.environ["APPBUILDER_TOKEN"] = '...'
 
 # 初始化并使用 QueryRewrite 组件
-query_rewrite = appbuilder.QueryRewrite(model="Qianfan-Agent-Speed-8k")
+query_rewrite = appbuilder.QueryRewrite(model="Qianfan-Agent-Speed-8K")
 answer = query_rewrite(appbuilder.Message(['我应该怎么办理护照？', '您可以查询官网或人工咨询', '我需要准备哪些材料？', '身份证、免冠照片一张以及填写完整的《中国公民因私出国（境）申请表》', '在哪里办']), rewrite_type="带机器人回复")
 print(answer)
 ```

docs/BasisModule/Components/llms/similar_question/README.md

@@ -23,7 +23,7 @@ import appbuilder
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = "..."
 
-similar_question = appbuilder.SimilarQuestion(model="Qianfan-Agent-Speed-8k")
+similar_question = appbuilder.SimilarQuestion(model="Qianfan-Agent-Speed-8K")
 
 msg = "我想吃冰淇淋，哪里的冰淇淋比较好吃？"
 msg = appbuilder.Message(msg)

docs/BasisModule/Components/llms/style_rewrite/README.md

@@ -33,7 +33,7 @@ import appbuilder
 os.environ["APPBUILDER_TOKEN"] = "..."
 
 # 初始化并使用 StyleRewrite 组件
-style_rewrite = appbuilder.StyleRewrite(model="Qianfan-Agent-Speed-8k")
+style_rewrite = appbuilder.StyleRewrite(model="Qianfan-Agent-Speed-8K")
 answer = style_rewrite(appbuilder.Message("文心大模型发布新版"), style="激励话术")
 ```
 

docs/BasisModule/Components/llms/style_writing/README.md

@@ -26,7 +26,7 @@ import os
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = "..."
 
-model = "Qianfan-Agent-Speed-8k"
+model = "Qianfan-Agent-Speed-8K"
 style_writing = appbuilder.StyleWriting(model)
 
 query = "帮我写一篇关于人体工学椅的文案"

docs/BasisModule/Components/llms/tag_extraction/README.md

@@ -31,7 +31,7 @@ import appbuilder
 # 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5
 os.environ["APPBUILDER_TOKEN"] = '...'
 
-tag_extraction = appbuilder.TagExtraction(model="Qianfan-Agent-Speed-8k")
+tag_extraction = appbuilder.TagExtraction(model="Qianfan-Agent-Speed-8K")
 result = tag_extraction(appbuilder.Message("从这段文本中抽取关键标签"))
 ```
 

docs/BasisModule/Components/rag_with_baidu_search/README.md

@@ -38,7 +38,7 @@ import os
 os.environ["APPBUILDER_TOKEN"] = '...'
 
 # 创建rag_with_baidusearch对象
-rag_with_baidusearch_component = appbuilder.RAGWithBaiduSearch(model="Qianfan-Agent-Speed-8k")
+rag_with_baidusearch_component = appbuilder.RAGWithBaiduSearch(model="Qianfan-Agent-Speed-8K")
 
 # 运行rag_with_baidusearch基本组件
 msg = appbuilder.Message("残疾人怎么办相关证件")
@@ -111,7 +111,7 @@ os.environ["APPBUILDER_TOKEN"] = '...'
 
 # 创建rag_with_baidusearch对象, 并初始化人设指令
 rag_with_baidusearch_component = appbuilder.RAGWithBaiduSearch(
-        model="Qianfan-Agent-Speed-8k", 
+        model="Qianfan-Agent-Speed-8K", 
         instruction=appbuilder.Message("你是问答助手，在回答问题前需要加上: 很高兴为您解答"))
 
 

docs/BasisModule/Components/rag_with_baidu_search_pro/README.md

@@ -26,7 +26,7 @@ import os
 os.environ["APPBUILDER_TOKEN"] = '...'
 
 # 创建rag_with_baidusearch_pro对象
-rag_with_baidu_search_pro = appbuilder.RagWithBaiduSearchPro(model="Qianfan-Agent-Speed-8k")
+rag_with_baidu_search_pro = appbuilder.RagWithBaiduSearchPro(model="Qianfan-Agent-Speed-8K")
 
 # 运行rag_with_baidusearch基本组件
 msg = appbuilder.Message("残疾人怎么办相关证件")
@@ -88,7 +88,7 @@ os.environ["APPBUILDER_TOKEN"] = '...'
 
 # 创建rag_with_baidusearch对象, 并初始化人设指令
 rag_with_baidusearch_pro = appbuilder.RagWithBaiduSearchPro(
-        model="Qianfan-Agent-Speed-8k", 
+        model="Qianfan-Agent-Speed-8K", 
         instruction=appbuilder.Message("你是问答助手，在回答问题前需要加上: 很高兴为您解答"))
 
 

docs/BasisModule/Deployment/agentruntime.md

@@ -120,7 +120,7 @@ os.environ["APPBUILDER_TOKEN"] = 'YOUR_APPBUILDER_TOKEN'
 class PlaygroundWithHistory(Component):
     def __init__(self):
         super().__init__()
-        self.query_rewrite = QueryRewrite(model="Qianfan-Agent-Speed-8k")
+        self.query_rewrite = QueryRewrite(model="Qianfan-Agent-Speed-8K")
         self.play = Playground(
             prompt_template="{query}",
             model="eb-4"

docs/BasisModule/Platform/KnowledgeBase/knowledgebase.md

@@ -300,10 +300,10 @@ class DocumentChoices(BaseModel):
 class DocumentChunker(BaseModel):
     choices: list[str] = Field(..., description="使用哪些chunker方法 (separator | pattern | onePage)，separator：自定义切片—标识符，pattern：自定义切片—标识符中选择正则表达式，onePage：整文件切片")
     prependInfo: list[str] = Field(
-        ...,
+        None,
         description="chunker关联元数据，可选值为title (增加标题), filename(增加文件名)",
     )
-    separator: Optional[DocumentSeparator] = Field(..., description="分隔符配置")
+    separator: Optional[DocumentSeparator] = Field(None, description="分隔符配置")
     pattern: Optional[DocumentPattern] = Field(None, description="正则表达式")
 
 class DocumentSeparator(BaseModel):