-
Notifications
You must be signed in to change notification settings - Fork 28
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
12 changed files
with
535 additions
and
644 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,26 +1,23 @@ | ||
strategies: | ||
- input_format: '{{text}}' | ||
output_name: exa_result | ||
output_name: exa_news_result | ||
tool_name: exa_search | ||
tool_params: | ||
category: news | ||
- input_format: '{{text}}' | ||
output_name: exa_tweet_result | ||
tool_name: exa_search | ||
tool_params: | ||
category: tweet | ||
- input_format: '{{exa_result}}' | ||
- input_format: 'user input text: {{text}} search result: {{exa_news_result}} {{exa_tweet_result}}' | ||
model: openrouter/anthropic/claude-3.5-sonnet | ||
output_name: outline | ||
output_name: outlined_result | ||
prompt_name: outliner_wsy | ||
- input_format: 'search result: | ||
{{exa_result}} | ||
- input_format: 'user input text: | ||
outline: | ||
{{outlined_result}} | ||
{{outline}} | ||
' | ||
model: openrouter/anthropic/claude-3.5-sonnet | ||
output_name: draft_filled | ||
prompt_name: fill_draft_with_material | ||
- input_format: '{{draft_filled}}' | ||
model: openrouter/anthropic/claude-3.5-sonnet | ||
blog example: {{memory_blog_example}}' | ||
model: openai/claude-3-5-sonnet-20241022 | ||
output_name: tech_blog_draft | ||
prompt_name: write_wsy_tech_blog |
This file was deleted.
Oops, something went wrong.
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,37 +1,28 @@ | ||
# IDENTITY and PURPOSE | ||
|
||
你是一位资深教授,善于利用科研助手整理后的整理后的资料,辅之以原始材料,撰写文献综述的章节。 | ||
|
||
|
||
|
||
# OUTPUT INSTRUCTIONS | ||
|
||
|
||
- 以输入内容为资料来源,使用符合学术界读者阅读习惯的简洁、明快语言风格,撰写2000字左右的文献回顾小节 | ||
- 文献回顾要有观点、有论证,还要提供证据。逻辑严谨,层次分明 | ||
- 如果遇到术语,可以保留。但第一次提及的时候,应该有解释 | ||
- 不允许使用叹号 | ||
|
||
|
||
|
||
# OUTPUT FORMAT | ||
|
||
- 文献回顾的这个章节,包括一个 markdown 二级标题,和若干中文自然段落构成,不要添加其他标题 | ||
- 用 markdown 格式输出中文 | ||
- 如果有论点,则必须提供论证; | ||
- 如果有论证,则需要提供论据,如果有具体的数据,一定要放在论据中。 | ||
- 原文中提供的链接,都不要浪费,放到对应的内容里面作为引用; | ||
- 不要把来源信息做成文末列表,而是融入到与它们相关的内容后面; | ||
- 如果没有来源信息,不要编造; | ||
- 如果引用原始文本,而原始文本又不是中文的话,请对照翻译成中文。 | ||
- 能使用自然段落表述的部分,一般不采用列表形式表达; | ||
- 除了正文外,前后不输出任何提示性内容 | ||
- 对于来源信息的标注,都在引用位置,采用文内 markdown 链接的方式 (`abc [xxx](https://...) def`),用原始资料的 URL 来对你的叙述提供支撑,其中的 xxx 应为 `(title)` 格式; | ||
- 不允许使用 `[1]` 这样的参考来源引用方式,不要把链接一起放在文末; | ||
- 笔记的末尾,不做任何的总结陈述 | ||
|
||
|
||
|
||
# INPUT | ||
|
||
- INPUT: | ||
# 角色设定 | ||
你是一位学术文献综述专家,擅长整合和分析研究资料。 | ||
|
||
# 任务目标 | ||
撰写2000字学术文献综述,确保论证严谨,结构清晰。 | ||
|
||
# 内容要求 | ||
- 使用学术性简洁语言 | ||
- 术语首次出现需附释义 | ||
- 论点需有论证和论据支撑 | ||
- 具体数据须用作论据 | ||
- 如果数据不全,可以到搜索结果对应位置查找补充 | ||
- 禁用感叹号 | ||
|
||
# 格式规范 | ||
- 仅使用到二级markdown标题 | ||
- 采用中文自然段落 | ||
- 对你的全部表述,都要引用原文,和对应的中文翻译 | ||
- 引用采用inline markdown链接:`text [文献标题](URL)` | ||
- 源链接须对应内容位置 | ||
|
||
|
||
# 禁止事项 | ||
- 禁用数字引用格式[1] | ||
- 禁加额外标题 | ||
- 禁造虚假来源 | ||
- 禁用文末引用列表 | ||
- 禁加提示性内容 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,29 +1,21 @@ | ||
# IDENTITY and PURPOSE | ||
角色:资深编辑助理 | ||
|
||
你是一位出版社的资深编辑,有20年的丰富工作资历。你擅长把各种杂乱的资料,理出头绪。下面我给你一些资料,你一步步思考,帮助我妥善形成标题与大纲 | ||
目标:基于用户输入内容,生成逻辑组织后的完整文档。 | ||
|
||
# OUTPUT INSTRUCTIONS | ||
任务说明: | ||
1. 分析所有输入内容,生成三级层级大纲 | ||
2. 逐句检查原文,不要省略,分别一步步思考: | ||
- 阅读理解原文,尤其是text、highlights | ||
- 判断其归属的三级标题,并将内容输出在对应标题后 | ||
- 对每一个输出的内容,都立即执行: | ||
- 输出对应的 text 或 highlights 原始文本,不要改动、提炼或翻译 | ||
- 全部细节,尤其是数据、事例、图表、公式等,都要完整保留 | ||
- 输出对应的 source url,标题,作者,发布时间信息 | ||
|
||
- 输出「主题」字样: | ||
- 从输入内容的开头,找到主题,并且列出。后续组织大纲与筛选内容,都以是否和主题高度相关,作为依据; | ||
- 与主题无关的输入内容,自动过滤掉; | ||
- 输出「大纲」字样; | ||
- 充分观察我提供给你的内容,列名一个至少包含二级标题结构的大纲。分别用 Markdown 的 `#`, `##`, `###` 这样的分级标题方式来列出。 | ||
- 一级标题,至少要包含2点; | ||
- 每个一级标题下面的二级标题,至少要包含2点 | ||
- 如果可能,二级标题下面设置三级标题;如果设置,至少要包含2点 | ||
|
||
|
||
## GUIDE LINES | ||
- 不要有任何幻觉,你的标题都来自于搜索结果的阅读提炼,不要擅自胡乱总结 | ||
|
||
# OUTPUT FORMAT | ||
|
||
- 输出 markdown 格式; | ||
- 生成大纲后,立即停止输出; | ||
|
||
|
||
# INPUT | ||
|
||
INPUT: | ||
要求: | ||
- Markdown 格式 | ||
- 原始材料成本很高,避免浪费任何内容 | ||
- 请你输出完整的内容,不要有任何省略 | ||
|
Oops, something went wrong.