github_mirrors/wiseflow
1
0
Fork 0
mirror of https://github.com/TeamWiseFlow/wiseflow.git synced 2025-01-23 02:20:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
bigbrother666sh 2024-12-26 11:35:29 +08:00
parent de6d5cdbb1
commit 4c9d7a89c1
5 changed files with 71 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@ -2,11 +2,11 @@
**[English](README_EN.md) | [日本語](README_JP.md) | [한국어](README_KR.md)**
🚀 **首席情报官**（Wiseflow）是一个敏捷的信息挖掘工具，可以从网站、微信公众号、社交平台等各种信息源中按设定的关注点提炼讯息，自动做标签归类并上传数据库。
🚀 **首席情报官**（Wiseflow）是一个敏捷的信息挖掘工具，可以从各种给定信源中精准抓取特定信息，依靠大模型的思考与分析能力，无需人工参与。
**我们缺的不是信息，而是从海量信息中过滤噪音，从而让有价值的信息显露出来**
🌱看看首席情报官是如何帮您节省时间，过滤无关信息，并整理关注要点的吧！🌱
🌱看看AI情报官是如何帮您节省时间，过滤无关信息，并整理关注要点的吧！🌱
https://github.com/user-attachments/assets/f6fec29f-2b4b-40f8-8676-8433abb086a7
@ -55,6 +55,8 @@ wiseflow自2024年6月底发布 V0.3.0版本来受到了开源社区的广泛关
🌹 点赞、fork是好习惯 🌹
**windows 用户请提前下载 git bash 工具** [链接](https://git-scm.com/downloads/win)
```bash
git clone https://github.com/TeamWiseFlow/wiseflow.git
```
@ -111,6 +113,18 @@ export VL_MODEL="gpt-4o"
😄 欢迎使用 [AiHubMix邀请链接](https://aihubmix.com?aff=Gp54) 注册 🌹
#### 本地部署大模型服务
以 Xinference 为例，.env 配置可以参考如下：
```bash
# LLM_API_KEY='' 本地服务无需这一项，请注释掉或删除
export LLM_API_BASE='http://127.0.0.1:9997'
export PRIMARY_MODEL=启动的模型 ID
export SECONDARY_MODEL=启动的模型 ID
export VL_MODEL=启动的模型 ID
```
#### 3.2 pocketbase 账号密码配置
```bash
@ -205,7 +219,7 @@ PocketBase作为流行的轻量级数据库，目前已有 Go/Javascript/Python
本项目基于 [Apache2.0](LICENSE) 开源。
商用以及定制合作，请联系 **Email：zm.zhao@foxmail.com**
商用合作，请联系 **Email：zm.zhao@foxmail.com**
- 商用客户请联系我们报备登记，产品承诺永远免费。

22
README_EN.md
View File

@ -2,11 +2,11 @@
**[简体中文](README.md) | [日本語](README_JP.md) | [한국어](README_KR.md)**
🚀 **Chief Intelligence Officer** (Wiseflow) is an agile information mining tool that can extract information from various sources such as websites, WeChat official accounts, and social platforms based on preset focus points, automatically tag and categorize the information, and upload it to the database.
🚀 **Chief Intelligence Officer** (Wiseflow) is an agile information mining tool that can accurately extract specific information from various given sources, relying on the thinking and analytical capabilities of large language models, without human intervention.
**What we lack is not information, but the ability to filter out noise from massive information, thereby revealing valuable information.**
🌱 See how Chief Intelligence Officer helps you save time, filter irrelevant information, and organize key points of interest! 🌱
🌱 See how AI Intelligence Officer helps you save time, filter irrelevant information, and organize key points of interest! 🌱
https://github.com/user-attachments/assets/f6fec29f-2b4b-40f8-8676-8433abb086a7
@ -55,6 +55,8 @@ However, we have also noticed some misunderstandings about the functional positi
🌹 Starring and forking are good habits 🌹
**windows users please download git bash tool first** [link](https://git-scm.com/downloads/win)
```bash
git clone https://github.com/TeamWiseFlow/wiseflow.git
```
@ -104,7 +106,7 @@ When using AiHubMix models, the .env configuration can refer to the following:
```bash
export LLM_API_KEY=Your_API_KEY
export LLM_API_BASE="https://aihubmix.com/v1" # 具体参考 https://doc.aihubmix.com/
export LLM_API_BASE="https://aihubmix.com/v1" # refer to https://doc.aihubmix.com/
export PRIMARY_MODEL="gpt-4o"
export SECONDARY_MODEL="gpt-4o-mini"
export VL_MODEL="gpt-4o"
@ -112,6 +114,18 @@ export VL_MODEL="gpt-4o"
😄 Welcome to register using the [AiHubMix referral link](https://aihubmix.com?aff=Gp54) 🌹
#### Use Local Large Language Model Service
Taking Xinference as an example, the .env configuration can refer to the following:
```bash
# LLM_API_KEY='' no need for local service, please comment out or delete
export LLM_API_BASE='http://127.0.0.1:9997'
export PRIMARY_MODEL=launched_model_id
export SECONDARY_MODEL=launched_model_id
export VL_MODEL=launched_model_id
```
#### 3.2 Pocketbase Account and Password Configuration
```bash
@ -206,7 +220,7 @@ PocketBase, as a popular lightweight database, currently has SDKs for Go/Javascr
This project is open-source under the [Apache2.0](LICENSE) license.
For commercial and custom cooperation, please contact **Email: zm.zhao@foxmail.com**
For cooperation, please contact **Email: zm.zhao@foxmail.com**
- Commercial customers, please contact us for registration. The product promises to be forever free.

22
README_JP.md
View File

@ -2,13 +2,13 @@
**[English](README_EN.md) | [简体中文](README.md) | [한국어](README_KR.md)**
🚀 **首席情報官**（Wiseflow）は、ウェブサイト、微信公衆号、ソーシャルプラットフォームなど、さまざまな情報源から設定された関心事に基づいて情報を抽出し、自動的にタグ付けしてデータベースにアップロードする、アジャイルな情報マイニングツールです。
🚀 **首席情報官**（Wiseflow）は、大規模言語モデルの思考と分析能力を活用し、人手を介さずに様々な情報源から特定の情報を正確に抽出できる俊敏な情報マイニングツールです。
**私たちが欠けているのは情報ではなく、大量の情報からノイズをフィルタリングし、価値ある情報を明らかにすることです**
🌱首席情報官がどのようにあなたの時間を節約し、無関係な情報をフィルタリングし、関心のあるポイントを整理するのかを見てみましょう！🌱
https://github.com/user-attachments/assets/f6fec29f-2b4b-40f8-8676-8433abb086a7
<div style="padding:56.56% 0 0 0;position:relative;"><iframe src="https://player.vimeo.com/video/1042199968?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479" frameborder="0" allow="autoplay; fullscreen; picture-in-picture; clipboard-write" style="position:absolute;top:0;left:0;width:100%;height:100%;" title="prompt_video_v03x"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script>
## 🔥 テストスクリプトとテストレポートの公開
@ -55,6 +55,8 @@ wiseflowは2024年6月末にV0.3.0バージョンをリリースして以来、
🌹 いいね、forkは良い習慣です 🌹
**Windowsユーザーは事前にGit Bashツールをダウンロードしてください** [リンク](https://git-scm.com/downloads/win)
```bash
git clone https://github.com/TeamWiseFlow/wiseflow.git
```
@ -104,13 +106,25 @@ AiHubMixモデルを使用する場合、.envの設定は以下を参考にし
```bash
export LLM_API_KEY=Your_API_KEY
export LLM_API_BASE="https://aihubmix.com/v1" # 具体参考 https://doc.aihubmix.com/
export LLM_API_BASE="https://aihubmix.com/v1" # referhttps://doc.aihubmix.com/
export PRIMARY_MODEL="gpt-4o"
export SECONDARY_MODEL="gpt-4o-mini"
export VL_MODEL="gpt-4o"
```
😄 [AiHubMixの紹介リンク](https://aihubmix.com?aff=Gp54)からご登録いただけますと幸いです 🌹
#### ローカル大規模言語モデルサービスのデプロイ
Xinferenceを例にすると、.envの設定は以下を参考にできます：
```bash
# LLM_API_KEY='' no need for local service, please comment out or delete
export LLM_API_BASE='http://127.0.0.1:9997'
export PRIMARY_MODEL=launched_model_id
export SECONDARY_MODEL=launched_model_id
export VL_MODEL=launched_model_id
```
#### 3.2 Pocketbaseのアカウントとパスワードの設定
```bash
@ -206,7 +220,7 @@ PocketBaseは人気のある軽量データベースで、現在Go/Javascript/Py
本プロジェクトは [Apache2.0](LICENSE) オープンソースライセンスに基づいています。
商用およびカスタムコラボレーションについては、**Email：35252986@qq.com** までお問い合わせください
商用およびカスタムコラボレーションについては、**Email：zm.zhao@foxmail.com** までお問い合わせください
- 商用顧客は私たちに報告登録をお願いします。製品は永遠に無料で提供されることを約束します。

22
README_KR.md
View File

@ -2,13 +2,13 @@
**[English](README_EN.md) | [日本語](README_JP.md) | [简体中文](README.md)**
🚀 **수석 정보 책임자** (Wiseflow)는 웹사이트, 위챗 공중 계정, 소셜 플랫폼 등 다양한 정보 소스에서 설정된 관심사에 따라 정보를 추출하고, 자동으로 태그를 분류하여 데이터베이스에 업로드하는 민첩한 정보 마이닝 도구입니다.
🚀 **수석 정보 책임자** (Wiseflow)는 다양한 정보 소스에서 특정 정보를 정확하게 추출할 수 있는 민첩한 정보 마이닝 도구입니다. 대규모 언어 모델의 사고 및 분석 능력을 활용하여 인간의 개입 없이도 작동합니다.
**우리가 부족한 것은 정보가 아니라, 방대한 정보 속에서 노이즈를 필터링하여 가치 있는 정보를 드러내는 것입니다.**
🌱 수석 정보 책임자가 어떻게 시간을 절약하고, 관련 없는 정보를 필터링하며, 관심 사항을 정리하는지 살펴보세요! 🌱
https://github.com/user-attachments/assets/f6fec29f-2b4b-40f8-8676-8433abb086a7
<div style="padding:56.56% 0 0 0;position:relative;"><iframe src="https://player.vimeo.com/video/1042199968?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479" frameborder="0" allow="autoplay; fullscreen; picture-in-picture; clipboard-write" style="position:absolute;top:0;left:0;width:100%;height:100%;" title="prompt_video_v03x"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script>
## 🔥 테스트 스크립트 및 테스트 보고서 발표
@ -55,6 +55,8 @@ wiseflow는 2024년 6월 말 V0.3.0 버전 출시 이후 오픈소스 커뮤니
🌹 좋아요, fork는 좋은 습관입니다 🌹
**windows 사용자는 먼저 git bash 도구를 다운로드해야 합니다** [링크](https://git-scm.com/downloads/win)
```bash
git clone https://github.com/TeamWiseFlow/wiseflow.git
```
@ -104,7 +106,7 @@ AiHubMix 모델을 사용할 때 .env 구성은 다음을 참조할 수 있습
```bash
export LLM_API_KEY=Your_API_KEY
export LLM_API_BASE="https://aihubmix.com/v1" # 具体参考 https://doc.aihubmix.com/
export LLM_API_BASE="https://aihubmix.com/v1" # refer https://doc.aihubmix.com/
export PRIMARY_MODEL="gpt-4o"
export SECONDARY_MODEL="gpt-4o-mini"
export VL_MODEL="gpt-4o"
@ -112,6 +114,18 @@ export VL_MODEL="gpt-4o"
😄 Welcome to register using the [AiHubMix referral link](https://aihubmix.com?aff=Gp54) 🌹
#### 로컬 대규모 언어 모델 서비스 배포
Xinference를 예로 들면, .env 구성은 다음을 참조할 수 있습니다:
```bash
# LLM_API_KEY='' no need for local service, please comment out or delete
export LLM_API_BASE='http://127.0.0.1:9997'
export PRIMARY_MODEL=launched_model_id
export SECONDARY_MODEL=launched_model_id
export VL_MODEL=launched_model_id
```
#### 3.2 Pocketbase Account and Password Configuration
```bash
@ -205,7 +219,7 @@ PocketBase는 인기 있는 경량 데이터베이스로, 현재 Go/Javascript/P
이 프로젝트는 [Apache2.0](LICENSE) 오픈소스 라이선스를 기반으로 합니다.
상업적 및 맞춤형 협력은 **Email: 35252986@qq.com**으로 문의하세요.
상업적 및 맞춤형 협력은 **Email: zm.zhao@foxmail.com**으로 문의하세요.
- 상업용 고객은 등록을 위해 연락해 주세요. 제품은 영원히 무료로 제공됩니다.

13
test/reports/wiseflow_report_20241223_bigbrother666/README.md
View File

@ -52,16 +52,3 @@ Qwen/Qwen2.5-32B-Instruct: ￥1.26 / M Tokens
Qwen/Qwen2.5-14B-Instruct: ￥0.7 / M Tokens
Qwen/Qwen2.5-Coder-7B-Instruct: 0 / M Tokens (Limited time free)
| Model | Prompt Language | Missing Characters | Not Following Instructions | Recognition Errors | Hallucinations | Total Score | Rating |
|-------|----------------|-------------------|--------------------------|-------------------|----------------|--------------|---------|
| Qwen/Qwen2-VL-72B-Instruct | cn prompt | 2 | 1 | 3 | 0 | 6 | |
| | en prompt | 2 | 1 | 1 | 0 | 4 | 👍 |
| OpenGVLab/InternVL2-26B | cn prompt | 1 | 0 | 2 | 0 | 3 | 👍👍 |
| | en prompt | 0 | 2 | 3 | 0 | 5 | |
| Pro/Qwen/Qwen2-VL-7B-Instruct | cn prompt | 1 | 1 | 2 | 1 | 5 | |
| | en prompt | 0 | 2 | 3 | 0 | 5 | |
| Pro/OpenGVLab/InternVL2-8B | cn prompt | 3 | 2 | 2 | 0 | 7 | |
| | en prompt | 2 | 2 | 4 | 1 | 9 | |
| deepseek-ai/deepseek-vl2 | cn prompt | 1 | 1 | 1 | 1 | 4 | 👍 |
| | en prompt | 3 | 0 | 1 | 4 | 8 | |