? RAGBOT.AI (이전의 RBOT) : Rajiv의 오픈 소스 AI Augmented Brain Assistant는 LLMS (Large Augmented Generation)와 큰 언어 모델 (LLM)의 힘을 결합합니다.
ragbot.ai는 사용자 지침 및 선별 된 데이터 세트와 함께 사용자 프롬프트를 처리하여 컨텍스트 인식 응답을 가능하게합니다. OpenAi의 GPT 및 Anthropic의 Claude를 포함한 LLM으로 구동되는 Ragbot.ai는 미리 훈련 된 조밀 한 검색 및 시퀀스-시퀀스 모델의 힘을 결합하여보다 사실적이고 유익한 텍스트를 생성하는 기술 인 Rag를 사용합니다.
? 맞춤형 지침 및 선별 된 데이터 세트는 Ragbot.ai가 컨텍스트를 더 잘 이해하여 개인화되고 정확하며 관련 응답을 통해 Box LLM의 기능을 능가합니다.
Rajiv Pant가 개발했습니다
코드 기고자 및 공동 작업자
기여하는 방법
귀하의 코드 기여를 환영합니다. 저장소를 포크하고 개선 사항으로 풀 요청을 제출하십시오.
Ragbot.ai 소개 : Ragbot.ai가 작성한 개인화 된 AI 보조원
블로그 게시물에서 발췌 :
AI 어시스턴트로서 저는 Chatgpt Plus, Bing Chat 및 Google Bard의 현재 구현과 차별화되는 고유 한 수준의 개인화 및 적응성을 제공합니다. 맞춤형 선별 된 데이터 세트 파일을 포함하는 폴더를 사용하면 개인 생활, 직장, 교육 및 특정 프로젝트와 같은 여러 사용 사례를 충족시킬 수 있습니다. 이 사용자 정의를 통해 고유 한 요구에 맞는 방식으로 당신을 이해하고 지원할 수 있습니다.
개인 정보, 가족 세부 정보, 여행 및 음식 선호도 등을 포함하는 선별 된 데이터 세트 파일로 폴더를 만들 수 있습니다. 이 정보를 사용함으로써 귀하의 개인 생명 보조원으로 기능 할 수 있으며 AI 기반 권장 사항을 제공하고 귀하의 특정 상황에 맞는 지원을 지원할 수 있습니다.
마찬가지로 작업 수명과 관련된 선별 된 데이터 세트 파일을 포함하는 다른 폴더를 개발할 수 있습니다. 이러한 파일에는 업무, 업계, 동료, 프로젝트 및 기타 업무 관련 정보에 대한 세부 정보가 포함될 수 있습니다. 이러한 맥락에서, 나는 이메일 초안 작성, 회의 일정, 연구 수행 등과 같은 다양한 작업을 통해 효율성과 조직을 향상시킬 수 있습니다.
또한 학업 배경, 관심 주제, 과목 및 기타 교육 세부 사항에 대한 정보가 포함 된 선별 된 데이터 세트 파일로 폴더를 만들어 교육 목적으로 저를 사용자 정의 할 수도 있습니다. 이 역할에서 저는 숙제를 돕는 것에서부터 복잡한 개념을 설명하거나 학습 자원을 추천하는 것까지 개인화 된 교육 지원을 제공 할 수 있습니다.
위에서 언급 한 사용 사례 외에도 특정 프로젝트에 대한 귀하를 지원할 수 있도록 조정할 수 있습니다. 목표, 팀 구성원, 마감일 및 관련 리소스와 같은 프로젝트 관련 정보가 포함 된 선별 된 데이터 세트 파일이 포함 된 폴더를 작성함으로써 프로젝트 라이프 사이클 전체에 걸쳐 도움을 줄 수 있으며, 각 고유 한 프로젝트에 맞는 귀중한 통찰력과 지원을 제공합니다.
맞춤형 큐 레이트 된 데이터 세트 파일을 사용하여 다양한 요구에 대한 고유 한 프로파일을 만들 수있는 능력은 Chatgpt Plus, Bing Chat 및 Google Bard와 차별화됩니다. 이 다목적 성을 통해 나는 당신의 삶의 여러 측면에서 개인화 된 지원을 제공하여 특정 요구 사항을 이해하고 제공 할 수 있도록합니다.
설치 안내서 및 구성 및 개인화 안내서를 읽으십시오.



generate_prompt_template.py 는 사용자 정의 지침 및 선별 된 데이터 세트를 연결하여 AI 어시스턴트를위한 프롬프트 템플릿을 생성하는 Python 스크립트입니다. 사용자가 AI 구동 도구의 효과를 향상시키기 위해 개인화되고 상황을 인식하는 프롬프트를 만들도록 도와줍니다.
generate_prompt_template.py 사용하는 방법에 대한 자세한 정보 및 그 이점은 Pretme Prempt Template Guide를 참조하십시오.
rajivpant@rp-2023-mac-mini ragbot % ./ragbot --help
usage: ragbot.py [-h] [-ls] [-p PROMPT | -f PROMPT_FILE | -i | --stdin]
[-profile PROFILE] [-c [CUSTOM_INSTRUCTIONS ...]] [-nc]
[-d [CURATED_DATASET ...]] [-nd]
[-e {openai,anthropic,google}] [-m MODEL] [-t TEMPERATURE]
[-mt MAX_TOKENS] [-l LOAD]
Ragbot.AI is an augmented brain and asistant. Learn more at https://ragbot.ai
options:
-h, --help show this help message and exit
-ls, --list-saved List all the currently saved JSON files.
-p PROMPT, --prompt PROMPT
The user's input to generate a response for.
-f PROMPT_FILE, --prompt_file PROMPT_FILE
The file containing the user's input to generate a
response for.
-i, --interactive Enable interactive assistant chatbot mode.
--stdin Read the user's input from stdin.
-profile PROFILE, --profile PROFILE
Name of the profile to use.
-c [CUSTOM_INSTRUCTIONS ...], --custom_instructions [CUSTOM_INSTRUCTIONS ...]
Path to the prompt custom instructions file or folder.
Can accept multiple values.
-nc, --nocusom_instructions
Ignore all prompt custom instructions even if they are
specified.
-d [CURATED_DATASET ...], --curated_dataset [CURATED_DATASET ...]
Path to the prompt context curated dataset file or
folder. Can accept multiple values.
-nd, --nocurated_dataset
Ignore all prompt context curated dataset even if they
are specified.
-e {openai,anthropic,google}, --engine {openai,anthropic,google}
The engine to use for the chat.
-m MODEL, --model MODEL
The model to use for the chat. Defaults to engine's
default model.
-t TEMPERATURE, --temperature TEMPERATURE
The creativity of the response, with higher values
being more creative.
-mt MAX_TOKENS, --max_tokens MAX_TOKENS
The maximum number of tokens to generate in the
response.
-l LOAD, --load LOAD Load a previous interactive session from a file.
rajivpant@rp-2023-mac-mini ragbot % ragbot.ai를 사용하려면 선별 된 데이터 세트 파일 및/또는 여러 개의 선별 된 데이터 세트 파일이 포함 된 폴더를 제공 할 수 있습니다. https://github.com/rajivpant/ragbot/tree/main/example-curated-datasets에서 선별 된 데이터 세트 파일의 예를 볼 수 있습니다.
Example 1:
rajivpant@RP-2021-MacBook-Pro ragbot % ./ragbot.py -d custom-instructions/ curated-datasets/public/ ../ragbot-private/curated-datasets/personal/ ../ragbot-private/curated-datasets/hearst -p " Write a short note in Rajiv's voice about Rajiv's job, coworkers, family members, and travel and food preferences for the person temporarily backfilling for his EA. "
curated datasets being used:
- custom-instructions/
- curated-datasets/public/travel-food.md
- curated-datasets/public/employment-history.md
- curated-datasets/public/about.md
- curated-datasets/public/biography.md
- ../ragbot-private/curated-datasets/personal/accounts.md
- ../ragbot-private/curated-datasets/personal/contact-info.md
- ../ragbot-private/curated-datasets/personal/personal-family.md
- ../ragbot-private/curated-datasets/hearst/hearst.md
Using AI engine openai with model gpt-4
[redacted in this example]Example 2:
rajivpant@RP-2021-MacBook-Pro ragbot % ./ragbot.py -d custom-instructions/ curated-datasets/public/ -p " Write a short resume of Rajiv "
curated datasets being used:
- custom-instructions/
- curated-datasets/public/travel-food.md
- curated-datasets/public/employment-history.md
- curated-datasets/public/about.md
- curated-datasets/public/biography.md
Using AI engine openai with model gpt-4
[truncated in this example]Example 3:
./ragbot.py -p "Tell me a story about a brave knight and a wise wizard." -d curated datasets/story_characters 대화식 모드에서 ragbot.ai를 사용하려면 명령 줄 또는 입력 파일을 통해 프롬프트를 제공하지 않고 -i 또는 --interactive 플래그를 사용하십시오. 이 모드에서는 각 응답 후에 후속 프롬프트를 입력 할 수 있습니다.
예:
./ragbot.py -i -d curated-datasets/story_characters 첫 번째 예에서, ragbot.ai는 ../ragbot-private/curated-datasets 폴더의 선별 된 데이터 세트 파일을 사용하여 Rajiv의 목소리로 짧은 메모를 생성합니다. 두 번째 예에서 Ragbot.ai는 curated-datasets/software_development.txt Curated DataSet 파일을 사용하여 소프트웨어 개발을위한 모범 사례에 대한 정보를 제공합니다. 세 번째 예에서 Ragbot.ai는 curated-datasets/story_characters 폴더의 선별 된 데이터 세트 파일을 사용하여 용감한 기사와 현명한 마법사에 대한 이야기를 들려줍니다.
rajivpant@RP-2021-MacBook-Pro ragbot % ./ragbot.py -d ragbot.py -p " if no curated dataset files are being used, then I want the code to show that. "
curated datasets being used:
- ragbot.py
Using AI engine openai with model gpt-4
To modify the code to show a message when no curated dataset files are being used, you can add an else statement after checking for the curated dataset files. Update the code in the `main()` function as follows:
```python
if curated_dataset_files:
print("curated datasets being used:")
for file in curated_dataset_files:
print(f" - {file}")
else:
print("No curated dataset files are being used.")
```
This will print "No curated dataset files are being used." when there are no curated dataset files detected.
rajivpant@RP-2021-MacBook-Pro ragbot %
내가 사용하는 선별 된 데이터 세트 파일이 무엇인지 추측하도록 요청
rajivpant@RP-2021-MacBook-Pro ragbot % find curated-datasets ../ragbot-private/curated-datasets -print | ./ragbot.py -d custom-instructions/ curated-datasets/public/ ../ragbot-private/curated-datasets/personal/ ../ragbot-private/curated-datasets/hearst/ -p " What do you guess these files are for? "
curated datasets being used:
- custom-instructions/
- curated-datasets/public/travel-food.md
- curated-datasets/public/employment-history.md
- curated-datasets/public/about.md
- curated-datasets/public/biography.md
- ../ragbot-private/curated-datasets/personal/accounts.md
- ../ragbot-private/curated-datasets/personal/contact-info.md
- ../ragbot-private/curated-datasets/personal/personal-family.md
- ../ragbot-private/curated-datasets/hearst/hearst.md
Using AI engine openai with model gpt-4
These files appear to be related to the curated-datasets of an AI system, likely for generating text or providing assistance based on the provided information. The files seem to be divided into two categories: public and private.
Public files:
- curated-datasets/public/travel-food.md: Rajiv's travel and food preferences
- curated-datasets/public/employment-history.md: Rajiv's employment history
- curated-datasets/public/about.md: General information about Rajiv
- curated-datasets/public/biography.md: Biography of Rajiv
Private files (stored in a separate private folder):
- curated-datasets/personal/accounts.md: Semi-private personal account information, such as frequent flyer numbers or loyalty programs. Does not contain any confidential or sensitive information.
- curated-datasets/personal/contact-info.md: Personal contact information, such as phone numbers and email addresses. Does not contain any confidential or sensitive information.
- curated-datasets/personal/personal-family.md: Personal and family information, such as family members and relationships. Does not contain any confidential or sensitive information.
Hearst-specific files:
- curated-datasets/hearst/hearst.md: Non-confidential, publicly available information related to the Hearst corporation, including Rajiv's role there
Overall, these files seem to contain various information about a person, their preferences, and professional background, likely used to tailor the AI system's responses and assistance.
rajivpant@RP-2021-MacBook-Pro ragbot % 프로젝트에 대한 기술적 질문을합니다
ragbot.ai의 현재 버전에서 -stdin 및 -prompt 옵션은 상호 배타적이므로 다음 예제는 더 이상 작동하지 않습니다. 이 readme 파일에 대한 향후 업데이트에서 유사한 결과를 얻기위한 대체 예제를 제시합니다.
alexredmon@ar-macbook ~/s/scribe > cat docker-compose.yml | ragbot --stdin -p " which services will be exposed on which ports by running all services in the following docker-compose.yml file? "
In the given docker-compose.yml file, the following services are exposed on their respective ports:
1. "scribe" service: - Exposed on port 80 - Exposed on port 9009 (mapped to internal port 9009)
2. "scribe-feature" service: - Exposed on port 80
3. "scribe-redis" service: - Exposed on port 6379 (mapped to internal port 6379)
alexredmon@ar-macbook ~/s/scribe >Claude Instant 모델과 함께 인류 엔진 사용
rajivpant@RP-2021-MacBook-Pro ragbot % ./ragbot.py -e anthropic -m " claude-instant-v1 " -p " Tell me 5 fun things to do in NYC. "
No curated dataset files are being used.
Using AI engine anthropic with model claude-instant-v1
Here are 5 fun things to do in NYC:
1. Visit Central Park. Walk the paths, rent a paddle boat, visit the zoo, catch a Shakespeare in the Park performance.
2. Catch a Broadway show. New York is the center of the theater world with some of the greatest plays and musicals on Broadway and off Broadway.
3. Go to the top of the Empire State Building. Take in the panoramic views of all of NYC from one of its most famous landmarks.
4. Shop and dine in SoHo and the West Village. Explore trendy boutique shops and dig into meals at charming sidewalk cafes.
5. Take a free walking tour. There are numerous companies that offer guided walking tours of various NYC neighborhoods, covering history, culture, architecture and more.
rajivpant@RP-2021-MacBook-Pro ragbot % 무작위 창의성
ragbot.ai의 현재 버전에서 -stdin 및 -prompt 옵션은 상호 배타적이므로 다음 예제는 더 이상 작동하지 않습니다. 이 readme 파일에 대한 향후 업데이트에서 유사한 결과를 얻기위한 대체 예제를 제시합니다.
alexredmon@ar-macbook ~ > cat names.csv
rajiv,
jim,
dennis,
alexandria
alexredmon@ar-macbook ~ > catnames.csv | ragbot.py --stdin -p "Generate a creative nickname for each of the following people"
rajiv, Rajiv Razzle-Dazzle
jim, Jolly JimJam
dennis, Daring Denmaster
alexandria, All-Star Alexi
alexredmon@ar-macbook ~ >