Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja-AI-php.cn

Jadual Kandungan

FastGPT

Di sini kami menggunakan Docker Compose untuk menswastakan FastGPT dengan cepat

mkdir tinywan-fastgptcd tinywan-fastgpt

Salin selepas log masuk

" >

mkdir tinywan-fastgptcd tinywan-fastgpt

Salin selepas log masuk

Laluan ke direktori yang dibuat di atas ialah /d/Tinywan/GPT/tinywan-fastgpt#🎜🎜 ##🎜 🎜#

{"SystemParams": {"pluginBaseUrl": "","vectorMaxProcess": 15,"qaMaxProcess": 15,"pgHNSWEfSearch": 100},"ChatModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","price": 0,"maxContext": 16000,"maxResponse": 4000,"quoteMaxToken": 2000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-3.5-turbo-16k","name": "GPT35-16k","maxContext": 16000,"maxResponse": 16000,"price": 0,"quoteMaxToken": 8000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-4","name": "GPT4-8k","maxContext": 8000,"maxResponse": 8000,"price": 0,"quoteMaxToken": 4000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-4-vision-preview","name": "GPT4-Vision","maxContext": 128000,"maxResponse": 4000,"price": 0,"quoteMaxToken": 100000,"maxTemperature": 1.2,"censor": false,"vision": true,"defaultSystemChatPrompt": ""}],"QAModels": [{"model": "gpt-3.5-turbo-16k","name": "GPT35-16k","maxContext": 16000,"maxResponse": 16000,"price": 0}],"CQModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 16000,"maxResponse": 4000,"price": 0,"functionCall": true,"functionPrompt": ""},{"model": "gpt-4","name": "GPT4-8k","maxContext": 8000,"maxResponse": 8000,"price": 0,"functionCall": true,"functionPrompt": ""}],"ExtractModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 16000,"maxResponse": 4000,"price": 0,"functionCall": true,"functionPrompt": ""}],"QGModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 1600,"maxResponse": 4000,"price": 0}],"VectorModels": [{"model": "text-embedding-ada-002","name": "Embedding-2","price": 0.2,"defaultToken": 700,"maxToken": 3000}],"AudioSpeechModels": [{"model": "tts-1","name": "OpenAI TTS1","price": 0,"voices": [{"label": "Alloy","value": "alloy","bufferId": "openai-Alloy"},{"label": "Echo","value": "echo","bufferId": "openai-Echo"},{"label": "Fable","value": "fable","bufferId": "openai-Fable"},{"label": "Onyx","value": "onyx","bufferId": "openai-Onyx"},{"label": "Nova","value": "nova","bufferId": "openai-Nova"},{"label": "Shimmer","value": "shimmer","bufferId": "openai-Shimmer"}]}],"WhisperModel": {"model": "whisper-1","name": "Whisper1","price": 0}}

Salin selepas log masuk

" >

{"SystemParams": {"pluginBaseUrl": "","vectorMaxProcess": 15,"qaMaxProcess": 15,"pgHNSWEfSearch": 100},"ChatModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","price": 0,"maxContext": 16000,"maxResponse": 4000,"quoteMaxToken": 2000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-3.5-turbo-16k","name": "GPT35-16k","maxContext": 16000,"maxResponse": 16000,"price": 0,"quoteMaxToken": 8000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-4","name": "GPT4-8k","maxContext": 8000,"maxResponse": 8000,"price": 0,"quoteMaxToken": 4000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-4-vision-preview","name": "GPT4-Vision","maxContext": 128000,"maxResponse": 4000,"price": 0,"quoteMaxToken": 100000,"maxTemperature": 1.2,"censor": false,"vision": true,"defaultSystemChatPrompt": ""}],"QAModels": [{"model": "gpt-3.5-turbo-16k","name": "GPT35-16k","maxContext": 16000,"maxResponse": 16000,"price": 0}],"CQModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 16000,"maxResponse": 4000,"price": 0,"functionCall": true,"functionPrompt": ""},{"model": "gpt-4","name": "GPT4-8k","maxContext": 8000,"maxResponse": 8000,"price": 0,"functionCall": true,"functionPrompt": ""}],"ExtractModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 16000,"maxResponse": 4000,"price": 0,"functionCall": true,"functionPrompt": ""}],"QGModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 1600,"maxResponse": 4000,"price": 0}],"VectorModels": [{"model": "text-embedding-ada-002","name": "Embedding-2","price": 0.2,"defaultToken": 700,"maxToken": 3000}],"AudioSpeechModels": [{"model": "tts-1","name": "OpenAI TTS1","price": 0,"voices": [{"label": "Alloy","value": "alloy","bufferId": "openai-Alloy"},{"label": "Echo","value": "echo","bufferId": "openai-Echo"},{"label": "Fable","value": "fable","bufferId": "openai-Fable"},{"label": "Onyx","value": "onyx","bufferId": "openai-Onyx"},{"label": "Nova","value": "nova","bufferId": "openai-Nova"},{"label": "Shimmer","value": "shimmer","bufferId": "openai-Shimmer"}]}],"WhisperModel": {"model": "whisper-1","name": "Whisper1","price": 0}}

Salin selepas log masuk

Dapatkan versi kemas kini imej melalui docker arahan. -karang tarik# 🎜🎜#

使用知识库

创建应用

关联知识库

开始对话

总结

Rumah

Peranti teknologi

Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja

WBOYWBOYWBOYWBOYWBOYWBOYWBOYWBOYWBOYWBOYWBOYWBOYWB

Nov 26, 2023 am 11:18 AM

ai data asas pengetahuan

FastGPT

FastGPT ialah sistem soal jawab asas pengetahuan yang dibina menggunakan model bahasa besar LLM, yang boleh menyediakan pemprosesan data plug-and-play dan fungsi panggilan model. Pada masa yang sama, ia turut menyokong orkestrasi aliran kerja visual Aliran untuk merealisasikan senario soalan dan jawapan yang kompleks

Carta Aliran Teras Pangkalan Pengetahuan

Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja #🎜🎜🎜#🎜🎜 🎜#Sumber imej: https://doc.fastgpt.in

Private deployment

Di sini kami menggunakan Docker Compose untuk menswastakan FastGPT dengan cepat

1. Pasang Docker

# 安装 Dockercurl -fsSL https://get.docker.com | bash -s docker --mirror Aliyunsystemctl enable --now docker# 安装 docker-composecurl -L https://github.com/docker/compose/releases/download/2.20.3/docker-compose-`uname -s`-`uname -m` -o /usr/local/bin/docker-composechmod +x /usr/local/bin/docker-compose# 验证安装docker -vdocker-compose -v

Salin selepas log masuk

Jika sudah dipasang, langkau sahaja

#🎜🎜🎜 #2

Buat direktori tempatan dan masukkan direktori

mkdir tinywan-fastgptcd tinywan-fastgpt

Salin selepas log masuk

Laluan ke direktori yang dibuat di atas ialah /d/Tinywan/GPT/tinywan-fastgpt#🎜🎜 ##🎜 🎜#

docker-compose.yml configuration file

version: '3.3'services:pg:image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.5.0 # 阿里云container_name: pgrestart: alwaysports: # 生产环境建议不要暴露- 5432:5432networks:- fastgptenvironment:# 这里的配置只有首次运行生效。修改后，重启镜像是不会生效的。需要把持久化数据删除再重启，才有效果- POSTGRES_USER=username- POSTGRES_PASSWORD=password- POSTGRES_DB=postgresvolumes:- ./pg/data:/var/lib/postgresql/datamongo:image: mongo:5.0.18# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.18 # 阿里云container_name: mongorestart: alwaysports: # 生产环境建议不要暴露- 27017:27017networks:- fastgptenvironment:# 这里的配置只有首次运行生效。修改后，重启镜像是不会生效的。需要把持久化数据删除再重启，才有效果- MONGO_INITDB_ROOT_USERNAME=username- MONGO_INITDB_ROOT_PASSWORD=passwordvolumes:- ./mongo/data:/data/dbfastgpt:container_name: fastgptimage: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:latest # 阿里云ports:- 3000:3000networks:- fastgptdepends_on:- mongo- pgrestart: alwaysenvironment:# root 密码，用户名为: root- DEFAULT_ROOT_PSW=123465# 中转地址，如果是用官方号，不需要管- OPENAI_BASE_URL=https://api.openai.com/v1- CHAT_API_KEY=sb-xxx- DB_MAX_LINK=5 # database max link- TOKEN_KEY=any- ROOT_KEY=root_key- FILE_TOKEN_KEY=filetoken# mongo 配置，不需要改. 如果连不上，可能需要去掉 ?authSource=admin- MONGODB_URI=mongodb://username:password@mongo:27017/fastgpt?authSource=admin# pg配置. 不需要改- PG_URL=postgresql://username:password@pg:5432/postgresvolumes:- ./config.json:/app/data/config.jsonnetworks:fastgpt:

Salin selepas log masuk

Nota: Sila isikan nilai yang sepadan dengan CHAT_API_KEY.

config.json fail konfigurasi

{"SystemParams": {"pluginBaseUrl": "","vectorMaxProcess": 15,"qaMaxProcess": 15,"pgHNSWEfSearch": 100},"ChatModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","price": 0,"maxContext": 16000,"maxResponse": 4000,"quoteMaxToken": 2000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-3.5-turbo-16k","name": "GPT35-16k","maxContext": 16000,"maxResponse": 16000,"price": 0,"quoteMaxToken": 8000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-4","name": "GPT4-8k","maxContext": 8000,"maxResponse": 8000,"price": 0,"quoteMaxToken": 4000,"maxTemperature": 1.2,"censor": false,"vision": false,"defaultSystemChatPrompt": ""},{"model": "gpt-4-vision-preview","name": "GPT4-Vision","maxContext": 128000,"maxResponse": 4000,"price": 0,"quoteMaxToken": 100000,"maxTemperature": 1.2,"censor": false,"vision": true,"defaultSystemChatPrompt": ""}],"QAModels": [{"model": "gpt-3.5-turbo-16k","name": "GPT35-16k","maxContext": 16000,"maxResponse": 16000,"price": 0}],"CQModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 16000,"maxResponse": 4000,"price": 0,"functionCall": true,"functionPrompt": ""},{"model": "gpt-4","name": "GPT4-8k","maxContext": 8000,"maxResponse": 8000,"price": 0,"functionCall": true,"functionPrompt": ""}],"ExtractModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 16000,"maxResponse": 4000,"price": 0,"functionCall": true,"functionPrompt": ""}],"QGModels": [{"model": "gpt-3.5-turbo-1106","name": "GPT35-1106","maxContext": 1600,"maxResponse": 4000,"price": 0}],"VectorModels": [{"model": "text-embedding-ada-002","name": "Embedding-2","price": 0.2,"defaultToken": 700,"maxToken": 3000}],"AudioSpeechModels": [{"model": "tts-1","name": "OpenAI TTS1","price": 0,"voices": [{"label": "Alloy","value": "alloy","bufferId": "openai-Alloy"},{"label": "Echo","value": "echo","bufferId": "openai-Echo"},{"label": "Fable","value": "fable","bufferId": "openai-Fable"},{"label": "Onyx","value": "onyx","bufferId": "openai-Onyx"},{"label": "Nova","value": "nova","bufferId": "openai-Nova"},{"label": "Shimmer","value": "shimmer","bufferId": "openai-Shimmer"}]}],"WhisperModel": {"model": "whisper-1","name": "Whisper1","price": 0}}

Salin selepas log masuk

3 Mulakan bekas

Dapatkan versi kemas kini imej melalui docker arahan. -karang tarik# 🎜🎜#

Gambar

Mulakan bekas-com melalui arahan -d Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja

Picture

Lihat # status permulaan kontena Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja

Picture

4 Akses FastGPT

#🎜🎜🎜#0 kini boleh diakses secara langsung. . Ini adalah penempatan tempatan, jadi anda boleh mengaksesnya terus melalui http://127.0.0.1:3000.

Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja Berjaya digunakan, anda boleh mengakses halaman berikut:

Picture#🎜🎜🎜🎜 ## 🎜🎜#Nama pengguna log masuk ialah akar, dan kata laluannya ialah DEFAULT_ROOT_PSW ditetapkan dalam pembolehubah persekitaran docker-compose.yml.

Selepas berjaya log masuk, anda akan dialihkan ke halaman berikut: Bina Pangkalan Pengetahuan
Buat Pangkalan Pengetahuan

Selepas log masuk berjaya, kami boleh mencipta pangkalan pengetahuan baharu dan menamakannya Timbunan Teknologi Sumber Terbuka Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja # 🎜 🎜#Picture

Cara mengimport pengalaman peribadi ke dalam pangkalan pengetahuan adalah melalui fail

Kandungan yang perlu ditulis semula ialah: [Baharu/Import 】【Import fail】. Kandungan yang ditulis semula: [Buat/Import][Import Fail]

Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja Picture

Selepas pengesahan data, mula mengimport Tukar kepada data vektor

Picture

Bina pangkalan pengetahuan AI model bahasa yang besar dalam masa tiga minit sahaja Apabila memilih fail untuk diimport, anda boleh memilih pelan pembahagian langsung. Pembahagian langsung akan menggunakan pembahagian ayat untuk membahagikan teks kepada panjang tertentu, dan akhirnya membahagikannya kepada beberapa kumpulan q. Jika anda memilih penyelesaian pembahagian langsung, adalah disyorkan untuk menggunakan templat umum semasa menetapkan perkataan gesaan petikan dalam aplikasi Tidak perlu memilih templat soal jawab