[Merge] Dev (#195)
This commit is contained in:
xzw
GitHub
commit
f301087b17
1126
Baby EmoLLM.ipynb
Normal file
1126
Baby EmoLLM.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
54
README.md
54
README.md
@ -253,33 +253,33 @@ git clone https://github.com/SmartFlowAI/EmoLLM.git
|
|||||||
|
|
||||||
### 作者（排名不分先后）
|
### 作者（排名不分先后）
|
||||||
|
|
||||||
| 用户名 | 学校/组织 | 备注 | 贡献 |
|
| 用户名 | 学校/组织 | 备注 | 贡献 |
|
||||||
| :-----------------------------------------------------------: | :------------------------------------------------: | :------------------------------------------------------------------: | :-------------------------------------------: |
|
| :----------------------------------------------------------: | :------------------------------------------------: | :----------------------------------------------------------: | :-------------------------------------------: |
|
||||||
| [aJupyter](https://github.com/aJupyter) | 南开大学在读硕士 | DataWhale成员 | 项目发起人 |
|
| [aJupyter](https://github.com/aJupyter) | 南开大学在读硕士 | DataWhale成员 | 项目发起人 |
|
||||||
| [MING-ZCH](https://github.com/MING-ZCH) | 华中科技大学在读本科生 | LLM x Psychology 研究者 | 项目联合负责人 |
|
| [MING-ZCH](https://github.com/MING-ZCH) | 华中科技大学在读本科生 | LLM x Psychology 研究者 | 项目联合负责人 |
|
||||||
| [jujimeizuo](https://github.com/jujimeizuo) | 江南大学在读硕士 | | |
|
| [jujimeizuo](https://github.com/jujimeizuo) | 江南大学在读硕士 | | |
|
||||||
| [Smiling-Weeping-zhr](https://github.com/Smiling-Weeping-zhr) | 哈尔滨工业大学（威海）在读本科生 | | |
|
| [Smiling-Weeping-zhr](https://github.com/Smiling-Weeping-zhr) | 哈尔滨工业大学（威海）在读本科生 | | |
|
||||||
| [8baby8](https://github.com/8baby8) | 飞桨领航团区域主管 | 文心大模型核心开发者 | |
|
| [8baby8](https://github.com/8baby8) | 飞桨领航团区域主管 | 文心大模型核心开发者 | |
|
||||||
| [zxazys](https://github.com/zxazys) | 南开大学在读硕士 | | |
|
| [zxazys](https://github.com/zxazys) | 南开大学在读硕士 | | |
|
||||||
| [JasonLLLLLLLLLLL](https://github.com/JasonLLLLLLLLLLL) | swufe | | |
|
| [JasonLLLLLLLLLLL](https://github.com/JasonLLLLLLLLLLL) | swufe | | |
|
||||||
| [MrCatAI](https://github.com/MrCatAI) | AI搬用工 | | |
|
| [MrCatAI](https://github.com/MrCatAI) | AI搬用工 | | |
|
||||||
| [ZeyuBa](https://github.com/ZeyuBa) | 自动化所在读硕士 | | |
|
| [ZeyuBa](https://github.com/ZeyuBa) | 自动化所在读硕士 | | |
|
||||||
| [aiyinyuedejustin](https://github.com/aiyinyuedejustin) | 宾夕法尼亚大学在读硕士 | | |
|
| [aiyinyuedejustin](https://github.com/aiyinyuedejustin) | 宾夕法尼亚大学在读硕士 | | |
|
||||||
| [Nobody-ML](https://github.com/Nobody-ML) | 中国石油大学（华东）在读本科生 | | |
|
| [Nobody-ML](https://github.com/Nobody-ML) | 中国石油大学（华东）在读本科生 | | |
|
||||||
| [chg0901](https://github.com/chg0901) | [MiniSora](https://github.com/mini-sora/minisora/) | [MiniSora](https://github.com/mini-sora/minisora/)主要维护者，管理员 | LLM预训练和微调、模型上传、数据清洗、文档翻译 |
|
| [chg0901](https://github.com/chg0901) | [MiniSora](https://github.com/mini-sora/minisora/) | [MiniSora](https://github.com/mini-sora/minisora/)主要维护者，管理员 | LLM预训练和微调、模型上传、数据清洗、文档翻译 |
|
||||||
| [Mxoder](https://github.com/Mxoder) | 北京航空航天大学在读本科生 | | |
|
| [Mxoder](https://github.com/Mxoder) | 北京航空航天大学在读本科生 | | |
|
||||||
| [Anooyman](https://github.com/Anooyman) | 南京理工大学硕士 | | |
|
| [Anooyman](https://github.com/Anooyman) | 南京理工大学硕士 | | |
|
||||||
| [Vicky-3021](https://github.com/Vicky-3021) | 西安电子科技大学硕士（研0） | | |
|
| [Vicky-3021](https://github.com/Vicky-3021) | 西安电子科技大学硕士（研0） | | |
|
||||||
| [SantiagoTOP](https://github.com/santiagoTOP) | 太原理工大学在读硕士 | | |
|
| [SantiagoTOP](https://github.com/santiagoTOP) | 太原理工大学在读硕士 | | 数据清洗，文档管理、Baby EmoLLM维护 |
|
||||||
| [zealot52099](https://github.com/zealot52099) | 个人开发者 | | 清洗数据、LLM微调、RAG |
|
| [zealot52099](https://github.com/zealot52099) | 个人开发者 | | 清洗数据、LLM微调、RAG |
|
||||||
| [wwwyfff](https://github.com/wwwyfff) | 复旦大学在读硕士 | | |
|
| [wwwyfff](https://github.com/wwwyfff) | 复旦大学在读硕士 | | |
|
||||||
| [Yicooong](https://github.com/Yicooong) | 南开大学在读硕士 | | |
|
| [Yicooong](https://github.com/Yicooong) | 南开大学在读硕士 | | |
|
||||||
| [jkhumor](https://github.com/jkhumor) | 南开大学在读硕士 | | RAG |
|
| [jkhumor](https://github.com/jkhumor) | 南开大学在读硕士 | | RAG |
|
||||||
| [lll997150986](https://github.com/lll997150986) | 南开大学在读硕士 | | 微调 |
|
| [lll997150986](https://github.com/lll997150986) | 南开大学在读硕士 | | 微调 |
|
||||||
| [nln-maker](https://github.com/nln-maker) | 南开大学在读硕士 | | 前后端开发 |
|
| [nln-maker](https://github.com/nln-maker) | 南开大学在读硕士 | | 前后端开发 |
|
||||||
| [dream00001](https://github.com/dream00001) | 南开大学在读硕士 | | 前后端开发 |
|
| [dream00001](https://github.com/dream00001) | 南开大学在读硕士 | | 前后端开发 |
|
||||||
| [王几行XING](https://zhihu.com/people/brycewang1898) | 北京大学硕士毕业 | | 清洗数据、LLM微调、前后端开发 |
|
| [王几行XING](https://zhihu.com/people/brycewang1898) | 北京大学硕士毕业 | | 清洗数据、LLM微调、前后端开发 |
|
||||||
| [思在] | 北京大学硕士毕业（微软美国） | | LLM微调、前后端开发 |
|
| [思在] | 北京大学硕士毕业（微软美国） | | LLM微调、前后端开发 |
|
||||||
|
|
||||||
### 版权说明
|
### 版权说明
|
||||||
|
|
||||||
|
|||||||
54
README_EN.md
54
README_EN.md
@ -78,7 +78,7 @@ The Model aims to fully understand and promote the mental health of individuals,
|
|||||||
- Psychological resilience: Refers to an individual's ability to recover from adversity and adapt. Those with strong psychological resilience can bounce back from challenges and learn and grow from them.
|
- Psychological resilience: Refers to an individual's ability to recover from adversity and adapt. Those with strong psychological resilience can bounce back from challenges and learn and grow from them.
|
||||||
- Prevention and intervention measures: The Mental Health Grand Model also includes strategies for preventing psychological issues and promoting mental health, such as psychological education, counseling, therapy, and social support systems.
|
- Prevention and intervention measures: The Mental Health Grand Model also includes strategies for preventing psychological issues and promoting mental health, such as psychological education, counseling, therapy, and social support systems.
|
||||||
- Assessment and diagnostic tools: Effective promotion of mental health requires scientific tools to assess individuals' psychological states and diagnose potential psychological issues.
|
- Assessment and diagnostic tools: Effective promotion of mental health requires scientific tools to assess individuals' psychological states and diagnose potential psychological issues.
|
||||||
|
|
||||||
|
|
||||||
<table>
|
<table>
|
||||||
<tr>
|
<tr>
|
||||||
@ -253,32 +253,32 @@ This project uses Git for version control. You can see the currently available v
|
|||||||
|
|
||||||
### Authors (in no particular order)
|
### Authors (in no particular order)
|
||||||
|
|
||||||
| Username | School/Organization | Remarks | Contributions |
|
| Username | School/Organization | Remarks | Contributions |
|
||||||
| :-----------------------------------------------------------: | :------------------------------------------------------------------: | :-----------------------------------------------------------------------: | :-----------------------------------------------------------------------------------: |
|
| :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
|
||||||
| [aJupyter](https://github.com/aJupyter) | Nankai University, Master's student | DataWhale member | Project initiator |
|
| [aJupyter](https://github.com/aJupyter) | Nankai University, Master's student | DataWhale member | Project initiator |
|
||||||
| [MING-ZCH](https://github.com/MING-ZCH) | Huazhong University of Science and Technology, Undergraduate student | LLM X Psychology researcher | Project co-leader |
|
| [MING-ZCH](https://github.com/MING-ZCH) | Huazhong University of Science and Technology, Undergraduate student | LLM X Psychology researcher | Project co-leader |
|
||||||
| [jujimeizuo](https://github.com/jujimeizuo) | Jiangnan University, Master's student | | |
|
| [jujimeizuo](https://github.com/jujimeizuo) | Jiangnan University, Master's student | | |
|
||||||
| [Smiling-Weeping-zhr](https://github.com/Smiling-Weeping-zhr) | Harbin Institute of Technology (Weihai), Undergraduate student | | |
|
| [Smiling-Weeping-zhr](https://github.com/Smiling-Weeping-zhr) | Harbin Institute of Technology (Weihai), Undergraduate student | | |
|
||||||
| [8baby8](https://github.com/8baby8) | PaddlePaddle Pilot Team Regional Director | Wenxin Large Model core developer | |
|
| [8baby8](https://github.com/8baby8) | PaddlePaddle Pilot Team Regional Director | Wenxin Large Model core developer | |
|
||||||
| [zxazys](https://github.com/zxazys) | Nankai University, Master's student | | |
|
| [zxazys](https://github.com/zxazys) | Nankai University, Master's student | | |
|
||||||
| [JasonLLLLLLLLLLL](https://github.com/JasonLLLLLLLLLLL) | SWUFE (Southwestern University of Finance and Economics) | | |
|
| [JasonLLLLLLLLLLL](https://github.com/JasonLLLLLLLLLLL) | SWUFE (Southwestern University of Finance and Economics) | | |
|
||||||
| [MrCatAI](https://github.com/MrCatAI) | AI Mover | | |
|
| [MrCatAI](https://github.com/MrCatAI) | AI Mover | | |
|
||||||
| [ZeyuBa](https://github.com/ZeyuBa) | Institute of Automation, Master's student | | |
|
| [ZeyuBa](https://github.com/ZeyuBa) | Institute of Automation, Master's student | | |
|
||||||
| [aiyinyuedejustin](https://github.com/aiyinyuedejustin) | University of Pennsylvania, Master's student | | |
|
| [aiyinyuedejustin](https://github.com/aiyinyuedejustin) | University of Pennsylvania, Master's student | | |
|
||||||
| [Nobody-ML](https://github.com/Nobody-ML) | China University of Petroleum (East China), Undergraduate student | | |
|
| [Nobody-ML](https://github.com/Nobody-ML) | China University of Petroleum (East China), Undergraduate student | | |
|
||||||
| [chg0901](https://github.com/chg0901) | [MiniSora](https://github.com/mini-sora/minisora) | Maintainer and Admin of [MiniSora](https://github.com/mini-sora/minisora) | LLM Pre-Training and Fine-Tuning, Model Uploading, Data Cleaning and Docs Translation |
|
| [chg0901](https://github.com/chg0901) | [MiniSora](https://github.com/mini-sora/minisora) | Maintainer and Admin of [MiniSora](https://github.com/mini-sora/minisora) | LLM Pre-Training and Fine-Tuning, Model Uploading, Data Cleaning and Docs Translation |
|
||||||
| [Mxoder](https://github.com/Mxoder) | Beihang University, Undergraduate student | | |
|
| [Mxoder](https://github.com/Mxoder) | Beihang University, Undergraduate student | | |
|
||||||
| [Anooyman](https://github.com/Anooyman) | Nanjing University of Science and Technology, Master's student | | |
|
| [Anooyman](https://github.com/Anooyman) | Nanjing University of Science and Technology, Master's student | | |
|
||||||
| [Vicky-3021](https://github.com/Vicky-3021) | Xidian University, Master's student (Research Year 0) | | |
|
| [Vicky-3021](https://github.com/Vicky-3021) | Xidian University, Master's student (Research Year 0) | | |
|
||||||
| [SantiagoTOP](https://github.com/santiagoTOP) | Taiyuan University of Technology, Master's student | | |
|
| [SantiagoTOP](https://github.com/santiagoTOP) | Taiyuan University of Technology, Master's student | | Data cleansing, document management, Baby EmoLLM maintenance |
|
||||||
| [zealot52099](https://github.com/zealot52099) | Individual developer | | Data Processing, LLM finetuning and RAG |
|
| [zealot52099](https://github.com/zealot52099) | Individual developer | | Data Processing, LLM finetuning and RAG |
|
||||||
| [wwwyfff](https://github.com/wwwyfff) | FuDan University, Master's student | | |
|
| [wwwyfff](https://github.com/wwwyfff) | FuDan University, Master's student | | |
|
||||||
| [jkhumor](https://github.com/jkhumor) | Nankai University, Master's student | | RAG |
|
| [jkhumor](https://github.com/jkhumor) | Nankai University, Master's student | | RAG |
|
||||||
| [lll997150986](https://github.com/lll997150986) | Nankai University, Master's student | | Fine Tuning |
|
| [lll997150986](https://github.com/lll997150986) | Nankai University, Master's student | | Fine Tuning |
|
||||||
| [nln-maker](https://github.com/nln-maker) | Nankai University, Master's student | | Front-end and back-end development |
|
| [nln-maker](https://github.com/nln-maker) | Nankai University, Master's student | | Front-end and back-end development |
|
||||||
| [dream00001](https://github.com/dream00001) | Nankai University, Master's student | | Front-end and back-end development |
|
| [dream00001](https://github.com/dream00001) | Nankai University, Master's student | | Front-end and back-end development |
|
||||||
| [王几行XING](zhihu.com/people/brycewang1898) | Peking University, Master's graduate | | Data Processing, LLM finetuning, Front-end and back-end development |
|
| [王几行XING](zhihu.com/people/brycewang1898) | Peking University, Master's graduate | | Data Processing, LLM finetuning, Front-end and back-end development |
|
||||||
| [思在] | Peking University, Master's graduate (Microsoft) | | LLM finetuning, Front-end and back-end development |
|
| [思在] | Peking University, Master's graduate (Microsoft) | | LLM finetuning, Front-end and back-end development |
|
||||||
|
|
||||||
### Copyright Notice
|
### Copyright Notice
|
||||||
|
|
||||||
|
|||||||
@ -1,9 +1,9 @@
|
|||||||
import json
|
import json
|
||||||
|
|
||||||
# 打开JSON文件并读取其内容
|
# 打开JSON文件并读取其内容
|
||||||
# file_name = 'single_turn_dataset_1.json'
|
file_name = 'single_turn_dataset_1.json'
|
||||||
file_name = 'single_turn_dataset_2.json'
|
# file_name = 'single_turn_dataset_2.json'
|
||||||
with open(f'/root/StableCascade/emollm2/EmoLLM/datasets/{file_name}', 'rt', encoding='utf-8') as file:
|
with open(f'E:\LLM\EmoLLM\datasets\\{file_name}', 'rt', encoding='utf-8') as file:
|
||||||
format1_data = json.load(file)
|
format1_data = json.load(file)
|
||||||
|
|
||||||
system = "你是心理健康助手EmoLLM，由EmoLLM团队打造。你旨在通过专业心理咨询，协助来访者完成心理诊断。请充分利用专业心理学知识与咨询技术，一步步帮助来访者解决心理问题。"
|
system = "你是心理健康助手EmoLLM，由EmoLLM团队打造。你旨在通过专业心理咨询，协助来访者完成心理诊断。请充分利用专业心理学知识与咨询技术，一步步帮助来访者解决心理问题。"
|
||||||
|
|||||||
@ -58,6 +58,14 @@ JSON 数据格式如下
|
|||||||
如果已经有 vector DB 则会直接加载对应数据库
|
如果已经有 vector DB 则会直接加载对应数据库
|
||||||
|
|
||||||
|
|
||||||
|
**注意**: 可以直接从 xlab 下载对应 DB（请在rag文件目录下执行对应 code）
|
||||||
|
```python
|
||||||
|
# https://openxlab.org.cn/models/detail/Anooyman/EmoLLMRAGTXT/tree/main
|
||||||
|
git lfs install
|
||||||
|
git clone https://code.openxlab.org.cn/Anooyman/EmoLLMRAGTXT.git
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
### 配置 config 文件
|
### 配置 config 文件
|
||||||
|
|
||||||
根据需要改写 config.config 文件：
|
根据需要改写 config.config 文件：
|
||||||
|
|||||||
@ -20,6 +20,7 @@ knowledge_json_path = os.path.join(data_dir, 'knowledge.json') # json
|
|||||||
knowledge_pkl_path = os.path.join(data_dir, 'knowledge.pkl') # pkl
|
knowledge_pkl_path = os.path.join(data_dir, 'knowledge.pkl') # pkl
|
||||||
doc_dir = os.path.join(data_dir, 'txt')
|
doc_dir = os.path.join(data_dir, 'txt')
|
||||||
qa_dir = os.path.join(data_dir, 'json')
|
qa_dir = os.path.join(data_dir, 'json')
|
||||||
|
cloud_vector_db_dir = os.path.join(base_dir, 'EmoLLMRAGTXT')
|
||||||
|
|
||||||
# log
|
# log
|
||||||
log_dir = os.path.join(base_dir, 'log') # log
|
log_dir = os.path.join(base_dir, 'log') # log
|
||||||
@ -30,13 +31,13 @@ chunk_size=1000
|
|||||||
chunk_overlap=100
|
chunk_overlap=100
|
||||||
|
|
||||||
# vector DB
|
# vector DB
|
||||||
vector_db_dir = os.path.join(data_dir, 'vector_db')
|
vector_db_dir = os.path.join(cloud_vector_db_dir, 'vector_db')
|
||||||
|
|
||||||
# RAG related
|
# RAG related
|
||||||
# select num: 代表rerank 之后选取多少个 documents 进入 LLM
|
# select num: 代表rerank 之后选取多少个 documents 进入 LLM
|
||||||
# retrieval num： 代表从 vector db 中检索多少 documents。（retrieval num 应该大于等于 select num）
|
# retrieval num： 代表从 vector db 中检索多少 documents。（retrieval num 应该大于等于 select num）
|
||||||
select_num = 3
|
select_num = 3
|
||||||
retrieval_num = 10
|
retrieval_num = 3
|
||||||
|
|
||||||
# LLM key
|
# LLM key
|
||||||
glm_key = ''
|
glm_key = ''
|
||||||
|
|||||||
@ -4,7 +4,7 @@ import os
|
|||||||
|
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
from langchain_community.vectorstores import FAISS
|
from langchain_community.vectorstores import FAISS
|
||||||
from config.config import (
|
from rag.src.config.config import (
|
||||||
embedding_path,
|
embedding_path,
|
||||||
embedding_model_name,
|
embedding_model_name,
|
||||||
doc_dir, qa_dir,
|
doc_dir, qa_dir,
|
||||||
@ -19,7 +19,6 @@ from config.config import (
|
|||||||
from langchain.embeddings import HuggingFaceBgeEmbeddings
|
from langchain.embeddings import HuggingFaceBgeEmbeddings
|
||||||
from langchain_community.document_loaders import DirectoryLoader, TextLoader
|
from langchain_community.document_loaders import DirectoryLoader, TextLoader
|
||||||
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
||||||
from langchain.document_loaders import DirectoryLoader
|
|
||||||
from langchain_core.documents.base import Document
|
from langchain_core.documents.base import Document
|
||||||
from FlagEmbedding import FlagReranker
|
from FlagEmbedding import FlagReranker
|
||||||
|
|
||||||
@ -199,7 +198,7 @@ class Data_process():
|
|||||||
创建并保存向量库
|
创建并保存向量库
|
||||||
'''
|
'''
|
||||||
logger.info(f'Creating index...')
|
logger.info(f'Creating index...')
|
||||||
#split_doc = self.split_document(doc_dir)
|
split_doc = self.split_document(doc_dir)
|
||||||
split_qa = self.split_conversation(qa_dir)
|
split_qa = self.split_conversation(qa_dir)
|
||||||
# logger.info(f'split_doc == {len(split_doc)}')
|
# logger.info(f'split_doc == {len(split_doc)}')
|
||||||
# logger.info(f'split_qa == {len(split_qa)}')
|
# logger.info(f'split_qa == {len(split_qa)}')
|
||||||
@ -218,7 +217,7 @@ class Data_process():
|
|||||||
if not os.path.exists(vector_db_dir) or not os.listdir(vector_db_dir):
|
if not os.path.exists(vector_db_dir) or not os.listdir(vector_db_dir):
|
||||||
db = self.create_vector_db(emb_model)
|
db = self.create_vector_db(emb_model)
|
||||||
else:
|
else:
|
||||||
db = FAISS.load_local(vector_db_dir, emb_model, allow_dangerous_deserialization=True)
|
db = FAISS.load_local(vector_db_dir, emb_model)
|
||||||
return db
|
return db
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
|
|||||||
@ -2,8 +2,8 @@ from langchain_core.output_parsers import StrOutputParser
|
|||||||
from langchain_core.prompts import PromptTemplate
|
from langchain_core.prompts import PromptTemplate
|
||||||
from transformers.utils import logging
|
from transformers.utils import logging
|
||||||
|
|
||||||
from data_processing import Data_process
|
from rag.src.data_processing import Data_process
|
||||||
from config.config import prompt_template
|
from rag.src.config.config import prompt_template
|
||||||
logger = logging.get_logger(__name__)
|
logger = logging.get_logger(__name__)
|
||||||
|
|
||||||
|
|
||||||
@ -48,19 +48,19 @@ class EmoLLMRAG(object):
|
|||||||
ouput: 检索后并且 rerank 的内容
|
ouput: 检索后并且 rerank 的内容
|
||||||
"""
|
"""
|
||||||
|
|
||||||
content = ''
|
content = []
|
||||||
documents = self.vectorstores.similarity_search(query, k=self.retrieval_num)
|
documents = self.vectorstores.similarity_search(query, k=self.retrieval_num)
|
||||||
|
|
||||||
for doc in documents:
|
for doc in documents:
|
||||||
content += doc.page_content
|
content.append(doc.page_content)
|
||||||
|
|
||||||
# 如果需要rerank，调用接口对 documents 进行 rerank
|
# 如果需要rerank，调用接口对 documents 进行 rerank
|
||||||
if self.rerank_flag:
|
if self.rerank_flag:
|
||||||
documents, _ = self.data_processing_obj.rerank(documents, self.select_num)
|
documents, _ = self.data_processing_obj.rerank(documents, self.select_num)
|
||||||
|
|
||||||
content = ''
|
content = []
|
||||||
for doc in documents:
|
for doc in documents:
|
||||||
content += doc
|
content.append(doc)
|
||||||
logger.info(f'Retrieval data: {content}')
|
logger.info(f'Retrieval data: {content}')
|
||||||
return content
|
return content
|
||||||
|
|
||||||
|
|||||||
@ -12,6 +12,7 @@ import copy
|
|||||||
import os
|
import os
|
||||||
import warnings
|
import warnings
|
||||||
from dataclasses import asdict, dataclass
|
from dataclasses import asdict, dataclass
|
||||||
|
from rag.src.pipeline import EmoLLMRAG
|
||||||
from typing import Callable, List, Optional
|
from typing import Callable, List, Optional
|
||||||
|
|
||||||
import streamlit as st
|
import streamlit as st
|
||||||
@ -188,8 +189,9 @@ robot_prompt = "<|im_start|>assistant\n{robot}<|im_end|>\n"
|
|||||||
cur_query_prompt = "<|im_start|>user\n{user}<|im_end|>\n<|im_start|>assistant\n"
|
cur_query_prompt = "<|im_start|>user\n{user}<|im_end|>\n<|im_start|>assistant\n"
|
||||||
|
|
||||||
|
|
||||||
def combine_history(prompt):
|
def combine_history(prompt, retrieval_content=''):
|
||||||
messages = st.session_state.messages
|
messages = st.session_state.messages
|
||||||
|
prompt = f"你需要根据以下从书本中检索到的专业知识:`{retrieval_content}`。从一个心理专家的专业角度来回答后续提问：{prompt}"
|
||||||
meta_instruction = (
|
meta_instruction = (
|
||||||
"你是一个由aJupyter、Farewell、jujimeizuo、Smiling&Weeping研发（排名按字母顺序排序，不分先后）、散步提供技术支持、上海人工智能实验室提供支持开发的心理健康大模型。现在你是一个心理专家，我有一些心理问题，请你用专业的知识帮我解决。"
|
"你是一个由aJupyter、Farewell、jujimeizuo、Smiling&Weeping研发（排名按字母顺序排序，不分先后）、散步提供技术支持、上海人工智能实验室提供支持开发的心理健康大模型。现在你是一个心理专家，我有一些心理问题，请你用专业的知识帮我解决。"
|
||||||
)
|
)
|
||||||
@ -211,6 +213,7 @@ def main():
|
|||||||
# torch.cuda.empty_cache()
|
# torch.cuda.empty_cache()
|
||||||
print("load model begin.")
|
print("load model begin.")
|
||||||
model, tokenizer = load_model()
|
model, tokenizer = load_model()
|
||||||
|
rag_obj = EmoLLMRAG(model)
|
||||||
print("load model end.")
|
print("load model end.")
|
||||||
|
|
||||||
user_avator = "assets/user.png"
|
user_avator = "assets/user.png"
|
||||||
@ -232,9 +235,12 @@ def main():
|
|||||||
# Accept user input
|
# Accept user input
|
||||||
if prompt := st.chat_input("What is up?"):
|
if prompt := st.chat_input("What is up?"):
|
||||||
# Display user message in chat message container
|
# Display user message in chat message container
|
||||||
|
retrieval_content = rag_obj.get_retrieval_content(prompt)
|
||||||
with st.chat_message("user", avatar=user_avator):
|
with st.chat_message("user", avatar=user_avator):
|
||||||
st.markdown(prompt)
|
st.markdown(prompt)
|
||||||
real_prompt = combine_history(prompt)
|
#st.markdown(retrieval_content)
|
||||||
|
|
||||||
|
real_prompt = combine_history(prompt, retrieval_content)
|
||||||
# Add user message to chat history
|
# Add user message to chat history
|
||||||
st.session_state.messages.append({"role": "user", "content": prompt, "avatar": user_avator})
|
st.session_state.messages.append({"role": "user", "content": prompt, "avatar": user_avator})
|
||||||
|
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user