RYDE-WORK/Langchain-Chatchat
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/Langchain-Chatchat.git synced 2026-09-18 20:13:21 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

支持通过配置项同时启动多个模型，将Wiki纳入samples知识库 (#2002)

Browse Source 
新功能：
- 将 LLM_MODEL 配置项改为 LLM_MODELS 列表，同时启动多个模型
- 将 wiki 纳入 samples 知识库

依赖变化：
- 指定 streamlit~=1.27.0。1.26.0会报rerun错误，1.28.0会有无限刷新错误

修复优化：
- 优化 get_default_llm_model 逻辑
- 适配 Qwen 在线 API 做 Embeddings 时最大 25 行的限制
- 列出知识库磁盘文件时跳过 . 开头的文件
This commit is contained in:
liunux4odoo 2023-11-09 22:15:52 +08:00 committed by GitHub
parent ce1001a043
commit b51ba11f45
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
33 changed files with 238 additions and 194 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.gitignore vendored
View File

@ -2,7 +2,10 @@
*.log.*
*.bak
logs
/knowledge_base/
/knowledge_base/*
!/knowledge_base/samples
/knowledge_base/samples/vector_store
/configs/*.py
.vscode/

3
.gitmodules vendored Normal file
View File

@ -0,0 +1,3 @@
[submodule "knowledge_base/samples/content/wiki"]
path = knowledge_base/samples/content/wiki
url = https://github.com/chatchat-space/Langchain-Chatchat.wiki.git

4
chains/llmchain_with_history.py
View File

@ -1,12 +1,12 @@
from server.utils import get_ChatOpenAI
from configs.model_config import LLM_MODEL, TEMPERATURE
from configs.model_config import LLM_MODELS, TEMPERATURE
from langchain.chains import LLMChain
from langchain.prompts.chat import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
)
model = get_ChatOpenAI(model_name=LLM_MODEL, temperature=TEMPERATURE)
model = get_ChatOpenAI(model_name=LLM_MODELS[0], temperature=TEMPERATURE)
human_prompt = "{input}"

1
configs/basic_config.py.example
View File

@ -2,6 +2,7 @@ import logging
import os
import langchain
# 是否显示详细日志
log_verbose = False
langchain.verbose = False

3
configs/kb_config.py.example
View File

@ -56,7 +56,10 @@ KB_INFO = {
"知识库名称": "知识库介绍",
"samples": "关于本项目issue的解答",
}
# 通常情况下不需要更改以下内容
# 知识库默认存储路径
KB_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "knowledge_base")
if not os.path.exists(KB_ROOT_PATH):

187
configs/model_config.py.example
View File

@ -1,96 +1,13 @@
import os
# 可以指定一个绝对路径，统一存放所有的Embedding和LLM模型。
# 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录
# 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录。
# 如果模型目录名称和 MODEL_PATH 中的 key 或 value 相同，程序会自动检测加载，无需修改 MODEL_PATH 中的路径。
MODEL_ROOT_PATH = ""
# 在以下字典中修改属性值，以指定本地embedding模型存储位置。支持3种设置方法：
# 1、将对应的值修改为模型绝对路径
# 2、不修改此处的值（以 text2vec 为例）：
# 2.1 如果{MODEL_ROOT_PATH}下存在如下任一子目录：
# - text2vec
# - GanymedeNil/text2vec-large-chinese
# - text2vec-large-chinese
# 2.2 如果以上本地路径不存在，则使用huggingface模型
MODEL_PATH = {
"embed_model": {
"ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
"ernie-base": "nghuyong/ernie-3.0-base-zh",
"text2vec-base": "shibing624/text2vec-base-chinese",
"text2vec": "GanymedeNil/text2vec-large-chinese",
"text2vec-paraphrase": "shibing624/text2vec-base-chinese-paraphrase",
"text2vec-sentence": "shibing624/text2vec-base-chinese-sentence",
"text2vec-multilingual": "shibing624/text2vec-base-multilingual",
"text2vec-bge-large-chinese": "shibing624/text2vec-bge-large-chinese",
"m3e-small": "moka-ai/m3e-small",
"m3e-base": "moka-ai/m3e-base",
"m3e-large": "moka-ai/m3e-large",
"bge-small-zh": "BAAI/bge-small-zh",
"bge-base-zh": "BAAI/bge-base-zh",
"bge-large-zh": "BAAI/bge-large-zh",
"bge-large-zh-noinstruct": "BAAI/bge-large-zh-noinstruct",
"bge-base-zh-v1.5": "BAAI/bge-base-zh-v1.5",
"bge-large-zh-v1.5": "BAAI/bge-large-zh-v1.5",
"piccolo-base-zh": "sensenova/piccolo-base-zh",
"piccolo-large-zh": "sensenova/piccolo-large-zh",
"text-embedding-ada-002": "your OPENAI_API_KEY",
},
# TODO: add all supported llm models
"llm_model": {
# 以下部分模型并未完全测试，仅根据fastchat和vllm模型的模型列表推定支持
"chatglm2-6b": "THUDM/chatglm2-6b",
"chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
"chatglm3-6b": "THUDM/chatglm3-6b-32k",
"chatglm3-6b-32k": "THUDM/chatglm3-6b-32k",
"baichuan2-13b": "baichuan-inc/Baichuan2-13B-Chat",
"baichuan2-7b": "baichuan-inc/Baichuan2-7B-Chat",
"baichuan-7b": "baichuan-inc/Baichuan-7B",
"baichuan-13b": "baichuan-inc/Baichuan-13B",
'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat',
"aquila-7b": "BAAI/Aquila-7B",
"aquilachat-7b": "BAAI/AquilaChat-7B",
"internlm-7b": "internlm/internlm-7b",
"internlm-chat-7b": "internlm/internlm-chat-7b",
"falcon-7b": "tiiuae/falcon-7b",
"falcon-40b": "tiiuae/falcon-40b",
"falcon-rw-7b": "tiiuae/falcon-rw-7b",
"gpt2": "gpt2",
"gpt2-xl": "gpt2-xl",
"gpt-j-6b": "EleutherAI/gpt-j-6b",
"gpt4all-j": "nomic-ai/gpt4all-j",
"gpt-neox-20b": "EleutherAI/gpt-neox-20b",
"pythia-12b": "EleutherAI/pythia-12b",
"oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
"dolly-v2-12b": "databricks/dolly-v2-12b",
"stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
"Llama-2-13b-hf": "meta-llama/Llama-2-13b-hf",
"Llama-2-70b-hf": "meta-llama/Llama-2-70b-hf",
"open_llama_13b": "openlm-research/open_llama_13b",
"vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3",
"koala": "young-geng/koala",
"mpt-7b": "mosaicml/mpt-7b",
"mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
"mpt-30b": "mosaicml/mpt-30b",
"opt-66b": "facebook/opt-66b",
"opt-iml-max-30b": "facebook/opt-iml-max-30b",
"Qwen-7B": "Qwen/Qwen-7B",
"Qwen-14B": "Qwen/Qwen-14B",
"Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
"Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
},
}
# 选用的 Embedding 名称
EMBEDDING_MODEL = "m3e-base" # 可以尝试最新的嵌入式sota模型：bge-large-zh-v1.5
EMBEDDING_MODEL = "m3e-base" # bge-large-zh
# Embedding 模型运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。
EMBEDDING_DEVICE = "auto"
@ -99,9 +16,11 @@ EMBEDDING_DEVICE = "auto"
EMBEDDING_KEYWORD_FILE = "keywords.txt"
EMBEDDING_MODEL_OUTPUT_PATH = "output"
# LLM 名称
LLM_MODEL = "chatglm2-6b"
# AgentLM模型的名称 (可以不指定，指定之后就锁定进入Agent之后的Chain的模型，不指定就是LLM_MODEL)
# 要运行的 LLM 名称，可以包括本地模型和在线模型。
# 第一个将作为 API 和 WEBUI 的默认模型
LLM_MODELS = ["chatglm2-6b-int4", "zhipu-api", "openai-api]
# AgentLM模型的名称 (可以不指定，指定之后就锁定进入Agent之后的Chain的模型，不指定就是LLM_MODELS[0])
Agent_MODEL = None
# LLM 运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。
@ -111,7 +30,6 @@ LLM_DEVICE = "auto"
HISTORY_LEN = 3
# 大模型最长支持的长度，如果不填写，则使用模型默认的最大长度，如果填写，则为用户设定的最大长度
MAX_TOKENS = None
# LLM通用对话参数
@ -197,6 +115,93 @@ ONLINE_LLM_MODEL = {
},
}
# 在以下字典中修改属性值，以指定本地embedding模型存储位置。支持3种设置方法：
# 1、将对应的值修改为模型绝对路径
# 2、不修改此处的值（以 text2vec 为例）：
# 2.1 如果{MODEL_ROOT_PATH}下存在如下任一子目录：
# - text2vec
# - GanymedeNil/text2vec-large-chinese
# - text2vec-large-chinese
# 2.2 如果以上本地路径不存在，则使用huggingface模型
MODEL_PATH = {
"embed_model": {
"ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
"ernie-base": "nghuyong/ernie-3.0-base-zh",
"text2vec-base": "shibing624/text2vec-base-chinese",
"text2vec": "GanymedeNil/text2vec-large-chinese",
"text2vec-paraphrase": "shibing624/text2vec-base-chinese-paraphrase",
"text2vec-sentence": "shibing624/text2vec-base-chinese-sentence",
"text2vec-multilingual": "shibing624/text2vec-base-multilingual",
"text2vec-bge-large-chinese": "shibing624/text2vec-bge-large-chinese",
"m3e-small": "moka-ai/m3e-small",
"m3e-base": "moka-ai/m3e-base",
"m3e-large": "moka-ai/m3e-large",
"bge-small-zh": "BAAI/bge-small-zh",
"bge-base-zh": "BAAI/bge-base-zh",
"bge-large-zh": "BAAI/bge-large-zh",
"bge-large-zh-noinstruct": "BAAI/bge-large-zh-noinstruct",
"bge-base-zh-v1.5": "BAAI/bge-base-zh-v1.5",
"bge-large-zh-v1.5": "BAAI/bge-large-zh-v1.5",
"piccolo-base-zh": "sensenova/piccolo-base-zh",
"piccolo-large-zh": "sensenova/piccolo-large-zh",
"text-embedding-ada-002": "your OPENAI_API_KEY",
},
"llm_model": {
# 以下部分模型并未完全测试，仅根据fastchat和vllm模型的模型列表推定支持
"chatglm2-6b": "THUDM/chatglm2-6b",
"chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
"chatglm3-6b": "THUDM/chatglm3-6b-32k",
"chatglm3-6b-32k": "THUDM/chatglm3-6b-32k",
"baichuan2-13b": "baichuan-inc/Baichuan2-13B-Chat",
"baichuan2-7b": "baichuan-inc/Baichuan2-7B-Chat",
"baichuan-7b": "baichuan-inc/Baichuan-7B",
"baichuan-13b": "baichuan-inc/Baichuan-13B",
'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat',
"aquila-7b": "BAAI/Aquila-7B",
"aquilachat-7b": "BAAI/AquilaChat-7B",
"internlm-7b": "internlm/internlm-7b",
"internlm-chat-7b": "internlm/internlm-chat-7b",
"falcon-7b": "tiiuae/falcon-7b",
"falcon-40b": "tiiuae/falcon-40b",
"falcon-rw-7b": "tiiuae/falcon-rw-7b",
"gpt2": "gpt2",
"gpt2-xl": "gpt2-xl",
"gpt-j-6b": "EleutherAI/gpt-j-6b",
"gpt4all-j": "nomic-ai/gpt4all-j",
"gpt-neox-20b": "EleutherAI/gpt-neox-20b",
"pythia-12b": "EleutherAI/pythia-12b",
"oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
"dolly-v2-12b": "databricks/dolly-v2-12b",
"stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
"Llama-2-13b-hf": "meta-llama/Llama-2-13b-hf",
"Llama-2-70b-hf": "meta-llama/Llama-2-70b-hf",
"open_llama_13b": "openlm-research/open_llama_13b",
"vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3",
"koala": "young-geng/koala",
"mpt-7b": "mosaicml/mpt-7b",
"mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
"mpt-30b": "mosaicml/mpt-30b",
"opt-66b": "facebook/opt-66b",
"opt-iml-max-30b": "facebook/opt-iml-max-30b",
"Qwen-7B": "Qwen/Qwen-7B",
"Qwen-14B": "Qwen/Qwen-14B",
"Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
"Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
},
}
# 通常情况下不需要更改以下内容
# nltk 模型存储路径

50
configs/server_config.py.example
View File

@ -31,8 +31,7 @@ FSCHAT_OPENAI_API = {
# fastchat model_worker server
# 这些模型必须是在model_config.MODEL_PATH或ONLINE_MODEL中正确配置的。
# 在启动startup.py时，可用通过`--model-worker --model-name xxxx`指定模型，不指定则为LLM_MODEL
# 必须在这里添加的模型才会出现在WEBUI中可选模型列表里（LLM_MODEL会自动添加）
# 在启动startup.py时，可用通过`--model-name xxxx yyyy`指定模型，不指定则为LLM_MODELS
FSCHAT_MODEL_WORKERS = {
# 所有模型共用的默认配置，可在模型专项配置中进行覆盖。
"default": {
@ -58,7 +57,7 @@ FSCHAT_MODEL_WORKERS = {
# "awq_ckpt": None,
# "awq_wbits": 16,
# "awq_groupsize": -1,
# "model_names": [LLM_MODEL],
# "model_names": LLM_MODELS,
# "conv_template": None,
# "limit_worker_concurrency": 5,
# "stream_interval": 2,
@ -96,30 +95,31 @@ FSCHAT_MODEL_WORKERS = {
# "device": "cpu",
# },
"zhipu-api": { # 请为每个要运行的在线API设置不同的端口
#以下配置可以不用修改，在model_config中设置启动的模型
"zhipu-api": {
"port": 21001,
},
# "minimax-api": {
# "port": 21002,
# },
# "xinghuo-api": {
# "port": 21003,
# },
# "qianfan-api": {
# "port": 21004,
# },
# "fangzhou-api": {
# "port": 21005,
# },
# "qwen-api": {
# "port": 21006,
# },
# "baichuan-api": {
# "port": 21007,
# },
# "azure-api": {
# "port": 21008,
# },
"minimax-api": {
"port": 21002,
},
"xinghuo-api": {
"port": 21003,
},
"qianfan-api": {
"port": 21004,
},
"fangzhou-api": {
"port": 21005,
},
"qwen-api": {
"port": 21006,
},
"baichuan-api": {
"port": 21007,
},
"azure-api": {
"port": 21008,
},
}
# fastchat multi model worker server

0
knowledge_base/samples/isssues_merge/langchain-ChatGLM_closed.csv → knowledge_base/samples/content/test_files/langchain-ChatGLM_closed.csv
View File

Internal Server Error - Gitea4PDT
500 Internal Server Error

Gitea Version: 1.23.8