mirror of
https://github.com/RYDE-WORK/Langchain-Chatchat.git
synced 2026-01-30 02:35:29 +08:00
7497b261b3
* Fix 知识库无法上载,NLTK_DATA_PATH路径错误 (#236) * Update chatglm_llm.py (#242) * 完善知识库路径问题，完善api接口 统一webui、API接口知识库路径，后续路径如下： 知识库路经就是：/项目代码文件夹/vector_store/'知识库名字' 文件存放路经：/项目代码文件夹/content/'知识库名字' 修复通过api接口创建知识库的BUG，完善API接口功能。 * Update model_config.py --------- Co-authored-by: Bob Chang <bob-chang@outlook.com> Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
63 lines
2.0 KiB
Python
63 lines
2.0 KiB
Python
import torch.cuda
|
||
import torch.backends
|
||
import os
|
||
|
||
embedding_model_dict = {
|
||
"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",
|
||
}
|
||
|
||
# Embedding model name
|
||
EMBEDDING_MODEL = "text2vec"
|
||
|
||
# Embedding running device
|
||
EMBEDDING_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
|
||
|
||
# supported LLM models
|
||
llm_model_dict = {
|
||
"chatyuan": "ClueAI/ChatYuan-large-v2",
|
||
"chatglm-6b-int4-qe": "THUDM/chatglm-6b-int4-qe",
|
||
"chatglm-6b-int4": "THUDM/chatglm-6b-int4",
|
||
"chatglm-6b-int8": "THUDM/chatglm-6b-int8",
|
||
"chatglm-6b": "THUDM/chatglm-6b",
|
||
}
|
||
|
||
# LLM model name
|
||
LLM_MODEL = "chatglm-6b"
|
||
|
||
# LLM lora path，默认为空，如果有请直接指定文件夹路径
|
||
LLM_LORA_PATH = ""
|
||
USE_LORA = True if LLM_LORA_PATH else False
|
||
|
||
# LLM streaming reponse
|
||
STREAMING = True
|
||
|
||
# Use p-tuning-v2 PrefixEncoder
|
||
USE_PTUNING_V2 = False
|
||
|
||
# LLM running device
|
||
LLM_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
|
||
|
||
VS_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "vector_store")
|
||
|
||
UPLOAD_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "content")
|
||
|
||
# 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
|
||
PROMPT_TEMPLATE = """已知信息：
|
||
{context}
|
||
|
||
根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
|
||
|
||
# 匹配后单段上下文长度
|
||
CHUNK_SIZE = 250
|
||
|
||
# LLM input history length
|
||
LLM_HISTORY_LEN = 3
|
||
|
||
# return top-k text chunk from vector store
|
||
VECTOR_SEARCH_TOP_K = 5
|
||
|
||
NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data")
|