Add support for folder path as input
This commit is contained in:
imClumsyPanda
parent
47e959ef79
commit
4ec339777c
21
README.md
21
README.md
|
|
@ -25,8 +25,10 @@
|
|||
4. 更正`README.md`中的代码错误（感谢 [@calcitem](https://github.com/calcitem)）。
|
||||
|
||||
**[2023/04/11]**
|
||||
1. 加入 Web UI V0.1 版本（感谢 [@liangtongt](https://github.com/liangtongt)）。
|
||||
|
||||
1. 加入 Web UI V0.1 版本（感谢 [@liangtongt](https://github.com/liangtongt)）；
|
||||
2. `README.md`中增加常见问题（感谢 [@calcitem](https://github.com/calcitem)）；
|
||||
3. 增加 LLM 和 Embedding 模型运行设备是否可用`cuda`、`mps`、`cpu`的自动判断。
|
||||
4. 在`knowledge_based_chatglm.py`中增加对`filepath`的判断，在之前支持单个文件导入的基础上，现支持单个文件夹路径作为输入，输入后将会遍历文件夹中各个文件，并在命令行中显示每个文件是否成功加载。
|
||||
|
||||
## 使用方式
|
||||
|
||||
|
|
@ -71,11 +73,18 @@ python knowledge_based_chatglm.py
|
|||
```
|
||||
|
||||
|
||||
### 已知问题
|
||||
- 目前已测试支持 txt、docx、md 格式文件，更多文件格式请参考 [langchain 文档](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/unstructured_file.html)，目前已知文档中若含有特殊字符，可能存在文件无法加载的问题；
|
||||
- 使用 macOS 运行本项目时，可能因为 macOS 版本为 13.3 及以上版本导致与 pytorch 不兼容，无法正常运行的情况。
|
||||
|
||||
### 常见问题
|
||||
Q: 本项目支持哪些文件格式？
|
||||
|
||||
A: 目前已测试支持 txt、docx、md 格式文件，更多文件格式请参考 [langchain 文档](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/unstructured_file.html)。目前已知文档中若含有特殊字符，可能存在文件无法加载的问题。
|
||||
|
||||
Q: 读取特定格式文件时遇到缺少`detectron2`时如何解决？
|
||||
|
||||
A: 因该包安装过程中遇到问题较多，且仅部分格式文件需要，所以未加入`requirements.txt`。可以通过一下命令安装
|
||||
|
||||
```commandline
|
||||
pip install "detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"
|
||||
```
|
||||
|
||||
Q: `Resource punkt not found.` 如何解决？
|
||||
|
||||
|
|
|
|||
|
|
@ -4,8 +4,8 @@ from langchain.llms.utils import enforce_stop_tokens
|
|||
from transformers import AutoTokenizer, AutoModel
|
||||
import torch
|
||||
|
||||
DEVICE = "cuda"
|
||||
DEVICE_ID = "0"
|
||||
DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
|
||||
DEVICE_ID = "0" if torch.cuda.is_available() else None
|
||||
CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE_ID else DEVICE
|
||||
|
||||
|
||||
|
|
@ -18,7 +18,7 @@ def torch_gc():
|
|||
|
||||
class ChatGLM(LLM):
|
||||
max_token: int = 10000
|
||||
temperature: float = 0.1
|
||||
temperature: float = 0.01
|
||||
top_p = 0.9
|
||||
history = []
|
||||
tokenizer: object = None
|
||||
|
|
@ -48,12 +48,12 @@ class ChatGLM(LLM):
|
|||
self.history = self.history+[[None, response]]
|
||||
return response
|
||||
|
||||
def load_model(self,
|
||||
model_name_or_path: str = "THUDM/chatglm-6b"):
|
||||
def load_model(self, model_name_or_path: str = "THUDM/chatglm-6b"):
|
||||
self.tokenizer = AutoTokenizer.from_pretrained(
|
||||
model_name_or_path,
|
||||
trust_remote_code=True
|
||||
)
|
||||
if torch.cuda.is_available():
|
||||
self.model = (
|
||||
AutoModel.from_pretrained(
|
||||
model_name_or_path,
|
||||
|
|
@ -61,3 +61,19 @@ class ChatGLM(LLM):
|
|||
.half()
|
||||
.cuda()
|
||||
)
|
||||
elif torch.backends.mps.is_available():
|
||||
self.model = (
|
||||
AutoModel.from_pretrained(
|
||||
model_name_or_path,
|
||||
trust_remote_code=True)
|
||||
.float()
|
||||
.to('mps')
|
||||
)
|
||||
else:
|
||||
self.model = (
|
||||
AutoModel.from_pretrained(
|
||||
model_name_or_path,
|
||||
trust_remote_code=True)
|
||||
.float()
|
||||
)
|
||||
self.model = self.model.eval()
|
||||
|
|
|
|||
|
|
@ -8,12 +8,17 @@ from langchain.embeddings.huggingface import HuggingFaceEmbeddings
|
|||
from langchain.vectorstores import FAISS
|
||||
from langchain.document_loaders import UnstructuredFileLoader
|
||||
from chatglm_llm import ChatGLM
|
||||
import sentence_transformers
|
||||
import torch
|
||||
import os
|
||||
|
||||
|
||||
# Global Parameters
|
||||
EMBEDDING_MODEL = "text2vec"
|
||||
EMBEDDING_MODEL = "local"#"text2vec"
|
||||
VECTOR_SEARCH_TOP_K = 6
|
||||
LLM_MODEL = "chatglm-6b"
|
||||
LLM_MODEL = "local"#"chatglm-6b"
|
||||
LLM_HISTORY_LEN = 3
|
||||
DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
|
||||
|
||||
# Show reply with source text from input document
|
||||
REPLY_WITH_SOURCE = True
|
||||
|
|
@ -22,12 +27,14 @@ embedding_model_dict = {
|
|||
"ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
|
||||
"ernie-base": "nghuyong/ernie-3.0-base-zh",
|
||||
"text2vec": "GanymedeNil/text2vec-large-chinese",
|
||||
"local": "/Users/liuqian/Downloads/ChatGLM-6B/text2vec-large-chinese"
|
||||
}
|
||||
|
||||
llm_model_dict = {
|
||||
"chatglm-6b-int4-qe": "THUDM/chatglm-6b-int4-qe",
|
||||
"chatglm-6b-int4": "THUDM/chatglm-6b-int4",
|
||||
"chatglm-6b": "THUDM/chatglm-6b",
|
||||
"local": "/Users/liuqian/Downloads/ChatGLM-6B/chatglm-6b"
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -40,11 +47,25 @@ def init_cfg(LLM_MODEL, EMBEDDING_MODEL, LLM_HISTORY_LEN, V_SEARCH_TOP_K=6):
|
|||
chatglm.history_len = LLM_HISTORY_LEN
|
||||
|
||||
embeddings = HuggingFaceEmbeddings(model_name=embedding_model_dict[EMBEDDING_MODEL],)
|
||||
embeddings.client = sentence_transformers.SentenceTransformer(embeddings.model_name,
|
||||
device=DEVICE)
|
||||
|
||||
|
||||
def init_knowledge_vector_store(filepath):
|
||||
def init_knowledge_vector_store(filepath:str):
|
||||
if os.path.isfile(filepath):
|
||||
loader = UnstructuredFileLoader(filepath, mode="elements")
|
||||
docs = loader.load()
|
||||
print(f"{os.path.split(filepath)[-1]} 已成功加载")
|
||||
elif os.path.isdir(filepath):
|
||||
docs = []
|
||||
for file in os.listdir(filepath):
|
||||
fullfilepath = os.path.join(filepath, file)
|
||||
try:
|
||||
loader = UnstructuredFileLoader(fullfilepath, mode="elements")
|
||||
docs += loader.load()
|
||||
print(f"{file} 已成功加载")
|
||||
except:
|
||||
print(f"{file} 未能成功加载")
|
||||
vector_store = FAISS.from_documents(docs, embeddings)
|
||||
return vector_store
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue