ironspiderman / machinelearningpractice Goto Github PK

chatglm_qa在上传文本文件时候报错
Traceback (most recent call last): File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\routes.py", line 534, in predict output = await route_utils.call_process_api( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api output = await app.get_blocks().process_api( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\blocks.py", line 1550, in process_api result = await self.call_function( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\blocks.py", line 1185, in call_function prediction = await anyio.to_thread.run_sync( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\anyio\to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\utils.py", line 661, in wrapper response = f(*args, **kwargs) File "E:\ChatGLM\MachineLearningPractice-main\03_上传文档问答.py", line 91, in add_file documents = load_documents(directory) File "E:\ChatGLM\MachineLearningPractice-main\03_上传文档问答.py", line 26, in load_documents documents = loader.load() File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\langchain\document_loaders\directory.py", line 156, in load self.load_file(i, p, docs, pbar) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\langchain\document_loaders\directory.py", line 105, in load_file raise e File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\langchain\document_loaders\directory.py", line 99, in load_file sub_docs = self.loader_cls(str(item), **self.loader_kwargs).load() File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\langchain\document_loaders\unstructured.py", line 86, in load elements = self._get_elements() File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\langchain\document_loaders\unstructured.py", line 172, in _get_elements return partition(filename=self.file_path, **self.unstructured_kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\partition\auto.py", line 434, in partition elements = partition_text( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\partition\text.py", line 93, in partition_text return _partition_text( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\documents\elements.py", line 526, in wrapper elements = func(*args, **kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\file_utils\filetype.py", line 619, in wrapper elements = func(*args, **kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\file_utils\filetype.py", line 574, in wrapper elements = func(*args, **kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\chunking\__init__.py", line 69, in wrapper elements = func(*args, **kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\partition\text.py", line 190, in _partition_text element = element_from_text(ctext) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\partition\text.py", line 235, in element_from_text elif is_possible_narrative_text(text): File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\partition\text_type.py", line 88, in is_possible_narrative_text if "eng" in languages and (sentence_count(text, 3) < 2) and (not contains_verb(text)): File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\partition\text_type.py", line 190, in contains_verb pos_tags = pos_tag(text) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\nlp\tokenize.py", line 44, in pos_tag _download_nltk_package_if_not_present( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\unstructured\nlp\tokenize.py", line 21, in _download_nltk_package_if_not_present nltk.find(f"{package_category}/{package_name}") File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\nltk\data.py", line 555, in find return find(modified_name, paths) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\nltk\data.py", line 542, in find return ZipFilePathPointer(p, zipentry) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\nltk\compat.py", line 41, in _decorator return init_func(*args, **kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\nltk\data.py", line 394, in __init__ zipfile = OpenOnDemandZipFile(os.path.abspath(zipfile)) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\nltk\compat.py", line 41, in _decorator return init_func(*args, **kwargs) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\nltk\data.py", line 935, in __init__ zipfile.ZipFile.__init__(self, filename) File "C:\Users\S3111\.conda\envs\chatglm\lib\zipfile.py", line 1269, in __init__ self._RealGetContents() File "C:\Users\S3111\.conda\envs\chatglm\lib\zipfile.py", line 1336, in _RealGetContents raise BadZipFile("File is not a zip file") zipfile.BadZipFile: File is not a zip file Traceback (most recent call last): File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\queueing.py", line 407, in call_prediction output = await route_utils.call_process_api( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api output = await app.get_blocks().process_api( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\blocks.py", line 1550, in process_api result = await self.call_function( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\blocks.py", line 1199, in call_function prediction = await utils.async_iteration(iterator) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\utils.py", line 519, in async_iteration return await iterator.__anext__() File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\utils.py", line 512, in __anext__ return await anyio.to_thread.run_sync( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\anyio\to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\utils.py", line 495, in run_sync_iterator_async return next(iterator) File "C:\Users\S3111\.conda\envs\chatglm\lib\site-packages\gradio\utils.py", line 649, in gen_wrapper yield from f(*args, **kwargs) File "E:\ChatGLM\MachineLearningPractice-main\03_上传文档问答.py", line 99, in bot message = history[-1][0] IndexError: list index out of range

请问一下，

QA_CHAIN_PROMPT = PromptTemplate.from_template("""根据下面的上下文（context）内容回答问题。
如果你不知道答案，就回答不知道，不要试图编造答案。
答案最多3句话，保持答案简介。
总是在答案结束时说”谢谢你的提问！“
{context}
问题：{question}
""")

这个prompt是如何作用的？好像没看到相关的调用

Traceback (most recent call last):
File "/data/glm/LLMKB.py", line 80, in
documents = load_documents()
File "/data/glm/LLMKB.py", line 30, in load_documents
documents = loader.load()
File "/dataanaconda3/envs/glm/lib/python3.10/site-packages/langchain/document_loaders/directory.py", line 156, in load
self.load_file(i, p, docs, pbar)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/langchain/document_loaders/directory.py", line 105, in load_file
raise e
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/langchain/document_loaders/directory.py", line 99, in load_file
sub_docs = self.loader_cls(str(item), **self.loader_kwargs).load()
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/langchain/document_loaders/unstructured.py", line 86, in load
elements = self._get_elements()
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/langchain/document_loaders/unstructured.py", line 172, in _get_elements
return partition(filename=self.file_path, **self.unstructured_kwargs)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/partition/auto.py", line 434, in partition
elements = partition_text(
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/partition/text.py", line 95, in partition_text
return _partition_text(
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/documents/elements.py", line 526, in wrapper
elements = func(*args, **kwargs)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/file_utils/filetype.py", line 627, in wrapper
elements = func(*args, **kwargs)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/file_utils/filetype.py", line 582, in wrapper
elements = func(*args, **kwargs)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/chunking/init.py", line 71, in wrapper
elements = func(*args, **kwargs)
File "/data/liujiqiang/anaconda3/envs/glm4/lib/python3.10/site-packages/unstructured/partition/text.py", line 192, in _partition_text
element = element_from_text(ctext)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/partition/text.py", line 285, in element_from_text
elif is_possible_narrative_text(text):
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/partition/text_type.py", line 88, in is_possible_narrative_text
if "eng" in languages and (sentence_count(text, 3) < 2) and (not contains_verb(text)):
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/partition/text_type.py", line 190, in contains_verb
pos_tags = pos_tag(text)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/nlp/tokenize.py", line 44, in pos_tag
_download_nltk_package_if_not_present(
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/unstructured/nlp/tokenize.py", line 21, in _download_nltk_package_if_not_present
nltk.find(f"{package_category}/{package_name}")
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/nltk/data.py", line 555, in find
return find(modified_name, paths)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/nltk/data.py", line 542, in find
return ZipFilePathPointer(p, zipentry)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/nltk/compat.py", line 41, in _decorator
return init_func(*args, **kwargs)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/nltk/data.py", line 394, in init
zipfile = OpenOnDemandZipFile(os.path.abspath(zipfile))
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/nltk/compat.py", line 41, in _decorator
return init_func(*args, **kwargs)
File "/data/anaconda3/envs/glm/lib/python3.10/site-packages/nltk/data.py", line 935, in init
zipfile.ZipFile.init(self, filename)
File "/data/anaconda3/envs/glm/lib/python3.10/zipfile.py", line 1269, in init
self._RealGetContents()
File "/data/anaconda3/envs/glm/lib/python3.10/zipfile.py", line 1336, in _RealGetContents
raise BadZipFile("File is not a zip file")
zipfile.BadZipFile: File is not a zip file

上传新的文件，可以写入向量库，但程序必须重启，新加入的文档向量才生效，请问是什么原因？
另外，ChatGLM函数的参数名错误，应该是endpoint_url.

Traceback (most recent call last):
File "D:\MachineLearningPractice-main\chatglm_qa\chatglm_document_qa.py", line 69, in
db = store_chroma(documents, embeddings)
File "D:\MachineLearningPractice-main\chatglm_qa\chatglm_document_qa.py", line 59, in store_chroma
db = Chroma.from_documents(docs, embeddings, persist_directory=persist_directory)
File "D:\Anaconda3\lib\site-packages\langchain_community\vectorstores\chroma.py", line 778, in from_documents
return cls.from_texts(
File "D:\Anaconda3\lib\site-packages\langchain_community\vectorstores\chroma.py", line 736, in from_texts
chroma_collection.add_texts(
File "D:\Anaconda3\lib\site-packages\langchain_community\vectorstores\chroma.py", line 275, in add_texts
embeddings = self._embedding_function.embed_documents(texts)
File "D:\Anaconda3\lib\site-packages\langchain_community\embeddings\huggingface.py", line 91, in embed_documents
embeddings = self.client.encode(texts, **self.encode_kwargs)
File "D:\Anaconda3\lib\site-packages\sentence_transformers\SentenceTransformer.py", line 153, in encode
self.to(device)
File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 989, in to
return self._apply(convert)
File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
module._apply(fn)
File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
module._apply(fn)
File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 664, in apply
param_applied = fn(param)
File "D:\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 987, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "D:\Anaconda3\lib\site-packages\torch\cuda_init.py", line 221, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

b站链接