weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' into dev

This commit is contained in:
imClumsyPanda 2023-05-14 00:14:43 +08:00
parent c86dd4dd47 3ff885d0d3
commit 5284fb2726
5 changed files with 34 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
api.py
View File

@ -181,7 +181,7 @@ async def delete_docs(
if os.path.exists(doc_path):
os.remove(doc_path)
else:
return {"code": 1, "msg": f"document {doc_name} not found"}
BaseResponse(code=1, msg=f"document {doc_name} not found")
remain_docs = await list_docs(knowledge_base_id)
if remain_docs["code"] != 0 or len(remain_docs["data"]) == 0:
@ -211,24 +211,30 @@ async def local_doc_chat(
):
vs_path = os.path.join(VS_ROOT_PATH, knowledge_base_id)
if not os.path.exists(vs_path):
raise ValueError(f"Knowledge base {knowledge_base_id} not found")
# return BaseResponse(code=1, msg=f"Knowledge base {knowledge_base_id} not found")
return ChatMessage(
question=question,
response=f"Knowledge base {knowledge_base_id} not found",
history=history,
source_documents=[],
)
else:
for resp, history in local_doc_qa.get_knowledge_based_answer(
query=question, vs_path=vs_path, chat_history=history, streaming=True
):
pass
source_documents = [
f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
f"""相关度：{doc.metadata['score']}\n\n"""
for inum, doc in enumerate(resp["source_documents"])
]
for resp, history in local_doc_qa.get_knowledge_based_answer(
query=question, vs_path=vs_path, chat_history=history, streaming=True
):
pass
source_documents = [
f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
f"""相关度：{doc.metadata['score']}\n\n"""
for inum, doc in enumerate(resp["source_documents"])
]
return ChatMessage(
question=question,
response=resp["result"],
history=history,
source_documents=source_documents,
)
return ChatMessage(
question=question,
response=resp["result"],
history=history,
source_documents=source_documents,
)
async def chat(

6
chains/local_doc_qa.py
View File

@ -39,7 +39,11 @@ def load_file(filepath, sentence_size=SENTENCE_SIZE):
def write_check_file(filepath, docs):
fout = open('load_file.txt', 'a')
folder_path = os.path.join(os.path.dirname(filepath), "tmp_files")
if not os.path.exists(folder_path):
os.makedirs(folder_path)
fp = os.path.join(folder_path, 'load_file.txt')
fout = open(fp, 'a')
fout.write("filepath=%s,len=%s" % (filepath, len(docs)))
fout.write('\n')
for i in docs:

6
cli_demo.py
View File

@ -31,13 +31,13 @@ if __name__ == "__main__":
chat_history=history,
streaming=STREAMING):
if STREAMING:
logger.info(resp["result"][last_print_len:])
print(resp["result"][last_print_len:], end="", flush=True)
last_print_len = len(resp["result"])
else:
logger.info(resp["result"])
print(resp["result"])
if REPLY_WITH_SOURCE:
source_text = [f"""出处 [{inum + 1}] {os.path.split(doc.metadata['source'])[-1]}：\n\n{doc.page_content}\n\n"""
# f"""相关度：{doc.metadata['score']}\n\n"""
for inum, doc in
enumerate(resp["source_documents"])]
logger.info("\n\n" + "\n\n".join(source_text))
print("\n\n" + "\n\n".join(source_text))

2
loader/image_loader.py
View File

@ -30,7 +30,7 @@ class UnstructuredPaddleImageLoader(UnstructuredFileLoader):
if __name__ == "__main__":
filepath = "../content/samples/test.jpg"
filepath = os.path.join(os.path.dirname(os.path.dirname(__file__)), "content", "samples", "test.jpg")
loader = UnstructuredPaddleImageLoader(filepath, mode="elements")
docs = loader.load()
for doc in docs:

2
loader/pdf_loader.py
View File

@ -46,7 +46,7 @@ class UnstructuredPaddlePDFLoader(UnstructuredFileLoader):
if __name__ == "__main__":
filepath = "../content/samples/test.pdf"
filepath = os.path.join(os.path.dirname(os.path.dirname(__file__)), "content", "samples", "test.pdf")
loader = UnstructuredPaddlePDFLoader(filepath, mode="elements")
docs = loader.load()
for doc in docs: