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

temporarily save faiss_cache

This commit is contained in:
hzg0601 2023-12-06 09:45:56 +00:00
parent 67b7c99d03
commit 1fac51fe35
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
requirements.txt
View File

@ -18,7 +18,7 @@ starlette~=0.27.0
unstructured[all-docs]==0.11.0 unstructured[all-docs]==0.11.0
python-magic-bin; sys_platform == 'win32' python-magic-bin; sys_platform == 'win32'
SQLAlchemy==2.0.19 SQLAlchemy==2.0.19
faiss-cpu faiss-cpu # `conda install faiss-gpu -c conda-forge` if you want to accelerate with gpus
accelerate>=0.24.1 accelerate>=0.24.1
spacy>=3.7.2 spacy>=3.7.2
PyMuPDF PyMuPDF
@ -64,7 +64,7 @@ metaphor-python>=0.1.23
# WebUI requirements # WebUI requirements
streamlit>=1.29.0 streamlit>=1.29.0 # do remember to add streamlit to environment variables if you use windows
streamlit-option-menu>=0.3.6 streamlit-option-menu>=0.3.6
streamlit-antd-components>=0.2.3 streamlit-antd-components>=0.2.3
streamlit-chatbox>=1.1.11 streamlit-chatbox>=1.1.11

4
server/knowledge_base/kb_cache/faiss_cache.py
View File

@ -45,7 +45,7 @@ class _FaissPool(CachePool):
# create an empty vector store # create an empty vector store
embeddings = EmbeddingsFunAdapter(embed_model) embeddings = EmbeddingsFunAdapter(embed_model)
doc = Document(page_content="init", metadata={}) doc = Document(page_content="init", metadata={})
vector_store = FAISS.from_documents([doc], embeddings, normalize_L2=True) vector_store = FAISS.from_documents([doc], embeddings, normalize_L2=True,distance_strategy="METRIC_INNER_PRODUCT")
ids = list(vector_store.docstore._dict.keys()) ids = list(vector_store.docstore._dict.keys())
vector_store.delete(ids) vector_store.delete(ids)
return vector_store return vector_store
@ -82,7 +82,7 @@ class KBFaissPool(_FaissPool):
if os.path.isfile(os.path.join(vs_path, "index.faiss")): if os.path.isfile(os.path.join(vs_path, "index.faiss")):
embeddings = self.load_kb_embeddings(kb_name=kb_name, embed_device=embed_device, default_embed_model=embed_model) embeddings = self.load_kb_embeddings(kb_name=kb_name, embed_device=embed_device, default_embed_model=embed_model)
vector_store = FAISS.load_local(vs_path, embeddings, normalize_L2=True) vector_store = FAISS.load_local(vs_path, embeddings, normalize_L2=True,distance_strategy="METRIC_INNER_PRODUCT")
elif create: elif create:
# create an empty vector store # create an empty vector store
if not os.path.exists(vs_path): if not os.path.exists(vs_path):