ivanwu/jarvis-models
1
0
Fork 0
mirror of https://github.com/BoardWare-Genius/jarvis-models.git synced 2025-12-13 16:53:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: modify rerank model name

Browse Source
This commit is contained in:
chenyunda218
2024-10-15 15:40:27 +08:00
parent b17fcf0feb
commit 31e9e56ab3
1 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/blackbox/chroma_query.py
View File

@ -22,11 +22,12 @@ class ChromaQuery(Blackbox):
def __init__(self, *args, **kwargs) -> None: def __init__(self, *args, **kwargs) -> None:
# config = read_yaml(args[0]) # config = read_yaml(args[0])
# load chromadb and embedding model # load chromadb and embedding model
self.embedding_model_1 = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="/home/gpu/Workspace/Models/BAAI/bge-large-zh-v1.5", device = "cuda:0") self.embedding_model_1 = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="/home/administrator/Workspace/Models/BAAI/bge-large-zh-v1.5", device = "cuda:0")
self.embedding_model_2 = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="/home/gpu/Workspace/Models/BAAI/bge-small-en-v1.5", device = "cuda:0") self.embedding_model_2 = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="/home/administrator/Workspace/Models/BAAI/bge-small-en-v1.5", device = "cuda:0")
self.client_1 = chromadb.HttpClient(host='10.6.81.119', port=7000) self.embedding_model_3 = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="/home/administrator/Workspace/Models/BAAI/bge-m3", device = "cuda:0")
self.client_1 = chromadb.HttpClient(host='172.16.4.7', port=7000)
# self.client_2 = chromadb.HttpClient(host='10.6.82.192', port=8000) # self.client_2 = chromadb.HttpClient(host='10.6.82.192', port=8000)
self.reranker_model_1 = CrossEncoder("/home/gpu/Workspace/Models/BAAI/bge-reranker-v2-m3", max_length=512, device = "cuda") self.reranker_model_1 = CrossEncoder("/home/administrator/Workspace/Models/BAAI/bge-reranker-v2-m3", max_length=512, device = "cuda")
def __call__(self, *args, **kwargs): def __call__(self, *args, **kwargs):
return self.processing(*args, **kwargs) return self.processing(*args, **kwargs)
@ -56,10 +57,10 @@ class ChromaQuery(Blackbox):
return JSONResponse(content={"error": "question is required"}, status_code=status.HTTP_400_BAD_REQUEST) return JSONResponse(content={"error": "question is required"}, status_code=status.HTTP_400_BAD_REQUEST)
if chroma_embedding_model is None or chroma_embedding_model.isspace() or chroma_embedding_model == "": if chroma_embedding_model is None or chroma_embedding_model.isspace() or chroma_embedding_model == "":
chroma_embedding_model = "/home/gpu/Workspace/Models/BAAI/bge-large-zh-v1.5" chroma_embedding_model = "/home/administrator/Workspace/Models/BAAI/bge-large-zh-v1.5"
if chroma_host is None or chroma_host.isspace() or chroma_host == "": if chroma_host is None or chroma_host.isspace() or chroma_host == "":
chroma_host = "10.6.81.119" chroma_host = "172.16.4.7"
if chroma_port is None or chroma_port.isspace() or chroma_port == "": if chroma_port is None or chroma_port.isspace() or chroma_port == "":
chroma_port = "7000" chroma_port = "7000"
@ -71,7 +72,7 @@ class ChromaQuery(Blackbox):
chroma_n_results = 10 chroma_n_results = 10
# load client and embedding model from init # load client and embedding model from init
if re.search(r"10.6.81.119", chroma_host) and re.search(r"7000", chroma_port): if re.search(r"172.16.4.7", chroma_host) and re.search(r"7000", chroma_port):
client = self.client_1 client = self.client_1
else: else:
try: try:
@ -79,10 +80,12 @@ class ChromaQuery(Blackbox):
except: except:
return JSONResponse(content={"error": "chroma client not found"}, status_code=status.HTTP_400_BAD_REQUEST) return JSONResponse(content={"error": "chroma client not found"}, status_code=status.HTTP_400_BAD_REQUEST)
if re.search(r"/home/gpu/Workspace/Models/BAAI/bge-large-zh-v1.5", chroma_embedding_model): if re.search(r"/home/administrator/Workspace/Models/BAAI/bge-large-zh-v1.5", chroma_embedding_model):
embedding_model = self.embedding_model_1 embedding_model = self.embedding_model_1
elif re.search(r"/home/gpu/Workspace/Models/BAAI/bge-small-en-v1.5", chroma_embedding_model): elif re.search(r"/home/administrator/Workspace/Models/BAAI/bge-small-en-v1.5", chroma_embedding_model):
embedding_model = self.embedding_model_2 embedding_model = self.embedding_model_2
elif re.search(r"/home/administrator/Workspace/Models/BAAI/bge-m3", chroma_embedding_model):
embedding_model = self.embedding_model_3
else: else:
try: try:
embedding_model = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=chroma_embedding_model, device = "cuda:0") embedding_model = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=chroma_embedding_model, device = "cuda:0")
@ -120,8 +123,8 @@ class ChromaQuery(Blackbox):
final_result = str(results["documents"]) final_result = str(results["documents"])
if chroma_reranker_model: if chroma_reranker_model:
if re.search(r"/home/gpu/Workspace/Models/BAAI/bge-reranker-v2-m3", chroma_embedding_model): if re.search(r"/home/administrator/Workspace/Models/BAAI/bge-reranker-v2-m3", chroma_reranker_model):
reranker_model = self.chroma_reranker_model_1 reranker_model = self.reranker_model_1
else: else:
try: try:
reranker_model = CrossEncoder(chroma_reranker_model, max_length=512, device = "cuda") reranker_model = CrossEncoder(chroma_reranker_model, max_length=512, device = "cuda")