Skip to content

fix: remove invalid dummy path from gov_rag base_path and move to config #390

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ARYANPATEL-BIT wants to merge 2 commits into
base: main
Choose a base branch
from
+12 −8
Open

fix: remove invalid dummy path from gov_rag base_path and move to config #390

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f870166
fix: remove invalid dummy path from gov_rag base_path and move to config
ARYANPATEL-BIT Apr 12, 2026
5d8577f
fix(review): address PR feedback regarding RAG concurrency and config…
ARYANPATEL-BIT Apr 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions examples/government_rag/singletask_learning_bench/testalgorithms/basemodel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,7 +157,7 @@ def get_access_token():
def preprocess(self, **kwargs):
print("BaseModel preprocess")
# input('stop here preprocess')
self.rag = GovernmentRAG(model_name="/home/icyfeather/models/bge-m3", device="cuda", persist_directory="./chroma_db")
self.rag = GovernmentRAG(base_path=Context.get_parameters("base_path"), model_name=Context.get_parameters("model_name", "BAAI/bge-large-zh-v1.5"), device="cuda", persist_directory="./chroma_db")
LOGGER.info("RAG initialized")

def train(self, train_data, valid_data=None, **kwargs):
Expand All @@ -174,16 +174,18 @@ def process_query(self, query: str, ground_truth: str, location: str, rag_type:
response = self.get_model_response(query)
else:
with self.gpu_lock:
base_path = Context.get_parameters("base_path")
model_name = Context.get_parameters("model_name", "BAAI/bge-large-zh-v1.5")

if rag_type == "[global]":
if self.rag is None:
self.rag = GovernmentRAG(model_name="/home/icyfeather/models/bge-m3", device="cuda", persist_directory="./chroma_db")
rag = GovernmentRAG(base_path=base_path, model_name=model_name, device="cuda", persist_directory="./chroma_db")
elif rag_type == "[local]":
self.rag = GovernmentRAG(model_name="/home/icyfeather/models/bge-m3", device="cuda", persist_directory="./chroma_db", provinces=[location])
rag = GovernmentRAG(base_path=base_path, model_name=model_name, device="cuda", persist_directory="./chroma_db", provinces=[location])
else: # [other]
all_locations = set(self.all_locations)
self.rag = GovernmentRAG(model_name="/home/icyfeather/models/bge-m3", device="cuda", persist_directory="./chroma_db", provinces=list(all_locations - set([location])))
all_locations = set(getattr(self, "all_locations", []))
rag = GovernmentRAG(base_path=base_path, model_name=model_name, device="cuda", persist_directory="./chroma_db", provinces=list(all_locations - set([location])))

relevant_docs = self.rag.query(query, k=1)
relevant_docs = rag.query(query, k=1)

# Clear GPU cache after query
if torch.cuda.is_available():
Expand Down
4 changes: 3 additions & 1 deletion examples/government_rag/singletask_learning_bench/testalgorithms/gov_rag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
class GovernmentRAG:
def __init__(
self,
base_path: str = "/path/ianvs/dataset/gov_rag",
base_path: Optional[str] = None,
provinces: Optional[Union[str, List[str]]] = None,
model_name: str = "BAAI/bge-large-zh-v1.5",
device: str = "cuda" if torch.cuda.is_available() else "cpu",
Expand All @@ -29,6 +29,8 @@ def __init__(
device: Device to run the model on
persist_directory: Directory to persist the vector database
"""
if base_path is None:
raise ValueError("base_path must be explicitly provided")
self.base_path = base_path
self.provinces = self._validate_provinces(provinces)
self.persist_directory = persist_directory
Expand Down