Update experiments: rename imports

experiments/edge_weight_ablation.py

@@ -27,7 +27,7 @@ _project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 sys.path.insert(0, _project_root)
 
 import types as _types
-for _pkg_path in ["src", "src.retrievers", "src.hipporag_pipeline"]:
+for _pkg_path in ["src", "src.retrievers", "src.passage_entity"]:
     if _pkg_path not in sys.modules:
         _m = _types.ModuleType(_pkg_path)
         _m.__path__ = [os.path.join(_project_root, *_pkg_path.split("."))]
@@ -46,14 +46,14 @@ _src = os.path.join(_project_root, "src")
 _load_mod("src.retrievers.base", os.path.join(_src, "retrievers", "base.py"))
 _load_mod("src.retrievers.flow_diffusion", os.path.join(_src, "retrievers", "flow_diffusion.py"))
 
-from src.hipporag_pipeline.config import HippoRAGConfig
-from src.hipporag_pipeline.embedding_store import EmbeddingModelWrapper
-from src.hipporag_pipeline.kg_builder import KGBuilder
-from src.hipporag_pipeline.openie import OpenIE
-from src.hipporag_pipeline.reranker import FactReranker
-from src.hipporag_pipeline.retriever import HippoRAGRetriever
-from src.hipporag_pipeline.graph_adapter import run_igraph_qafd
-from src.hipporag_pipeline.benchmark_runner import (
+from src.passage_entity.config import PassageEntityConfig
+from src.passage_entity.embedding_store import EmbeddingModelWrapper
+from src.passage_entity.kg_builder import KGBuilder
+from src.passage_entity.openie import OpenIE
+from src.passage_entity.reranker import FactReranker
+from src.passage_entity.retriever import PassageEntityRetriever
+from src.passage_entity.graph_adapter import run_igraph_qafd
+from src.passage_entity.benchmark_runner import (
     get_gold_docs, get_gold_answers, recall_at_k,
     exact_match, f1_score, run_qa, _openai_embed, _openai_complete,
 )
@@ -69,7 +69,7 @@ def load_everything(dataset="musique", num_queries=10):
     """Load KG, embeddings, data — once for all experiments."""
     api_key = os.environ.get("OPENAI_API_KEY", "")
 
-    config = HippoRAGConfig(
+    config = PassageEntityConfig(
         llm_model="gpt-4o-mini",
         embedding_model_key="openai-small",
         dataset=dataset,
@@ -110,7 +110,7 @@ def load_everything(dataset="musique", num_queries=10):
 
     # Build retriever
     reranker = FactReranker(llm_func)
-    retriever = HippoRAGRetriever(
+    retriever = PassageEntityRetriever(
         config=config,
         embedding_model=embedding_model,
         reranker=reranker,
@@ -126,7 +126,7 @@ def load_everything(dataset="musique", num_queries=10):
 
 
 def run_retrieval_with_params(
-    retriever: HippoRAGRetriever,
+    retriever: PassageEntityRetriever,
     queries: List[str],
     gold_docs: List[List[str]],
     gold_answers,
@@ -136,7 +136,7 @@ def run_retrieval_with_params(
     query_aware: bool = True,
 ) -> Dict:
     """Run retrieval with specific edge weight params. Returns metrics dict."""
-    from src.hipporag_pipeline.utils import compute_mdhash_id, min_max_normalize
+    from src.passage_entity.utils import compute_mdhash_id, min_max_normalize
 
     retriever._encode_queries(queries)
     k_list = [1, 2, 5, 10, 20, 50, 100, 200]

experiments/query_aware_ablation.py

@@ -28,7 +28,7 @@ _project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 sys.path.insert(0, _project_root)
 
 import types as _types
-for _pkg_path in ["src", "src.retrievers", "src.hipporag_pipeline"]:
+for _pkg_path in ["src", "src.retrievers", "src.passage_entity"]:
     if _pkg_path not in sys.modules:
         _m = _types.ModuleType(_pkg_path)
         _m.__path__ = [os.path.join(_project_root, *_pkg_path.split("."))]
@@ -47,18 +47,18 @@ _src = os.path.join(_project_root, "src")
 _load_mod("src.retrievers.base", os.path.join(_src, "retrievers", "base.py"))
 _load_mod("src.retrievers.flow_diffusion", os.path.join(_src, "retrievers", "flow_diffusion.py"))
 
-from src.hipporag_pipeline.config import HippoRAGConfig
-from src.hipporag_pipeline.embedding_store import EmbeddingModelWrapper
-from src.hipporag_pipeline.kg_builder import KGBuilder
-from src.hipporag_pipeline.openie import OpenIE
-from src.hipporag_pipeline.reranker import FactReranker
-from src.hipporag_pipeline.retriever import HippoRAGRetriever
-from src.hipporag_pipeline.graph_adapter import IGraphQAFD
-from src.hipporag_pipeline.benchmark_runner import (
+from src.passage_entity.config import PassageEntityConfig
+from src.passage_entity.embedding_store import EmbeddingModelWrapper
+from src.passage_entity.kg_builder import KGBuilder
+from src.passage_entity.openie import OpenIE
+from src.passage_entity.reranker import FactReranker
+from src.passage_entity.retriever import PassageEntityRetriever
+from src.passage_entity.graph_adapter import IGraphQAFD
+from src.passage_entity.benchmark_runner import (
     get_gold_docs, get_gold_answers, recall_at_k,
     exact_match, f1_score, run_qa, _openai_embed, _openai_complete,
 )
-from src.hipporag_pipeline.utils import compute_mdhash_id, min_max_normalize
+from src.passage_entity.utils import compute_mdhash_id, min_max_normalize
 
 logging.basicConfig(level=logging.WARNING)
 
@@ -69,7 +69,7 @@ logging.basicConfig(level=logging.WARNING)
 
 def load_dataset_and_kg(dataset="musique", num_queries=10):
     api_key = os.environ.get("OPENAI_API_KEY", "")
-    config = HippoRAGConfig(
+    config = PassageEntityConfig(
         llm_model="gpt-4o-mini",
         embedding_model_key="openai-small",
         dataset=dataset,
@@ -106,7 +106,7 @@ def load_dataset_and_kg(dataset="musique", num_queries=10):
     builder.index(docs)
 
     reranker = FactReranker(llm_func)
-    retriever = HippoRAGRetriever(
+    retriever = PassageEntityRetriever(
         config=config, embedding_model=embedding_model, reranker=reranker,
         graph=builder.graph,
         chunk_embedding_store=builder.chunk_embedding_store,
@@ -133,7 +133,7 @@ def load_dataset_and_kg(dataset="musique", num_queries=10):
 # ===========================================================================
 
 def run_qafd_detailed(
-    retriever: HippoRAGRetriever,
+    retriever: PassageEntityRetriever,
     query: str,
     gold_doc_set: set,
     alpha: float,

experiments/run_all_ablations.sh

@@ -4,7 +4,7 @@
 
 DATASET="musique"
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --dataset $DATASET --num_queries $N --embedding_model openai-small --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --dataset $DATASET --num_queries $N --embedding_model openai-small --skip_qa"
 
 echo "======================================================================"
 echo "  QAFD-RAG Query-Awareness Ablation (${DATASET}, ${N} queries)"

experiments/run_alpha_qa_sweep.sh

@@ -1,8 +1,8 @@
 #!/bin/bash
 # Alpha × QA sweep: find the sweet spot where decoupled QA edge weights help
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
 
 echo "======================================================================"
 echo "  Alpha x Query-Awareness Sweep (decoupled push, $N queries)"

experiments/run_batch_push_ablation.sh

@@ -1,9 +1,9 @@
 #!/bin/bash
 # Batch push ablation: does batch push make edge weights matter?
 # Compare: single vs batch, agnostic vs aware
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
 
 echo "======================================================================"
 echo "  Batch Push Ablation ($N queries per dataset)"

experiments/run_batch_push_nvidia.sh

@@ -1,9 +1,9 @@
 #!/bin/bash
 # Batch push sweep on nvidia KG (dense, 1.6M edges)
 # Goal: find config where QA-aware beats agnostic AND recall is high
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model nvidia-nv-embed-v2 --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model nvidia-nv-embed-v2 --skip_qa"
 LOG=experiments/results/batch_push_nvidia.log
 mkdir -p experiments/results
 exec > >(tee -a $LOG) 2>&1

experiments/run_decoupled_ablation.sh

@@ -1,9 +1,9 @@
 #!/bin/bash
 # Decoupled push ablation: does separating accumulation from routing
 # make query-aware edge weights effective?
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
 
 echo "======================================================================"
 echo "  Decoupled Push Ablation ($N queries per dataset)"

experiments/run_nvidia_qa_ablation.sh

@@ -1,9 +1,9 @@
 #!/bin/bash
 # Query-awareness ablation on nvidia-nv-embed-v2 KGs (dense, 1.6M edges)
 # Tests: QA-aware vs agnostic, different alpha/epsilon settings
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model nvidia-nv-embed-v2 --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model nvidia-nv-embed-v2 --skip_qa"
 
 echo "======================================================================"
 echo "  Query-Awareness on nvidia KG (dense graph, $N queries)"

experiments/run_overnight_qa_awareness.sh

@@ -2,8 +2,8 @@
 # Overnight query-awareness experiments
 # Tests decoupled push with alpha=3: QA-aware vs agnostic
 # Across tasks, graph types, and embedding models
-cd /home/davoud/QAFD-RAG
-LOG=/home/davoud/QAFD-RAG/experiments/results/overnight_qa_awareness.log
+cd "$(dirname "$0")/.."
+LOG=./experiments/results/overnight_qa_awareness.log
 mkdir -p experiments/results
 exec > >(tee -a $LOG) 2>&1
 echo "======================================================================"
@@ -11,7 +11,7 @@ echo "  Overnight Query-Awareness Experiments"
 echo "  Started: $(date)"
 echo "======================================================================"
 
-BASE_PE="python src/hipporag_pipeline/benchmark_runner.py"
+BASE_PE="python src/passage_entity/benchmark_runner.py"
 
 # =====================================================================
 # 1. PASSAGE-ENTITY: Multihop with OpenAI embedding (100q, alpha=3)

experiments/run_qa_awareness_v2.sh

@@ -1,8 +1,8 @@
 #!/bin/bash
 # Query-Awareness Ablation V2: warm walk, accumulation, more steps
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
 
 echo "======================================================================"
 echo "  Query-Awareness V2 Ablation ($N queries per dataset)"

experiments/run_sim_mode_ablation.sh

@@ -2,9 +2,9 @@
 # Edge weight ablation: similarity contrast functions across 3 datasets
 # Tests whether sharper similarity contrast makes query-aware edge weights effective
 
-cd /home/davoud/QAFD-RAG
+cd "$(dirname "$0")/.."
 N=100
-BASE="python src/hipporag_pipeline/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
+BASE="python src/passage_entity/benchmark_runner.py --task multihop --num_queries $N --embedding_model openai-small --skip_qa"
 
 echo "======================================================================"
 echo "  Similarity Mode Ablation ($N queries per dataset)"