visual-rag-toolkit 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

visual_rag/retrieval/multi_vector.py

@@ -2,6 +2,25 @@ import os
 from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse
 
+import numpy as np
+import torch
+
+try:
+    from dotenv import load_dotenv
+
+    DOTENV_AVAILABLE = True
+except ImportError:
+    DOTENV_AVAILABLE = False
+    load_dotenv = None
+
+try:
+    from qdrant_client import QdrantClient
+
+    QDRANT_AVAILABLE = True
+except ImportError:
+    QDRANT_AVAILABLE = False
+    QdrantClient = None
+
 from visual_rag.embedding.visual_embedder import VisualEmbedder
 from visual_rag.retrieval.single_stage import SingleStageRetriever
 from visual_rag.retrieval.three_stage import ThreeStageRetriever
@@ -11,9 +30,7 @@ from visual_rag.retrieval.two_stage import TwoStageRetriever
 class MultiVectorRetriever:
     @staticmethod
     def _maybe_load_dotenv() -> None:
-        try:
-            from dotenv import load_dotenv
-        except ImportError:
+        if not DOTENV_AVAILABLE:
             return
         if os.path.exists(".env"):
             load_dotenv(".env")
@@ -33,87 +50,83 @@ class MultiVectorRetriever:
     ):
         if qdrant_client is None:
             self._maybe_load_dotenv()
-            try:
-                from qdrant_client import QdrantClient
-            except ImportError as e:
+            if not QDRANT_AVAILABLE:
                 raise ImportError(
                     "Qdrant client not installed. Install with: pip install visual-rag-toolkit[qdrant]"
-                ) from e
+                )
 
             qdrant_url = (
-                qdrant_url
-                or os.getenv("SIGIR_QDRANT_URL")
-                or os.getenv("DEST_QDRANT_URL")
-                or os.getenv("QDRANT_URL")
+                qdrant_url or os.getenv("QDRANT_URL") or os.getenv("SIGIR_QDRANT_URL")  # legacy
             )
             if not qdrant_url:
-                raise ValueError(
-                    "QDRANT_URL is required (pass qdrant_url or set env var). "
-                    "You can also set DEST_QDRANT_URL to override."
-                )
+                raise ValueError("QDRANT_URL is required (pass qdrant_url or set env var).")
 
             qdrant_api_key = (
                 qdrant_api_key
-                or os.getenv("SIGIR_QDRANT_KEY")
-                or os.getenv("SIGIR_QDRANT_API_KEY")
-                or os.getenv("DEST_QDRANT_API_KEY")
                 or os.getenv("QDRANT_API_KEY")
+                or os.getenv("SIGIR_QDRANT_KEY")  # legacy
             )
 
             grpc_port = None
             if prefer_grpc:
                 try:
-                    if urlparse(qdrant_url).port == 6333:
+                    parsed = urlparse(qdrant_url)
+                    port = parsed.port
+                    if port == 6333:
                         grpc_port = 6334
                 except Exception:
-                    grpc_port = None
+                    pass
 
             def _make_client(use_grpc: bool):
                 return QdrantClient(
                     url=qdrant_url,
                     api_key=qdrant_api_key,
+                    timeout=request_timeout,
                     prefer_grpc=bool(use_grpc),
                     grpc_port=grpc_port,
-                    timeout=int(request_timeout),
                     check_compatibility=False,
                 )
 
-            qdrant_client = _make_client(prefer_grpc)
+            client = _make_client(prefer_grpc)
             if prefer_grpc:
                 try:
-                    _ = qdrant_client.get_collections()
+                    _ = client.get_collections()
                 except Exception as e:
                     msg = str(e)
                     if (
                         "StatusCode.PERMISSION_DENIED" in msg
                         or "http2 header with status: 403" in msg
                     ):
-                        qdrant_client = _make_client(False)
+                        client = _make_client(False)
                     else:
                         raise
+            qdrant_client = client
 
         self.client = qdrant_client
         self.collection_name = collection_name
+
         self.embedder = embedder or VisualEmbedder(model_name=model_name)
 
         self._two_stage = TwoStageRetriever(
-            self.client,
-            collection_name=self.collection_name,
-            request_timeout=int(request_timeout),
-            max_retries=int(max_retries),
-            retry_sleep=float(retry_sleep),
+            qdrant_client=qdrant_client,
+            collection_name=collection_name,
+            request_timeout=request_timeout,
+            max_retries=max_retries,
+            retry_sleep=retry_sleep,
         )
         self._three_stage = ThreeStageRetriever(
-            self.client,
-            collection_name=self.collection_name,
-            request_timeout=int(request_timeout),
-            max_retries=int(max_retries),
-            retry_sleep=float(retry_sleep),
+            qdrant_client=qdrant_client,
+            collection_name=collection_name,
+            request_timeout=request_timeout,
+            max_retries=max_retries,
+            retry_sleep=retry_sleep,
         )
         self._single_stage = SingleStageRetriever(
-            self.client,
-            collection_name=self.collection_name,
-            request_timeout=int(request_timeout),
+            qdrant_client=qdrant_client,
+            collection_name=collection_name,
+            request_timeout=request_timeout,
+            max_retries=max_retries,
+            retry_sleep=retry_sleep,
         )
 
     def build_filter(
@@ -143,14 +156,10 @@ class MultiVectorRetriever:
         return_embeddings: bool = False,
     ) -> List[Dict[str, Any]]:
         q = self.embedder.embed_query(query)
-        try:
-            import torch
-        except ImportError:
-            torch = None
-        if torch is not None and isinstance(q, torch.Tensor):
+        if isinstance(q, torch.Tensor):
             query_embedding = q.detach().cpu().numpy()
         else:
-            query_embedding = q.numpy()
+            query_embedding = np.asarray(q)
 
         return self.search_embedded(
             query_embedding=query_embedding,
@@ -179,27 +188,17 @@ class MultiVectorRetriever:
             return self._single_stage.search(
                 query_embedding=query_embedding,
                 top_k=top_k,
-                strategy="multi_vector",
-                filter_obj=filter_obj,
-            )
-
-        if mode == "single_tiles":
-            return self._single_stage.search(
-                query_embedding=query_embedding,
-                top_k=top_k,
-                strategy="tiles_maxsim",
                 filter_obj=filter_obj,
+                using="initial",
             )
-
-        if mode == "single_global":
+        elif mode == "single_pooled":
             return self._single_stage.search(
                 query_embedding=query_embedding,
                 top_k=top_k,
-                strategy="pooled_global",
                 filter_obj=filter_obj,
+                using="mean_pooling",
             )
-
-        if mode == "two_stage":
+        elif mode == "two_stage":
             return self._two_stage.search_server_side(
                 query_embedding=query_embedding,
                 top_k=top_k,
@@ -207,16 +206,14 @@ class MultiVectorRetriever:
                 filter_obj=filter_obj,
                 stage1_mode=stage1_mode,
             )
-
-        if mode == "three_stage":
-            s1 = int(stage1_k) if stage1_k is not None else 1000
-            s2 = int(stage2_k) if stage2_k is not None else 300
+        elif mode == "three_stage":
             return self._three_stage.search_server_side(
                 query_embedding=query_embedding,
                 top_k=top_k,
-                stage1_k=s1,
-                stage2_k=s2,
+                stage1_k=stage1_k,
+                stage2_k=stage2_k,
                 filter_obj=filter_obj,
+                stage1_mode=stage1_mode,
             )
-
-        raise ValueError(f"Unknown mode: {mode}")
+        else:
+            raise ValueError(f"Unknown mode: {mode}")

visual_rag/retrieval/single_stage.py

@@ -30,6 +30,9 @@ class SingleStageRetriever:
     Args:
         qdrant_client: Connected Qdrant client
         collection_name: Name of the Qdrant collection
+        request_timeout: Timeout for Qdrant requests (seconds)
+        max_retries: Number of retry attempts on failure
+        retry_sleep: Sleep time between retries (seconds)
 
     Example:
         >>> retriever = SingleStageRetriever(client, "my_collection")
@@ -41,10 +44,14 @@ class SingleStageRetriever:
         qdrant_client,
         collection_name: str,
         request_timeout: int = 120,
+        max_retries: int = 3,
+        retry_sleep: float = 1.0,
     ):
         self.client = qdrant_client
         self.collection_name = collection_name
         self.request_timeout = int(request_timeout)
+        self.max_retries = max_retries
+        self.retry_sleep = retry_sleep
 
     def search(
         self,

visual_rag/retrieval/two_stage.py

@@ -17,10 +17,15 @@ Research Context:
 """
 
 import logging
+import time
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
 import torch
+from qdrant_client.http import models as qdrant_models
+from qdrant_client.models import FieldCondition, Filter, MatchAny, MatchValue
+
+from visual_rag.embedding.pooling import compute_maxsim_score
 
 logger = logging.getLogger(__name__)
 
@@ -82,8 +87,6 @@ class TwoStageRetriever:
         self.retry_sleep = float(retry_sleep)
 
     def _retry_call(self, fn):
-        import time
-
         last_err = None
         for attempt in range(self.max_retries):
             try:
@@ -120,8 +123,6 @@ class TwoStageRetriever:
         Returns:
             List of results with scores
         """
-        from qdrant_client.http import models
-
         query_np = self._to_numpy(query_embedding)
 
         if prefetch_k is None:
@@ -155,9 +156,9 @@ class TwoStageRetriever:
                 limit=top_k,
                 query_filter=filter_obj,
                 with_payload=True,
-                search_params=models.SearchParams(exact=True),
+                search_params=qdrant_models.SearchParams(exact=True),
                 prefetch=[
-                    models.Prefetch(
+                    qdrant_models.Prefetch(
                         query=prefetch_query,
                         using=prefetch_using,
                         limit=prefetch_k,
@@ -363,8 +364,6 @@ class TwoStageRetriever:
         return_embeddings: bool = False,
     ) -> List[Dict[str, Any]]:
         """Stage 2: Rerank with full multi-vector MaxSim scoring."""
-        from visual_rag.embedding.pooling import compute_maxsim_score
-
         # Fetch full embeddings for candidates
         candidate_ids = [c["id"] for c in candidates]
 
@@ -435,8 +434,6 @@ class TwoStageRetriever:
 
         Supports single values or lists (using MatchAny).
         """
-        from qdrant_client.models import FieldCondition, Filter, MatchAny, MatchValue
-
         conditions = []
 
         if year is not None:

{visual_rag_toolkit-0.1.2.dist-info → visual_rag_toolkit-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: visual-rag-toolkit
-Version: 0.1.2
+Version: 0.1.4
 Summary: End-to-end visual document retrieval with ColPali, featuring two-stage pooling for scalable search
 Project-URL: Homepage, https://github.com/Ara-Yeroyan/visual-rag-toolkit
 Project-URL: Documentation, https://github.com/Ara-Yeroyan/visual-rag-toolkit#readme
@@ -88,14 +88,12 @@ Description-Content-Type: text/markdown
 [![PyPI](https://img.shields.io/pypi/v/visual-rag-toolkit)](https://pypi.org/project/visual-rag-toolkit/)
 [![Python](https://img.shields.io/pypi/pyversions/visual-rag-toolkit)](https://pypi.org/project/visual-rag-toolkit/)
 [![License](https://img.shields.io/pypi/l/visual-rag-toolkit)](LICENSE)
-[![CI](https://img.shields.io/github/actions/workflow/status/Ara-Yeroyan/visual-rag-toolkit/ci.yaml?branch=main)](https://github.com/Ara-Yeroyan/visual-rag-toolkit/actions/workflows/ci.yaml)
-
-Note:
-- The **PyPI badge** shows “not found” until the first release is published.
-- The **CI badge** requires the GitHub repo to be **public** (GitHub does not serve Actions badges for private repos).
+[![Demo](https://img.shields.io/badge/Demo-Hugging%20Face-yellow)](https://huggingface.co/spaces/Yeroyan/visual-rag-toolkit)
 
 End-to-end visual document retrieval toolkit featuring **fast multi-stage retrieval** (prefetch with pooled vectors + exact MaxSim reranking).
 
+**[Try the Live Demo](https://huggingface.co/spaces/Yeroyan/visual-rag-toolkit)** - Upload PDFs, index to Qdrant, and query with visual retrieval.
+
 This repo contains:
 - a **Python package** (`visual_rag`)
 - a **Streamlit demo app** (`demo/`)
@@ -162,7 +160,7 @@ for r in results[:3]:
 
 ### End-to-end: ingest PDFs (with cropping) → index in Qdrant
 
-This is the “SDK-style” pipeline: PDF → images → optional crop → embed → store vectors + payload in Qdrant.
+This is the "SDK-style" pipeline: PDF → images → optional crop → embed → store vectors + payload in Qdrant.
 
 ```python
 import os
@@ -174,8 +172,8 @@ import torch
 from visual_rag import VisualEmbedder
 from visual_rag.indexing import ProcessingPipeline, QdrantIndexer
 
-QDRANT_URL = os.environ["SIGIR_QDRANT_URL"]  # or QDRANT_URL
-QDRANT_KEY = os.getenv("SIGIR_QDRANT_KEY", "")  # or QDRANT_API_KEY
+QDRANT_URL = os.environ["QDRANT_URL"]
+QDRANT_KEY = os.getenv("QDRANT_API_KEY", "")
 
 collection = "my_visual_docs"
 
@@ -193,6 +191,8 @@ indexer = QdrantIndexer(
     prefer_grpc=True,
     vector_datatype="float16",
 )
+
+# Creates collection + required payload indexes (e.g., "filename" for skip_existing)
 indexer.create_collection(force_recreate=False)
 
 pipeline = ProcessingPipeline(
@@ -208,19 +208,32 @@ pipeline = ProcessingPipeline(
 
 pdfs = [Path("docs/a.pdf"), Path("docs/b.pdf")]
 for pdf_path in pdfs:
-    pipeline.process_pdf(
+    result = pipeline.process_pdf(
         pdf_path,
-        skip_existing=True,
+        skip_existing=True,  # Skip pages already in Qdrant (uses filename index)
         upload_to_cloudinary=False,
         upload_to_qdrant=True,
     )
+    # Logs automatically shown:
+    # [10:23:45] 📚 Processing PDF: a.pdf
+    # [10:23:45] 🖼️ Converting PDF to images...
+    # [10:23:46]    ✅ Converted 12 pages
+    # [10:23:46] 📦 Processing pages 1-8/12
+    # [10:23:46] 🤖 Generating embeddings for 8 pages...
+    # [10:23:48] 📤 Uploading batch of 8 pages...
+    # [10:23:48]    ✅ Uploaded 8 points to Qdrant
+    # [10:23:48] 📦 Processing pages 9-12/12
+    # [10:23:48] 🤖 Generating embeddings for 4 pages...
+    # [10:23:50] 📤 Uploading batch of 4 pages...
+    # [10:23:50]    ✅ Uploaded 4 points to Qdrant
+    # [10:23:50] ✅ Completed a.pdf: 12 uploaded, 0 skipped, 0 failed
 ```
 
 CLI equivalent:
 
 ```bash
-export SIGIR_QDRANT_URL="https://YOUR_QDRANT"
-export SIGIR_QDRANT_KEY="YOUR_KEY"
+export QDRANT_URL="https://YOUR_QDRANT"
+export QDRANT_API_KEY="YOUR_KEY"
 
 visual-rag process \
   --reports-dir ./docs \
@@ -263,7 +276,7 @@ Stage 2: Exact MaxSim reranking on candidates
          └── Return top-k results (e.g., 10)
 ```
 
-Three-stage extends this with an additional “cheap prefetch” stage before stage 2.
+Three-stage extends this with an additional "cheap prefetch" stage before stage 2.
 
 ## 📁 Package Structure
 
@@ -358,7 +371,7 @@ If you use this toolkit in your research, please cite:
 
 ```bibtex
 @software{visual_rag_toolkit,
-  title = {Visual RAG Toolkit: Scalable Visual Document Retrieval with Two-Stage Pooling},
+  title = {Visual RAG Toolkit: Scalable Visual Document Retrieval with 1D Convolutional Pooling},
   author = {Ara Yeroyan},
   year = {2026},
   url = {https://github.com/Ara-Yeroyan/visual-rag-toolkit}
@@ -374,4 +387,3 @@ MIT License - see [LICENSE](LICENSE) for details.
 - [Qdrant](https://qdrant.tech/) - Vector database with multi-vector support
 - [ColPali](https://github.com/illuin-tech/colpali) - Visual document retrieval models
 - [ViDoRe](https://huggingface.co/spaces/vidore/vidore-leaderboard) - Benchmark dataset
-

{visual_rag_toolkit-0.1.2.dist-info → visual_rag_toolkit-0.1.4.dist-info}/RECORD

@@ -11,48 +11,47 @@ benchmarks/vidore_tatdqa_test/dataset_loader.py,sha256=gCCneGAKWQm0WlJHLvGjoMrAb
 benchmarks/vidore_tatdqa_test/metrics.py,sha256=cLdYbRt5VcxInO1cN79ve6ZLP3kaSxRkdzRX3IbPPMs,1112
 benchmarks/vidore_tatdqa_test/run_qdrant.py,sha256=_PikeqIYpWPim-KEQOwvT-aqwYoAWASjqJVisi8PfQg,28681
 benchmarks/vidore_tatdqa_test/sweep_eval.py,sha256=d_kbyNTJ1LoFfIVnsZyiRO1nKyMqmRB5jEweZL6kYd4,12688
-demo/__init__.py,sha256=jVzjsVKZl5ZZuFxawA8Pxj3yuIKL7llkao3rBpde-aQ,204
-demo/app.py,sha256=1GZJ_JhVWvqoBewngc8tHeiuM1fNbxddEO6ZsEdwBfg,1029
+demo/__init__.py,sha256=QtvjqZ94WpbJ915Xik5ZzYFDtK7APmsQK6m0-Sxe8uw,204
+demo/app.py,sha256=nZbCz1mpRK-GZTgOHyz4m4AfgKFgsH-09JwXeL3d3ng,1405
 demo/commands.py,sha256=qxRE2x610yZvcjwEfSKiR9CyFonX-vRxFqQNJCUKfyA,13690
 demo/config.py,sha256=BNkV4NSEEMIV9e6Z-cxds2v247uVmTPCgL-M5ItPzMg,757
 demo/download_models.py,sha256=J10qQt2TpEshVOxvCX_ZSbV7YozIBqDATZnt8fUKFHs,2868
-demo/evaluation.py,sha256=wiVxzRu3UZ5wAwHlpSKQ6srZjnSR06dgQw3G0OOV2Eg,28954
-demo/example_metadata_mapping_sigir.json,sha256=UCgqZtr6Wnq_vS7zxPxpvuokk9gxOVgKydC7f1lauw8,824
-demo/indexing.py,sha256=u80FSQo5ahHfry7fQNWa3kvKDngURRkLhaze3zWro1o,14077
-demo/qdrant_utils.py,sha256=VWEC7BwhMjjB7iIS5iaVDMGt_CMh9mQG4F94k1Pt0yA,7677
+demo/evaluation.py,sha256=4ixJGg50KAVNiZ_mr5FMVv-QKCrZRooJ80LbrjKXM1s,27467
+demo/indexing.py,sha256=qUVEB3QrIolS53Ggxurccbh-QyeLLbzcY5TLyVBVKME,10620
+demo/qdrant_utils.py,sha256=Xh-thLIrACrYkFCrqazYNH0p3vS8_yMCaTbvt4HAy98,7778
 demo/results.py,sha256=dprvxnyHwxJvkAQuh4deaCsiEG1wm0n9svPyxI37vJg,1050
 demo/test_qdrant_connection.py,sha256=hkbyl3zGsw_GdBBp5MkW_3SBKTHXbwH3Sr_pUE54_po,3866
 demo/ui/__init__.py,sha256=EyBCvnXYfPbdyxJzyp9TjQBeJJUgmOY1yRHkUeC6JFQ,412
 demo/ui/benchmark.py,sha256=HiGCN4HrqeOC7L6t2kuzIiyWdcVE_cP2JTxoewrmPSo,14218
 demo/ui/header.py,sha256=J2hXr_nNyg1H9rmrd-EGx3WUl7lYo-Ca30ptgzBCfBs,806
-demo/ui/playground.py,sha256=Z3OgCWOzzTld1I3eN1IcTadaSzsqDQf7MiHwTbxbvJA,13692
-demo/ui/sidebar.py,sha256=muVCnvoeMOm1rHx7UPt68yLXlG3OERdXvJ3QqIXAUoc,7839
-demo/ui/upload.py,sha256=BHJmbIQOAYdMF_svxlRSYIe163Y5UX5P_gilJ09YHSA,20372
-visual_rag/__init__.py,sha256=UkGFXjPmjbO6Iad8ty1uJOMQsVMpV_s63ihchHltLx8,2555
-visual_rag/config.py,sha256=pd48M3j3n8ZV1HhaabMmP_uoEJnqhBC-Bma9vuvc8V4,7368
-visual_rag/demo_runner.py,sha256=wi0Wz3gZ39l4aovMd6zURq_CKUSgma4kGjF6hpQHwGY,2793
+demo/ui/playground.py,sha256=yRlWWzJgsc596vALn5f0PHhmhtJCMmfv61nYakW75GQ,13672
+demo/ui/sidebar.py,sha256=k7CZ5V7SxwbPOL9nQTWUct5y9mPY-YnLIeBgha7aIEE,8379
+demo/ui/upload.py,sha256=NVmd1-xRj_dfgq14x_eqcN6MjDAZ3hbPBD0YRUz8OOY,20508
+visual_rag/__init__.py,sha256=O8I4wQdQcQxAs7_SIPxnAzUOmRv5I9ezau8sZx9yqXQ,4384
+visual_rag/config.py,sha256=qqSQk2lM5MiRji-6xQNGS2gSiXA4NgyJnCbgGx7uGJQ,7395
+visual_rag/demo_runner.py,sha256=ahIKYhHQSLOF_kWbj0u_29SLX4qTdyxb3Smt_cMMfzI,2763
 visual_rag/qdrant_admin.py,sha256=NNczko2S5-K3qATNUxgYn51hNWgWb6boheL7vlCQGpM,7055
 visual_rag/cli/__init__.py,sha256=WgBRXm0VACfLltvVlLcSs3FTM1uQ7Uuw3CVD4-zWZwc,46
 visual_rag/cli/main.py,sha256=QmpnQ0lbC6Q9lwxaSCDh6paEEzI78IPY1jwc3_9y7VI,21083
 visual_rag/embedding/__init__.py,sha256=7QIENmxwRnwnUzsYKRY3VQTyF3HJkRiL1D7Au9XHF0w,682
 visual_rag/embedding/pooling.py,sha256=x8uY4VHbxEnsJRM2JeOkzPHDiwOkbi5NK4XW21U1hAc,11401
 visual_rag/embedding/visual_embedder.py,sha256=he9JpVHmo_szOiXCwtJdrCseGmf2y5Gi0UEFjwazzVY,23198
-visual_rag/indexing/__init__.py,sha256=pMLuinCIERbwWechn176nMrtlmTp0ySfuj8gdkNvRks,679
+visual_rag/indexing/__init__.py,sha256=rloBEBt3x8BQut1Tj1n8fuaQ3iXMS3pm64o8n-NlSAw,985
 visual_rag/indexing/cloudinary_uploader.py,sha256=e-G5du4D7z6mWWl2lahMidG-Wdc-baImFFILTojebpA,8826
 visual_rag/indexing/pdf_processor.py,sha256=V3RAKpwgIFicqUaXzaaljePxh_oP4UV5W0aiJyfv0BY,10247
 visual_rag/indexing/pipeline.py,sha256=1ScpVRlLCq2FWi3IPvlQcIfDCQQ2F64IlRd9ZZHiTaA,25037
-visual_rag/indexing/qdrant_indexer.py,sha256=uUOA-6Qkd_vEeP1LdgGyoh1FHu1ZNEyYKuNxJAqetBU,17121
+visual_rag/indexing/qdrant_indexer.py,sha256=E9uDwOL3A1nFJhFhJcI8V3JR8FL7nDahEYiv886oG1s,19526
 visual_rag/preprocessing/__init__.py,sha256=rCzfBO0jaVKp6MpPRRused_4gasHfobAbG-139Y806E,121
 visual_rag/preprocessing/crop_empty.py,sha256=iHXITFkRlF40VPJ4k9d432RUAi_89BhAEvK4wOEn96Q,5211
 visual_rag/retrieval/__init__.py,sha256=J9pnbeB83Fqs9n4g3GcIp1VR9dnuyAlcsIDVsf0lSb8,601
-visual_rag/retrieval/multi_vector.py,sha256=m5PKjkj0TFeWNccKNmCqghTM5b9ARr43Lq3sRhOxnjw,7381
-visual_rag/retrieval/single_stage.py,sha256=TSndnh4Kz9aT_0kKhNyLEvokbDLkgq--lXuyldzP5sU,4105
+visual_rag/retrieval/multi_vector.py,sha256=KyJg1VAxODr5rY80vXmsjSD9ueRpay4QGCJizPKiiBw,7008
+visual_rag/retrieval/single_stage.py,sha256=Ba06V-KRSFSZm0xzbjFR3EBEWaQkDo7U_pWNx25W8H0,4425
 visual_rag/retrieval/three_stage.py,sha256=YC0CVEohxTT5zhilcQHI7nYAk08E5jC3zkQ3-rNdLMw,5951
-visual_rag/retrieval/two_stage.py,sha256=_RnEgIx_qY4yu2iIk0a3w47D7WiKHlmBivm5gLEpyI4,16779
+visual_rag/retrieval/two_stage.py,sha256=eUbyvdf0-3f0qIiAdU6Wmlos5hGrGNyXjuvc2-Be41M,16775
 visual_rag/visualization/__init__.py,sha256=SITKNvBEseDp7F3K6UzLPA-6OQFqYfY5azS5nlDdihQ,447
 visual_rag/visualization/saliency.py,sha256=F3Plc18Sf3tzWcyncuaruTmENm1IfW5j9NFGEQR93cY,11248
-visual_rag_toolkit-0.1.2.dist-info/METADATA,sha256=LrZ-EUezUsmUJpnNofm5TTM5IJIUerznFDcBSucI7rc,12830
-visual_rag_toolkit-0.1.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-visual_rag_toolkit-0.1.2.dist-info/entry_points.txt,sha256=6Tob1GPg_ILGELjYTPsAnNMZ1W0NS939nfI7xyW2DIY,102
-visual_rag_toolkit-0.1.2.dist-info/licenses/LICENSE,sha256=hEg_weKnHXJakQRR3sw2ygcZ101zCI00zMhBOPb3yfA,1069
-visual_rag_toolkit-0.1.2.dist-info/RECORD,,
+visual_rag_toolkit-0.1.4.dist-info/METADATA,sha256=2nnhqsq3P_OG8GRk48sz569VB1I-aaKcOjKXYl-OvJo,13460
+visual_rag_toolkit-0.1.4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+visual_rag_toolkit-0.1.4.dist-info/entry_points.txt,sha256=6Tob1GPg_ILGELjYTPsAnNMZ1W0NS939nfI7xyW2DIY,102
+visual_rag_toolkit-0.1.4.dist-info/licenses/LICENSE,sha256=hEg_weKnHXJakQRR3sw2ygcZ101zCI00zMhBOPb3yfA,1069
+visual_rag_toolkit-0.1.4.dist-info/RECORD,,

demo/example_metadata_mapping_sigir.json

@@ -1,37 +0,0 @@
-{
-  "filenames": {
-    "sigir2025-llms": {
-      "year": 2025,
-      "source": "Conference Paper",
-      "district": null,
-      "doc_type": "paper",
-      "project": "sigir-demo",
-      "tags": ["llms", "retrieval"]
-    },
-    "sigir2025-ginger": {
-      "year": 2025,
-      "source": "Conference Paper",
-      "district": null,
-      "doc_type": "paper",
-      "project": "sigir-demo",
-      "tags": ["ginger", "case-study"]
-    },
-    "2505.15859v1": {
-      "year": 2025,
-      "source": "arXiv",
-      "district": null,
-      "doc_type": "preprint",
-      "project": "sigir-demo",
-      "tags": ["arxiv", "ranking"]
-    },
-    "2507.04942v2": {
-      "year": 2025,
-      "source": "arXiv",
-      "district": null,
-      "doc_type": "preprint",
-      "project": "sigir-demo",
-      "tags": ["arxiv", "rag"]
-    }
-  }
-}
-