feat: add support for 10 inputs

README.md

@@ -179,6 +179,8 @@ for file_path in sorted(p for p in documents_root.rglob("*") if p.is_file()):
 
 Already keeping your corpus in a bucket? `discover_documents()` and `extract_text()` name each document by
 its full S3 object key, so that is what `correct_answer_document_keys` must reference — prefix included.
+Discovery can span several locations in one bucket (`prefixes=["manuals/", "reports/"]`) and fails with a
+`BenchmarkKeyError` if a benchmark key matches none of the documents it found.
 
 
 ### Prepare `benchmark_data.json`

ai4rag/assets_generator/notebook_templates/maas_indexing_template.ipynb

@@ -206,7 +206,7 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "The data processing pipeline prepares documents for the RAG system in multiple steps. Each step produces outputs stored under `step_outputs/`. \n\n| Step | Function | Purpose |\n|------|----------|---------| \n| 1 | **`discover_documents`** | List documents in the bucket, prioritize benchmark-referenced docs, apply a size cap, and write a JSON manifest (no content download). |\n| 2 | **`extract_text`** | Download the listed documents from S3 and extract text to DoclingDocument JSON files using Docling. |"
+   "source": "The data processing pipeline prepares documents for the RAG system in multiple steps. Each step produces outputs stored under `step_outputs/`. \n\n| Step | Function | Purpose |\n|------|----------|---------| \n| 1 | **`discover_documents`** | List documents under every selected prefix, prioritize benchmark-referenced docs, apply a size cap, and write a JSON manifest (no content download). |\n| 2 | **`extract_text`** | Download the listed documents from S3 and extract text to DoclingDocument JSON files using Docling. |"
   },
   {
    "cell_type": "code",
@@ -219,7 +219,7 @@
     "\n",
     "step_output_dir = Path(\"./step_outputs\")\n",
     "input_data_bucket_name = os.environ[\"AWS_S3_BUCKET\"]\n",
-    "input_data_key = \"{INPUT_DATA_KEY}\"\n",
+    "input_data_keys = {INPUT_DATA_KEYS}\n",
     "step_output_dir.mkdir(parents=True, exist_ok=True)"
    ]
   },
@@ -229,15 +229,15 @@
    "source": [
     "### Documents discovery\n",
     "\n",
-    "Lists objects in the S3 input bucket, filters by supported extensions (e.g., `.pdf`, `.docx`, `.pptx`, `.md`, `.html`, `.txt`), and builds a document set. Documents referenced in the benchmark are prioritized, then others are added until a configurable size limit (1 GB by default) is reached. This step does not download document contents but writes a JSON manifest (`documents_descriptor.json`) containing the bucket, prefix, and list of selected object keys and sizes for the next step."
+    "Lists objects in the S3 input bucket, filters by supported extensions (e.g., `.pdf`, `.docx`, `.pptx`, `.md`, `.html`, `.txt`), and builds a document set. Documents referenced in the benchmark are prioritized, then others are added until a configurable size limit (1 GB by default) is reached. This step does not download document contents but writes a JSON manifest (`documents_descriptor.json`) containing the bucket, prefixes, and list of selected object keys and sizes for the next step."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": "result = discover_documents(\n    bucket_name=input_data_bucket_name,\n    prefix=input_data_key,\n    s3_client=s3_client,\n)\nresult.save(step_output_dir / \"discovered_documents\")\n\nprint(json.dumps(result.to_dict(), indent=4, ensure_ascii=False))"
+   "source": "result = discover_documents(\n    bucket_name=input_data_bucket_name,\n    prefixes=input_data_keys,\n    s3_client=s3_client,\n)\nresult.save(step_output_dir / \"discovered_documents\")\n\nprint(json.dumps(result.to_dict(), indent=4, ensure_ascii=False))"
   },
   {
    "cell_type": "markdown",

ai4rag/assets_generator/templates.py

@@ -2,6 +2,7 @@
 # Copyright IBM Corp. 2026
 # SPDX-License-Identifier: Apache-2.0
 # -----------------------------------------------------------------------------
+import json
 from pathlib import Path
 from typing import Any
 
@@ -38,7 +39,7 @@ def _format_required_env_vars(provider: str) -> str:
 def create_placeholder_mapping(
     output_data: dict[str, Any],
     test_data_key: str = "",
-    input_data_key: str = "",
+    input_data_keys: list[str] | None = None,
 ) -> dict[str, Any]:
     """Create a mapping from placeholder names to their values from a pattern definition.
 
@@ -52,8 +53,9 @@ def create_placeholder_mapping(
         The parsed ``pattern.json`` data.
     test_data_key : str, default=""
         S3 key of the test data file used as input to AI4RAG.
-    input_data_key : str, default=""
-        S3 key of the documents directory used as input to AI4RAG.
+    input_data_keys : list[str] | None, default=None
+        S3 key prefixes of the document locations used as input to AI4RAG.
+        Rendered into the notebook as a Python list literal.
 
     Returns
     -------
@@ -97,7 +99,9 @@ def create_placeholder_mapping(
     mapping["CHUNK_OVERLAP"] = ch.get("chunk_overlap", 50)
 
     mapping["TEST_DATA_KEY"] = test_data_key
-    mapping["INPUT_DATA_KEY"] = input_data_key
+    # Rendered by ``str.format`` into a bare expression, so it has to carry its
+    # own quoting and brackets to become a valid Python list literal.
+    mapping["INPUT_DATA_KEYS"] = json.dumps(input_data_keys or [])
 
     return mapping
 
@@ -107,7 +111,7 @@ def generate_notebook_from_template(
     output_data: dict[str, Any],
     output_notebook_path: str | Path,
     test_data_key: str = "",
-    input_data_key: str = "",
+    input_data_keys: list[str] | None = None,
 ) -> None:
     """Generate a filled notebook from a template and pattern configuration.
 
@@ -125,13 +129,13 @@ def generate_notebook_from_template(
         Path where the generated notebook is saved.
     test_data_key : str, default=""
         S3 key of the test data file used as input to AI4RAG.
-    input_data_key : str, default=""
-        S3 key of the documents directory used as input to AI4RAG.
+    input_data_keys : list[str] | None, default=None
+        S3 key prefixes of the document locations used as input to AI4RAG.
     """
     placeholder_mapping = create_placeholder_mapping(
         output_data,
         test_data_key=test_data_key,
-        input_data_key=input_data_key,
+        input_data_keys=input_data_keys,
     )
     notebook = Notebook.load(
         notebook_name=f"{notebook_template}_template.ipynb",

ai4rag/utils/data/__init__.py

@@ -2,12 +2,18 @@
 # Copyright IBM Corp. 2025-2026
 # SPDX-License-Identifier: Apache-2.0
 # -----------------------------------------------------------------------------
-from ai4rag.utils.data.documents_discovery import DiscoveryResult, DocumentDescriptor, discover_documents
+from ai4rag.utils.data.documents_discovery import (
+    BenchmarkKeyError,
+    DiscoveryResult,
+    DocumentDescriptor,
+    discover_documents,
+)
 from ai4rag.utils.data.test_data_loader import TestDataLoaderError, TestDataResult, load_test_data
 from ai4rag.utils.data.text_extraction import DoclingExtractionConfig, ExtractionResult, extract_text
 
 __all__ = [
     "discover_documents",
+    "BenchmarkKeyError",
     "DiscoveryResult",
     "DocumentDescriptor",
     "extract_text",