updated notebook for chapter_number

bug chapter_number = None. forgot = sign
elastic · Jun 5, 2024 · 5b49345 · 5b49345
1 parent fe8141e
commit 5b49345
Showing 1 changed file with 35 additions and 19 deletions.
diff --git a/notebooks/document-chunking/fetch-surrounding-chunks.ipynb b/notebooks/document-chunking/fetch-surrounding-chunks.ipynb
@@ -986,35 +986,43 @@
     "\n",
     "knn_boost_factor = 20\n",
     "text_expansion_boost = 1\n",
-    "query = build_custom_query(build_vector(user_query), user_query, knn_boost_factor, text_expansion_boost, debug=False)\n",
+    "query = build_custom_query(\n",
+    "    build_vector(user_query),\n",
+    "    user_query,\n",
+    "    knn_boost_factor,\n",
+    "    text_expansion_boost,\n",
+    "    debug=False,\n",
+    ")\n",
     "\n",
     "# Searching and identifying relevant passages\n",
     "results = esclient.search(index=index_name, body=query, _source=False)\n",
     "\n",
     "hit_id = None\n",
     "chunk_number = None\n",
-    "chapter_number None\n",
+    "chapter_number = None\n",
     "\n",
-    "if results and results.get('hits') and results['hits'].get('hits'):\n",
+    "if results and results.get(\"hits\") and results[\"hits\"].get(\"hits\"):\n",
     "    highest_score = -1\n",
     "    best_hit = None\n",
-    "    hit_id = results['hits']['hits'][0]['_id']\n",
-    "    chapter_number = results['hits']['hits'][0]['fields']['chapter'][0]\n",
-    "    if 'inner_hits' in results['hits']['hits'][0]:\n",
-    "        for hit_type in ['text_hits', 'dense_hit', 'sparse_hits']:\n",
-    "            if hit_type in results['hits']['hits'][0]['inner_hits']:\n",
-    "                inner_hit = results['hits']['hits'][0]['inner_hits'][hit_type]['hits']\n",
-    "                if inner_hit['hits']:\n",
-    "                    max_score = inner_hit['max_score']\n",
+    "    hit_id = results[\"hits\"][\"hits\"][0][\"_id\"]\n",
+    "    chapter_number = results[\"hits\"][\"hits\"][0][\"fields\"][\"chapter\"][0]\n",
+    "    if \"inner_hits\" in results[\"hits\"][\"hits\"][0]:\n",
+    "        for hit_type in [\"text_hits\", \"dense_hit\", \"sparse_hits\"]:\n",
+    "            if hit_type in results[\"hits\"][\"hits\"][0][\"inner_hits\"]:\n",
+    "                inner_hit = results[\"hits\"][\"hits\"][0][\"inner_hits\"][hit_type][\"hits\"]\n",
+    "                if inner_hit[\"hits\"]:\n",
+    "                    max_score = inner_hit[\"max_score\"]\n",
     "                    if max_score and max_score > highest_score:\n",
     "                        highest_score = max_score\n",
-    "                        best_hit = inner_hit['hits'][0]\n",
+    "                        best_hit = inner_hit[\"hits\"][0]\n",
     "\n",
     "    if best_hit:\n",
-    "        first_passage_text = best_hit['_source']['text']\n",
-    "        chunk_number = best_hit['_source']['chunk_number']\n",
-    "        #print(f\"Matched Chunk ID: {hit_id}, Chunk Number: {chunk_number}, Text: {first_passage_text}\")\n",
-    "        print(f\"Matched Chunk ID: {hit_id}, Chunk Number: {chunk_number}, Text:\\n{textwrap.fill(first_passage_text, width=200)}\")\n",
+    "        first_passage_text = best_hit[\"_source\"][\"text\"]\n",
+    "        chunk_number = best_hit[\"_source\"][\"chunk_number\"]\n",
+    "        # print(f\"Matched Chunk ID: {hit_id}, Chunk Number: {chunk_number}, Text: {first_passage_text}\")\n",
+    "        print(\n",
+    "            f\"Matched Chunk ID: {hit_id}, Chunk Number: {chunk_number}, Text:\\n{textwrap.fill(first_passage_text, width=200)}\"\n",
+    "        )\n",
     "        print(f\"\\n\")\n",
     "    else:\n",
     "        print(f\"ID: {hit_id}, No relevant passages found.\")\n",
@@ -1024,10 +1032,18 @@
     "print(f\"Fetch Surrounding Chunks\")\n",
     "print(f\"------------------------\")\n",
     "\n",
-    "max_chapter_chunk_result = esclient.search(index=index_name, body=get_max_chunk_number_query(chapter_number, debug=False), _source=False)\n",
-    "max_chunk_number = max_chapter_chunk_result['aggregations']['max_chunk_number']['max_chunk']['value']\n",
+    "max_chapter_chunk_result = esclient.search(\n",
+    "    index=index_name,\n",
+    "    body=get_max_chunk_number_query(chapter_number, debug=False),\n",
+    "    _source=False,\n",
+    ")\n",
+    "max_chunk_number = max_chapter_chunk_result[\"aggregations\"][\"max_chunk_number\"][\n",
+    "    \"max_chunk\"\n",
+    "][\"value\"]\n",
     "\n",
-    "adjacent_chunks_query = get_adjacent_chunks_query(hit_id, chunk_number, max_chunk_number, debug=False)\n",
+    "adjacent_chunks_query = get_adjacent_chunks_query(\n",
+    "    hit_id, chunk_number, max_chunk_number, debug=False\n",
+    ")\n",
     "results = esclient.search(index=index_name, body=adjacent_chunks_query, _source=False)\n",
     "print_text_from_results(results)"
    ],