diff --git a/rag_basic.ipynb b/rag_basic.ipynb index 27285c4..c43b34c 100644 --- a/rag_basic.ipynb +++ b/rag_basic.ipynb @@ -585,18 +585,18 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 42, "metadata": {}, "outputs": [ { - "ename": "NameError", - "evalue": "name 'i' is not defined", + "ename": "TypeError", + "evalue": "'builtin_function_or_method' object is not subscriptable", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[0;32mIn[39], line 4\u001b[0m\n\u001b[1;32m 1\u001b[0m df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame\u001b[38;5;241m.\u001b[39mfrom_dict(\n\u001b[1;32m 2\u001b[0m [\n\u001b[1;32m 3\u001b[0m {\n\u001b[0;32m----> 4\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mx\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_proj[\u001b[43mi\u001b[49m, \u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 5\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_proj[i, \u001b[38;5;241m1\u001b[39m],\n\u001b[1;32m 6\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msource\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_processed[i]\u001b[38;5;241m.\u001b[39mmetadata[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msource\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39msplit[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m][\u001b[38;5;241m1\u001b[39m],\n\u001b[1;32m 7\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mextract\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_processed[i]\u001b[38;5;241m.\u001b[39mpage_content[:\u001b[38;5;241m100\u001b[39m] \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m...\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 8\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msymbol\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcircle\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 9\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msize_col\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;241m4\u001b[39m\n\u001b[1;32m 10\u001b[0m }\n\u001b[1;32m 11\u001b[0m ]\n\u001b[1;32m 12\u001b[0m )\n", - "\u001b[0;31mNameError\u001b[0m: name 'i' is not defined" + "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[42], line 6\u001b[0m\n\u001b[1;32m 1\u001b[0m df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame\u001b[38;5;241m.\u001b[39mfrom_dict(\n\u001b[1;32m 2\u001b[0m [\n\u001b[1;32m 3\u001b[0m {\n\u001b[1;32m 4\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mx\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_proj[i, \u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 5\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_proj[i, \u001b[38;5;241m1\u001b[39m],\n\u001b[0;32m----> 6\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msource\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[43mdocs_processed\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43msource\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m[\u001b[38;5;241m1\u001b[39m],\n\u001b[1;32m 7\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mextract\u001b[39m\u001b[38;5;124m'\u001b[39m: docs_processed[i]\u001b[38;5;241m.\u001b[39mpage_content[:\u001b[38;5;241m100\u001b[39m] \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m...\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 8\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msymbol\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcircle\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 9\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msize_col\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;241m4\u001b[39m,\n\u001b[1;32m 10\u001b[0m }\n\u001b[1;32m 11\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;28mlen\u001b[39m(docs_processed))\n\u001b[1;32m 12\u001b[0m ]\n\u001b[1;32m 13\u001b[0m \u001b[38;5;241m+\u001b[39m [\n\u001b[1;32m 14\u001b[0m {\n\u001b[1;32m 15\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mx\u001b[39m\u001b[38;5;124m\"\u001b[39m: docs_proj[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m 16\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124my\u001b[39m\u001b[38;5;124m\"\u001b[39m: docs_proj[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m1\u001b[39m],\n\u001b[1;32m 17\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msource\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUser query\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 18\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mextract\u001b[39m\u001b[38;5;124m\"\u001b[39m: user_query,\n\u001b[1;32m 19\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize_col\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;241m100\u001b[39m,\n\u001b[1;32m 20\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msymbol\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstar\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 21\u001b[0m }\n\u001b[1;32m 22\u001b[0m ]\n\u001b[1;32m 23\u001b[0m )\n", + "\u001b[0;31mTypeError\u001b[0m: 'builtin_function_or_method' object is not subscriptable" ] } ], @@ -606,14 +606,25 @@ " {\n", " 'x': docs_proj[i, 0],\n", " 'y': docs_proj[i, 1],\n", - " 'source': docs_processed[i].metadata['source'].split['/'][1],\n", + " 'source': docs_processed[i].metadata['source'].split('/')[1],\n", " 'extract': docs_processed[i].page_content[:100] + \"...\",\n", " 'symbol': \"circle\",\n", - " 'size_col': 4\n", + " 'size_col': 4,\n", " }\n", " for i in range(len(docs_processed))\n", " ]\n", + " + [\n", + " {\n", + " \"x\": docs_proj[-1, 0],\n", + " \"y\": docs_proj[-1, 1],\n", + " \"source\": \"User query\",\n", + " \"extract\": user_query,\n", + " \"size_col\": 100,\n", + " \"symbol\": \"star\",\n", + " }\n", + " ]\n", ")\n", + "\n", "\n" ] }