Fix GraphRAG notebook: embedding dimension check, update LLM model to llama-3.3-70b-versatile, fix file ingestion, graph metrics access, and export methods

This commit is contained in:
KaifAhmad1
2025-12-24 13:00:10 +05:30
parent bd466b6016
commit cd437a9cfb
3 changed files with 937 additions and 5 deletions
@@ -2250,7 +2250,7 @@
},
{
"cell_type": "code",
"execution_count": 85,
"execution_count": 86,
"metadata": {},
"outputs": [
{
@@ -2259,8 +2259,8 @@
"text": [
"\n",
"Exporting knowledge graph...\n",
" Warning: JSON export error: 'GraphExporter' object has no attribute 'export_json'\n",
" Warning: GraphML export error: 'GraphExporter' object has no attribute 'export_graphml'\n",
" Exported to JSON: graphrag_kg.json\n",
" Exported to GraphML: graphrag_kg.graphml\n",
"\n",
"Phase 7 Complete. Graph visualized and exported.\n"
]
@@ -2276,14 +2276,14 @@
"\n",
"# Export to JSON (human-readable, easy to process)\n",
"try:\n",
" exporter.export_json(kg_final, \"graphrag_kg.json\")\n",
" exporter.export_knowledge_graph(kg_final, \"graphrag_kg.json\", format=\"json\")\n",
" print(\" Exported to JSON: graphrag_kg.json\")\n",
"except Exception as e:\n",
" print(f\" Warning: JSON export error: {e}\")\n",
"\n",
"# Export to GraphML (standard graph format)\n",
"try:\n",
" exporter.export_graphml(kg_final, \"graphrag_kg.graphml\")\n",
" exporter.export_knowledge_graph(kg_final, \"graphrag_kg.graphml\", format=\"graphml\")\n",
" print(\" Exported to GraphML: graphrag_kg.graphml\")\n",
"except Exception as e:\n",
" print(f\" Warning: GraphML export error: {e}\")\n",
@@ -0,0 +1,254 @@
<?xml version="1.0" encoding="UTF-8"?>
<graphml xmlns="http://graphml.graphdrawing.org/xmlns"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://graphml.graphdrawing.org/xmlns
http://graphml.graphdrawing.org/xmlns/1.0/graphml.xsd">
<key id="type" for="node" attr.name="type" attr.type="string"/>
<key id="confidence" for="node" attr.name="confidence" attr.type="double"/>
<graph id="G" edgedefault="directed">
<node id="makeup_and_beauty_blog">
<data key="label">Makeup and Beauty Blog</data>
<data key="type">ORG</data>
<data key="confidence">1.0</data>
</node>
<node id="monday_poll">
<data key="label">Monday Poll</data>
<data key="type">EVENT</data>
<data key="confidence">1.0</data>
</node>
<node id="2007">
<data key="label">2007</data>
<data key="type">DATE</data>
<data key="confidence">1.0</data>
</node>
<node id="rosacea">
<data key="label">Rosacea</data>
<data key="type">CONCEPT</data>
<data key="confidence">1.0</data>
</node>
<node id="dr._bailey">
<data key="label">Dr. Bailey</data>
<data key="type">PERSON</data>
<data key="confidence">1.0</data>
</node>
<node id="green_tea_antioxidant_skin_therapy">
<data key="label">Green Tea Antioxidant Skin Therapy</data>
<data key="type">PRODUCT</data>
<data key="confidence">1.0</data>
</node>
<node id="vol._892">
<data key="label">Vol. 892</data>
<data key="type">EVENT</data>
<data key="confidence">1.0</data>
</node>
<node id="laneige">
<data key="label">Laneige</data>
<data key="type">ORG</data>
<data key="confidence">1.0</data>
</node>
<node id="sausalito">
<data key="label">Sausalito</data>
<data key="type">GPE</data>
<data key="confidence">1.0</data>
</node>
<node id="ulta">
<data key="label">Ulta</data>
<data key="type">ORG</data>
<data key="confidence">1.0</data>
</node>
<node id="december_15,_2025">
<data key="label">December 15, 2025</data>
<data key="type">DATE</data>
<data key="confidence">1.0</data>
</node>
<node id="jo_malone">
<data key="label">Jo Malone</data>
<data key="type">ORG</data>
<data key="confidence">1</data>
</node>
<node id="trader_joe">
<data key="label">Trader Joe</data>
<data key="type">ORG</data>
<data key="confidence">1</data>
</node>
<node id="hawaii">
<data key="label">hawaii</data>
<data key="type">GPE</data>
<data key="confidence">1.0</data>
</node>
<node id="benzoyl_peroxide_cream">
<data key="label">Benzoyl Peroxide Cream</data>
<data key="type">PRODUCT</data>
<data key="confidence">1</data>
</node>
<node id="facial_dandruff">
<data key="label">Facial dandruff</data>
<data key="type">CONCEPT</data>
<data key="confidence">1</data>
</node>
<node id="calming_zinc_soap">
<data key="label">Calming Zinc Soap</data>
<data key="type">PRODUCT</data>
<data key="confidence">1</data>
</node>
<node id="hydrate">
<data key="label">Hydrate</data>
<data key="type">CONCEPT</data>
<data key="confidence">1.0</data>
</node>
<node id="daily_moisturizing_face_cream">
<data key="label">Daily Moisturizing Face Cream</data>
<data key="type">PRODUCT</data>
<data key="confidence">1.0</data>
</node>
<node id="omega_enriched_face_booster_oil">
<data key="label">Omega Enriched Face Booster Oil</data>
<data key="type">PRODUCT</data>
<data key="confidence">1.0</data>
</node>
<edge source="Makeup and Beauty Blog" target="Monday Poll">
<data key="label">hosts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Monday Poll" target="December 15, 2025">
<data key="label">occurs on</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Makeup and Beauty Blog Monday Poll, Vol. 893">
<data key="label">publishes</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Monday">
<data key="label">has</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="2007">
<data key="label">has</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Monday Poll">
<data key="label">hosts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Makeup and Beauty Blog Monday Poll">
<data key="label">posts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Vol. 892">
<data key="label">posts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="2007">
<data key="label">has been active since</data>
<data key="confidence">0.9</data>
</edge>
<edge source="MBB" target="Makeup and Beauty Blog">
<data key="label">related_to</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Makeup and Beauty Blog">
<data key="label">related_to</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Monday Poll">
<data key="label">hosts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Vol. 891">
<data key="label">posts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Makeup and Beauty Blog" target="Monday Poll">
<data key="label">posts</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Cavallo Point" target="Sausalito">
<data key="label">located_in</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey" target="Green Tea Antioxidant Skin Therapy">
<data key="label">prescribes</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Green Tea Antioxidant Skin Therapy" target="Rosacea Therapy Skin Care Kit">
<data key="label">part of</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey" target="Rosacea Therapy Skin Care Kit">
<data key="label">uses</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Rosacea Therapy Skin Care Kit" target="rosacea treatment routine">
<data key="label">part of</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey" target="rosacea treatment routine">
<data key="label">uses</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Facial dandruff" target="rosacea">
<data key="label">often occurs with</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Facial dandruff" target="rosacea">
<data key="label">needs to be addressed</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Calming Zinc Soap" target="Facial dandruff">
<data key="label">is often sufficient to control</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Calming Zinc Soap" target="rosacea">
<data key="label">is often sufficient to control</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Green Tea Antioxidant Skin Therapy" target="Facial dandruff">
<data key="label">is often sufficient to control</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Green Tea Antioxidant Skin Therapy" target="rosacea">
<data key="label">is often sufficient to control</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey's Skincare" target="Calming Zinc Soap">
<data key="label">produces</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey's Skincare" target="Green Tea Antioxidant Skin Therapy">
<data key="label">produces</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey" target="Calming Zinc Soap">
<data key="label">prescribes</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Dr. Bailey" target="Green Tea Antioxidant Skin Therapy">
<data key="label">prescribes</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Hydrate" target="Daily Moisturizing Face Cream">
<data key="label">is_achieved_by</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Daily Moisturizing Face Cream" target="Omega Enriched Face Booster Oil">
<data key="label">can_be_combined_with</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Omega Enriched Face Booster Oil" target="castor seed oil">
<data key="label">contains</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Omega Enriched Face Booster Oil" target="sea buckthorn">
<data key="label">contains</data>
<data key="confidence">0.9</data>
</edge>
<edge source="Daily Moisturizing Face Cream" target="Omega Enriched Face Booster Oil">
<data key="label">can_be_replaced_with</data>
<data key="confidence">0.9</data>
</edge>
</graph>
</graphml>
@@ -0,0 +1,678 @@
{
"nodes": [
{
"id": "makeup_and_beauty_blog",
"label": "Makeup and Beauty Blog",
"type": "ORG",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "makeup_and_beauty_blog",
"name": "Makeup and Beauty Blog",
"source": null
},
{
"id": "makeup_and_beauty_blog",
"name": "Makeup and Beauty Blog",
"source": null
},
{
"id": "makeup_and_beauty_blog_monday_poll,_vol._893",
"name": "Makeup and Beauty Blog Monday Poll, Vol. 893",
"source": null
},
{
"id": "makeup_and_beauty_blog_monday_poll",
"name": "Makeup and Beauty Blog Monday Poll",
"source": null
},
{
"id": "mbb",
"name": "MBB",
"source": null
}
],
"merge_count": 5
}
}
},
{
"id": "monday_poll",
"label": "Monday Poll",
"type": "EVENT",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "monday_poll",
"name": "Monday Poll",
"source": null
},
{
"id": "monday_poll",
"name": "Monday Poll",
"source": null
},
{
"id": "monday",
"name": "Monday",
"source": null
},
{
"id": "holiday",
"name": "holiday",
"source": null
},
{
"id": "holiday",
"name": "holiday",
"source": null
}
],
"merge_count": 5
}
}
},
{
"id": "2007",
"label": "2007",
"type": "DATE",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "2007",
"name": "2007",
"source": null
},
{
"id": "2007",
"name": "2007",
"source": null
},
{
"id": "2024",
"name": "2024",
"source": null
}
],
"merge_count": 3
}
}
},
{
"id": "rosacea",
"label": "Rosacea",
"type": "CONCEPT",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "rosacea",
"name": "Rosacea",
"source": null
},
{
"id": "rosacea",
"name": "rosacea",
"source": null
},
{
"id": "rosacea_treatment_routine",
"name": "rosacea treatment routine",
"source": null
},
{
"id": "rosie",
"name": "Rosie",
"source": null
},
{
"id": "rosacea_therapy_skin_care_kit",
"name": "Rosacea Therapy Skin Care Kit",
"source": null
},
{
"id": "marnie",
"name": "Marnie",
"source": null
},
{
"id": "cavallo_point",
"name": "Cavallo Point",
"source": null
},
{
"id": "castor_seed_oil",
"name": "castor seed oil",
"source": null
}
],
"merge_count": 8
}
}
},
{
"id": "dr._bailey",
"label": "Dr. Bailey",
"type": "PERSON",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "dr._bailey",
"name": "Dr. Bailey",
"source": null
},
{
"id": "dr._bailey",
"name": "Dr. Bailey",
"source": null
},
{
"id": "dr._bailey's_skincare",
"name": "Dr. Bailey's Skincare",
"source": null
},
{
"id": "dr._bailey's_skincare",
"name": "Dr. Bailey's Skincare",
"source": null
}
],
"merge_count": 4
}
}
},
{
"id": "green_tea_antioxidant_skin_therapy",
"label": "Green Tea Antioxidant Skin Therapy",
"type": "PRODUCT",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "green_tea_antioxidant_skin_therapy",
"name": "Green Tea Antioxidant Skin Therapy",
"source": null
},
{
"id": "green_tea_antioxidant_skin_therapy",
"name": "Green Tea Antioxidant Skin Therapy",
"source": null
}
],
"merge_count": 2
}
}
},
{
"id": "vol._892",
"label": "Vol. 892",
"type": "EVENT",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "vol._892",
"name": "Vol. 892",
"source": null
},
{
"id": "vol._891",
"name": "Vol. 891",
"source": null
}
],
"merge_count": 2
}
}
},
{
"id": "laneige",
"label": "Laneige",
"type": "ORG",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "laneige",
"name": "Laneige",
"source": null
},
{
"id": "lanikai",
"name": "Lanikai",
"source": null
}
],
"merge_count": 2
}
}
},
{
"id": "sausalito",
"label": "Sausalito",
"type": "GPE",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "sausalito",
"name": "Sausalito",
"source": null
},
{
"id": "sea_buckthorn",
"name": "sea buckthorn",
"source": null
}
],
"merge_count": 2
}
}
},
{
"id": "ulta",
"label": "Ulta",
"type": "ORG",
"attributes": {
"confidence": 1.0,
"provenance": {
"merged_from": [
{
"id": "ulta",
"name": "Ulta",
"source": null
},
{
"id": "clotrimazole",
"name": "clotrimazole",
"source": null
}
],
"merge_count": 2
}
}
},
{
"id": "december_15,_2025",
"label": "December 15, 2025",
"type": "DATE",
"attributes": {
"confidence": 1.0
}
},
{
"id": "jo_malone",
"label": "Jo Malone",
"type": "ORG",
"attributes": {
"confidence": 1
}
},
{
"id": "trader_joe",
"label": "Trader Joe",
"type": "ORG",
"attributes": {
"confidence": 1
}
},
{
"id": "hawaii",
"label": "hawaii",
"type": "GPE",
"attributes": {
"confidence": 1.0
}
},
{
"id": "benzoyl_peroxide_cream",
"label": "Benzoyl Peroxide Cream",
"type": "PRODUCT",
"attributes": {
"confidence": 1
}
},
{
"id": "facial_dandruff",
"label": "Facial dandruff",
"type": "CONCEPT",
"attributes": {
"confidence": 1
}
},
{
"id": "calming_zinc_soap",
"label": "Calming Zinc Soap",
"type": "PRODUCT",
"attributes": {
"confidence": 1
}
},
{
"id": "hydrate",
"label": "Hydrate",
"type": "CONCEPT",
"attributes": {
"confidence": 1.0
}
},
{
"id": "daily_moisturizing_face_cream",
"label": "Daily Moisturizing Face Cream",
"type": "PRODUCT",
"attributes": {
"confidence": 1.0
}
},
{
"id": "omega_enriched_face_booster_oil",
"label": "Omega Enriched Face Booster Oil",
"type": "PRODUCT",
"attributes": {
"confidence": 1.0
}
}
],
"edges": [
{
"source": "Makeup and Beauty Blog",
"target": "Monday Poll",
"type": "hosts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Monday Poll",
"target": "December 15, 2025",
"type": "occurs on",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Makeup and Beauty Blog Monday Poll, Vol. 893",
"type": "publishes",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Monday",
"type": "has",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "2007",
"type": "has",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Monday Poll",
"type": "hosts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Makeup and Beauty Blog Monday Poll",
"type": "posts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Vol. 892",
"type": "posts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "2007",
"type": "has been active since",
"attributes": {
"confidence": 0.9
}
},
{
"source": "MBB",
"target": "Makeup and Beauty Blog",
"type": "related_to",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Makeup and Beauty Blog",
"type": "related_to",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Monday Poll",
"type": "hosts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Vol. 891",
"type": "posts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Makeup and Beauty Blog",
"target": "Monday Poll",
"type": "posts",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Cavallo Point",
"target": "Sausalito",
"type": "located_in",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey",
"target": "Green Tea Antioxidant Skin Therapy",
"type": "prescribes",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Green Tea Antioxidant Skin Therapy",
"target": "Rosacea Therapy Skin Care Kit",
"type": "part of",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey",
"target": "Rosacea Therapy Skin Care Kit",
"type": "uses",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Rosacea Therapy Skin Care Kit",
"target": "rosacea treatment routine",
"type": "part of",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey",
"target": "rosacea treatment routine",
"type": "uses",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Facial dandruff",
"target": "rosacea",
"type": "often occurs with",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Facial dandruff",
"target": "rosacea",
"type": "needs to be addressed",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Calming Zinc Soap",
"target": "Facial dandruff",
"type": "is often sufficient to control",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Calming Zinc Soap",
"target": "rosacea",
"type": "is often sufficient to control",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Green Tea Antioxidant Skin Therapy",
"target": "Facial dandruff",
"type": "is often sufficient to control",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Green Tea Antioxidant Skin Therapy",
"target": "rosacea",
"type": "is often sufficient to control",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey's Skincare",
"target": "Calming Zinc Soap",
"type": "produces",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey's Skincare",
"target": "Green Tea Antioxidant Skin Therapy",
"type": "produces",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey",
"target": "Calming Zinc Soap",
"type": "prescribes",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Dr. Bailey",
"target": "Green Tea Antioxidant Skin Therapy",
"type": "prescribes",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Hydrate",
"target": "Daily Moisturizing Face Cream",
"type": "is_achieved_by",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Daily Moisturizing Face Cream",
"target": "Omega Enriched Face Booster Oil",
"type": "can_be_combined_with",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Omega Enriched Face Booster Oil",
"target": "castor seed oil",
"type": "contains",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Omega Enriched Face Booster Oil",
"target": "sea buckthorn",
"type": "contains",
"attributes": {
"confidence": 0.9
}
},
{
"source": "Daily Moisturizing Face Cream",
"target": "Omega Enriched Face Booster Oil",
"type": "can_be_replaced_with",
"attributes": {
"confidence": 0.9
}
}
],
"metadata": {
"num_entities": 20,
"num_relationships": 35,
"temporal_enabled": false,
"timestamp": "2025-12-24T12:46:41.535755",
"entity_resolution_applied": true
}
}