agentharbor commited on
Commit
1d042d1
·
verified ·
1 Parent(s): 3a4bac0

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -2
app.py CHANGED
@@ -49,7 +49,7 @@ containing atleast 10 columns along with their descriptions.''')
49
 
50
  schema_relations = model_response(f'''Based on the context: {py}, generate a knowledge graph represented using ASCII art. Also generate a brief description of the graph.
51
  Output:
52
- Description of the graph listing all the relationships
53
  ASCII version of the knowledge graph with nodes represented by tables and edges represented by the relationships. Edges should be annotated with the type of relationships identified - many-to-one, many-to-many, one-to-one, primary key, self joins, foreign keys etc''')
54
  yield dataset_description, py, schema_relations, None, None, None, None
55
  generated_glossary = model_response(f'''Based on the relationships identified: {schema_relations}
@@ -71,6 +71,7 @@ containing atleast 10 columns along with their descriptions.''')
71
  - Then output the relationships between the business terms as follows:
72
  term -> [related_term1, related_term2]
73
  Show the relationship between the glossary term and the column broken down by each table.
 
74
  ''')
75
  yield dataset_description, py, schema_relations, generated_glossary, None, None, None
76
  queries = generate_dataset_queries(dataset, generated_glossary, schema_relations)
@@ -105,7 +106,7 @@ iface = gr.Interface(
105
  live=False,
106
  theme = gr.themes.Ocean(),
107
  title="BQ knowledge engine ⚙️💡📊 (Simulator)",
108
- description="Provide a dataset ID to generate LookML, schema relationships, glossary, and more, with live updates.", examples=['ncaa_basketball2', 'supply_chain_ashwins','thelook_ecommerce','CORTEX_SAP_CDC','dt_kg_demo','geo_openstreetmap','google_political_ads','noaa_historic_severe_storms','stackoverflow'],
109
  article = "This is a simulator that provides a sneak-peek into how BQ knowledge engine works."
110
  )
111
  # Launch the app
 
49
 
50
  schema_relations = model_response(f'''Based on the context: {py}, generate a knowledge graph represented using ASCII art. Also generate a brief description of the graph.
51
  Output:
52
+ Description of the graph listing all the relationships in markdown format
53
  ASCII version of the knowledge graph with nodes represented by tables and edges represented by the relationships. Edges should be annotated with the type of relationships identified - many-to-one, many-to-many, one-to-one, primary key, self joins, foreign keys etc''')
54
  yield dataset_description, py, schema_relations, None, None, None, None
55
  generated_glossary = model_response(f'''Based on the relationships identified: {schema_relations}
 
71
  - Then output the relationships between the business terms as follows:
72
  term -> [related_term1, related_term2]
73
  Show the relationship between the glossary term and the column broken down by each table.
74
+ Ensure that the output is in markdown format
75
  ''')
76
  yield dataset_description, py, schema_relations, generated_glossary, None, None, None
77
  queries = generate_dataset_queries(dataset, generated_glossary, schema_relations)
 
106
  live=False,
107
  theme = gr.themes.Ocean(),
108
  title="BQ knowledge engine ⚙️💡📊 (Simulator)",
109
+ description="Provide a dataset ID to generate LookML, schema relationships, glossary, and more...", examples=['ncaa_basketball2', 'thelook_ecommerce','geo_openstreetmap','google_political_ads','noaa_historic_severe_storms','stackoverflow'],
110
  article = "This is a simulator that provides a sneak-peek into how BQ knowledge engine works."
111
  )
112
  # Launch the app