kaimary / gar Goto Github PK

View Code? Open in Web Editor NEW

16.0 2.0 1.0 221 KB

ICDE 2023 Paper, GAR: A Generate-and-Rank Approach for Natural Language to SQL Translation

License: Apache License 2.0

Python 96.20% Shell 3.33% Jsonnet 0.47%

semantic-parsing natural-language-interface generate-and-rank learning-to-rank text-to-sql

gar's Issues

Error SQL statements in the test steps

It seems that the value filter stage failed because there is a wrong table name events in the SQL statement.

For the SQL SELECT EVENTS.EVENT_DETAILS , PARTICIPANTS_IN_EVENTS.EVENT_ID FROM EVENTS AS T1 JOIN PARTICIPANTS_IN_EVENTS AS T2 ON T1.EVENT_ID = T2.EVENT_ID GROUP BY PARTICIPANTS_IN_EVENTS.EVENT_ID HAVING COUNT ( * ) > 'VALUE', there is an error:

Traceback (most recent call last):                                                                                                                  File "/f/.conda/envs/SQL_GAR2/lib/python3.7/runpy.py", line 193, in _run_module_as_main                                                             "__main__", mod_spec)                                                                                                                           File "/f/.conda/envs/SQL_GAR2/lib/python3.7/runpy.py", line 85, in _run_code                                                                    
    exec(code, run_globals)                                                                                                                       
  File "/f/code/SQL/GAR/scripts/value_postprocessing/candidate_filter_top10.py", line 187, in <module>                                            
    main()                                                                                                                                        
  File "/f/.conda/envs/SQL_GAR2/lib/python3.7/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/f/.conda/envs/SQL_GAR2/lib/python3.7/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/f/.conda/envs/SQL_GAR2/lib/python3.7/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/f/.conda/envs/SQL_GAR2/lib/python3.7/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/f/code/SQL/GAR/scripts/value_postprocessing/candidate_filter_top10.py", line 158, in main
    tmp = candidate_filter(candidates, db_id, db_context, tables_file, database_dir)
  File "/f/code/SQL/GAR/scripts/value_postprocessing/candidate_filter_top10.py", line 97, in candidate_filter
    sql_dict = rebuild_sql(db_id, dataset_path, sql_nested_query_tmp_name_convert(candidate), kmaps)
  File "/f/code/SQL/GAR/utils/evaluation/evaluate.py", line 536, in rebuild_sql
    sql = get_sql(schema, sql_str)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 630, in get_sql
    _, sql = parse_sql(toks, 0, tables_with_alias, schema)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 556, in parse_sql
    from_end_idx, table_units, conds, default_tables = parse_from(toks, start_idx, tables_with_alias, schema)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 433, in parse_from
    idx, table_unit, table_name = parse_table_unit(toks, idx, tables_with_alias, schema)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 281, in parse_table_unit
    key = tables_with_alias[toks[idx]]
KeyError: 'events'
RESULT REPORT: Value filter result failed!

Thank you in advance! Maybe there is something that I need to modify in the datasets.

Error in Reading Dataset for training

I am trying to train the model but I am getting
"AssertionError: Error col: "value"" ,

I have attached the entire output log.

New Text Document.txt

Issue in the code to run the Train script and evaluation script

I am not getting what arguments to be given while running the training script and evaluation script
Would yo pls mention the local path that you are using for each of these arguments...

$ bash train_pipeline.sh <dataset_name> <train_data_path> <dev_data_path> <table_path> <db_dir>

$ bash test_pipeline.sh <dataset_name> <test_file_path> <test_gold_sql_file> <table_path> <db_dir>

Package conflicts

I found the following error:

ERROR: Cannot install allennlp==1.2.0 and sentence-transformers==2.2.2 because these package versions have conflicting dependencies.

The conflict is caused by:
    sentence-transformers 2.2.2 depends on transformers<5.0.0 and >=4.6.0
    allennlp 1.2.0 depends on transformers<3.5 and >=3.1

However, these versions are shown in requirements.txt. I wonder what is the suitable versions of these packages?

Error SQL statements in training steps

Thank you for your excellent work. However, when I used spider to train the model (I used the script bash train_pipeline.sh spider datasets/spider/train_spider.json datasets/spider/dev.json datasets/spider/tables.json datasets/spider/database). When sql_str is select count ( * ) from follows group by "value", an AssertionError occurs: Error col: "value".

I wonder what I should do to solve this problem. Should I skip all the SQL strings that cause such an error by using a simple try-except statement?

The traceback is:

  4%|█████▊                                                                                                                                           | 278/7000 [00:00<00:18, 371.50it/s]Traceback (most recent call last):
  File "/f/.conda/envs/SQL_GAR/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/f/.conda/envs/SQL_GAR/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/f/code/SQL/GAR/scripts/retrieval_model_train_script.py", line 271, in <module>
    main()
  File "/f/.conda/envs/SQL_GAR/lib/python3.7/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/f/.conda/envs/SQL_GAR/lib/python3.7/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/f/.conda/envs/SQL_GAR/lib/python3.7/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/f/.conda/envs/SQL_GAR/lib/python3.7/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/f/code/SQL/GAR/scripts/retrieval_model_train_script.py", line 39, in main
    dataset_name, train_file, tables_file, db_dir, output_dir
  File "/f/code/SQL/GAR/scripts/retrieval_model_train_script.py", line 118, in generate_triples_for_retrieval_model
    checker = RecallChecker(data_file, tables_file, db_dir, output_dir)
  File "/f/code/SQL/GAR/utils/recall_checker_utils.py", line 31, in __init__
    self.initialize(dataset_file, tables_file)
  File "/f/code/SQL/GAR/utils/recall_checker_utils.py", line 42, in initialize
    g_sql = rebuild_sql(db_id, self.db_dir, sql_nested_query_tmp_name_convert(query), self.kmaps, tables_file)
  File "/f/code/SQL/GAR/utils/evaluation/evaluate.py", line 537, in rebuild_sql
    sql = get_sql(schema, sql_str)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 630, in get_sql
    _, sql = parse_sql(toks, 0, tables_with_alias, schema)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 566, in parse_sql
    idx, group_col_units = parse_group_by(toks, idx, tables_with_alias, schema, default_tables)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 477, in parse_group_by
    idx, col_unit = parse_col_unit(toks, idx, tables_with_alias, schema, default_tables)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 241, in parse_col_unit
    idx, col_id = parse_col(toks, idx, tables_with_alias, schema, default_tables)
  File "/f/code/SQL/GAR/utils/evaluation/process_sql.py", line 209, in parse_col
    assert False, "Error col: {}".format(tok)
AssertionError: Error col: "value"
RESULT REPORT: Retrieval model fine-tune data failed!

(Because I added print(sql_str) to the Line 536 of utils/evaluation/evaluate.py, File "/f/code/SQL/GAR/utils/evaluation/evaluate.py", line 537, in rebuild_sql should be Line 536)

Problems when self.skeletons is an empty list

I suggest to add an assert statement assert self.skeletons, "self.skeletons is []" before

GAR/generator/QunitGenerator/qunit_generator.py

Line 78 in bc3de0a

for skeleton in self.combinatorial_rule_base["skeleton"].copy():

This is because when self.skeletons is [], we will make self.combinatorial_rule_base["skeleton"] to be [] and will return None in the function in _default_choice in

GAR/generator/QunitGenerator/qunit_generator.py

Line 259 in bc3de0a

def _default_choice(self, node_name, state_machine):

and choice(self, node_name, state_machine) in

GAR/generator/QunitGenerator/qunit_generator.py

Line 242 in bc3de0a

def choice(self, node_name, state_machine):

which is used in

GAR/generator/QunitGenerator/qunit_generator.py

Line 439 in bc3de0a

expression = handler.choice(node_name, state_machine)

If the returned value of dfs_random is None,

GAR/generator/QunitGenerator/qunit_generator.py

Line 540 in bc3de0a

ret = dfs_random("skeleton", state_machine)

will always cause ret = None and make while True: a dead cycle.

This problem occurs for me because the file serialization/gar.spider/qunits.json contains {'global_syntactic': {'max_projection_num': 0, 'max_where_predicate_num': 0, 'max_having_predicate_num': 0, 'has_output': False, 'has_iue': False, 'has_group': False, 'max_group_num': 0, 'max_where_nested_num': 0, 'max_having_nested_num': 0, 'max_iue_num': 0, 'max_order_num': 0, 'has_where': False}, 'units': [], 'skeleton': []} for concert_singer. After deleted this file, the code works.

AttributeError: module 'torch' has no attribute 'frombuffer'

While runnning the test script I am encountering the following error:

(GAR) [husainmalwat@localhost GAR]$ bash test_pipeline.sh "spider" "datasets/spider/dev.json" "datasets/spider/dev_gold.sql" "datasets/spider/tables.json" "datasets/spider/database"
Dataset name: spider
Test JSON file: datasets/spider/dev.json
Gold SQL TXT file: datasets/spider/dev_gold.sql
Schema file of the dataset: datasets/spider/tables.json
Databases directory of the dataset: datasets/spider/database
==================================================================
ACTION REPORT: Testing pipeline starts ......
Re-ranker test data exists!
==================================================================
ACTION REPORT: Start to test re-ranker model /home/husainmalwat/GAR/saved_models/gar.spider/reranker/bertpooler+roberta-base/model.tar.gz
/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3
  warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
2023-06-19 20:09:10,725 - INFO - allennlp.models.archival - loading archive file /home/husainmalwat/GAR/saved_models/gar.spider/reranker/bertpooler+roberta-base/model.tar.gz
2023-06-19 20:09:10,725 - INFO - allennlp.models.archival - extracting archive file /home/husainmalwat/GAR/saved_models/gar.spider/reranker/bertpooler+roberta-base/model.tar.gz to temp dir /tmp/tmpwtncs7m0
2023-06-19 20:09:14,081 - WARNING - allennlp.common.params - error loading _jsonnet (this is expected on Windows), treating /tmp/tmpwtncs7m0/config.json as plain json
2023-06-19 20:09:14,082 - INFO - allennlp.common.params - dataset_reader.type = listwise_pair_ranker_reader
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.lazy = False
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.cache_directory = None
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.max_instances = 100000
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.manual_distributed_sharding = False
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.manual_multi_process_sharding = False
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.tokenizer.type = pretrained_transformer
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.tokenizer.model_name = roberta-base
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.tokenizer.add_special_tokens = False
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.tokenizer.max_length = None
2023-06-19 20:09:14,083 - INFO - allennlp.common.params - dataset_reader.tokenizer.stride = 0
2023-06-19 20:09:14,084 - INFO - allennlp.common.params - dataset_reader.tokenizer.tokenizer_kwargs = None
2023-06-19 20:09:20,318 - INFO - allennlp.common.params - dataset_reader.token_indexers.bert.type = pretrained_transformer
2023-06-19 20:09:20,318 - INFO - allennlp.common.params - dataset_reader.token_indexers.bert.token_min_padding_length = 0
2023-06-19 20:09:20,318 - INFO - allennlp.common.params - dataset_reader.token_indexers.bert.model_name = roberta-base
2023-06-19 20:09:20,318 - INFO - allennlp.common.params - dataset_reader.token_indexers.bert.namespace = tags
2023-06-19 20:09:20,319 - INFO - allennlp.common.params - dataset_reader.token_indexers.bert.max_length = None
2023-06-19 20:09:20,319 - INFO - allennlp.common.params - dataset_reader.token_indexers.bert.tokenizer_kwargs = None
2023-06-19 20:09:20,320 - INFO - allennlp.common.params - dataset_reader.max_tokens = None
2023-06-19 20:09:20,321 - INFO - allennlp.common.params - validation_dataset_reader.type = listwise_pair_ranker_reader
2023-06-19 20:09:20,321 - INFO - allennlp.common.params - validation_dataset_reader.lazy = False
2023-06-19 20:09:20,321 - INFO - allennlp.common.params - validation_dataset_reader.cache_directory = None
2023-06-19 20:09:20,322 - INFO - allennlp.common.params - validation_dataset_reader.max_instances = None
2023-06-19 20:09:20,322 - INFO - allennlp.common.params - validation_dataset_reader.manual_distributed_sharding = False
2023-06-19 20:09:20,322 - INFO - allennlp.common.params - validation_dataset_reader.manual_multi_process_sharding = False
2023-06-19 20:09:20,322 - INFO - allennlp.common.params - validation_dataset_reader.tokenizer.type = pretrained_transformer
2023-06-19 20:09:20,322 - INFO - allennlp.common.params - validation_dataset_reader.tokenizer.model_name = roberta-base
2023-06-19 20:09:20,323 - INFO - allennlp.common.params - validation_dataset_reader.tokenizer.add_special_tokens = False
2023-06-19 20:09:20,323 - INFO - allennlp.common.params - validation_dataset_reader.tokenizer.max_length = None
2023-06-19 20:09:20,323 - INFO - allennlp.common.params - validation_dataset_reader.tokenizer.stride = 0
2023-06-19 20:09:20,323 - INFO - allennlp.common.params - validation_dataset_reader.tokenizer.tokenizer_kwargs = None
2023-06-19 20:09:20,324 - INFO - allennlp.common.params - validation_dataset_reader.token_indexers.bert.type = pretrained_transformer
2023-06-19 20:09:20,324 - INFO - allennlp.common.params - validation_dataset_reader.token_indexers.bert.token_min_padding_length = 0
2023-06-19 20:09:20,325 - INFO - allennlp.common.params - validation_dataset_reader.token_indexers.bert.model_name = roberta-base
2023-06-19 20:09:20,325 - INFO - allennlp.common.params - validation_dataset_reader.token_indexers.bert.namespace = tags
2023-06-19 20:09:20,325 - INFO - allennlp.common.params - validation_dataset_reader.token_indexers.bert.max_length = None
2023-06-19 20:09:20,325 - INFO - allennlp.common.params - validation_dataset_reader.token_indexers.bert.tokenizer_kwargs = None
2023-06-19 20:09:20,326 - INFO - allennlp.common.params - validation_dataset_reader.max_tokens = None
2023-06-19 20:09:20,326 - INFO - allennlp.common.params - type = from_instances
2023-06-19 20:09:20,326 - INFO - allennlp.data.vocabulary - Loading token dictionary from /tmp/tmpwtncs7m0/vocabulary.
2023-06-19 20:09:20,328 - INFO - allennlp.common.params - model.type = listwise_pair_ranker
2023-06-19 20:09:20,329 - INFO - allennlp.common.params - model.regularizer = None
2023-06-19 20:09:20,329 - INFO - allennlp.common.params - model.text_field_embedder.type = basic
2023-06-19 20:09:20,330 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.type = pretrained_transformer
2023-06-19 20:09:20,330 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.model_name = roberta-base
2023-06-19 20:09:20,330 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.max_length = None
2023-06-19 20:09:20,330 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.sub_module = None
2023-06-19 20:09:20,330 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.train_parameters = True
2023-06-19 20:09:20,331 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.last_layer_only = True
2023-06-19 20:09:20,331 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.override_weights_file = None
2023-06-19 20:09:20,331 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.override_weights_strip_prefix = None
2023-06-19 20:09:20,331 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.gradient_checkpointing = None
2023-06-19 20:09:20,331 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.tokenizer_kwargs = None
2023-06-19 20:09:20,331 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.transformer_kwargs = None
2023-06-19 20:09:21,282 - INFO - allennlp.models.archival - removing temporary unarchived model dir at /tmp/tmpwtncs7m0
Traceback (most recent call last):
  File "/home/husainmalwat/anaconda3/envs/GAR/bin/allennlp", line 8, in <module>
    sys.exit(run())
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/__main__.py", line 34, in run
    main(prog="allennlp")
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/commands/__init__.py", line 118, in main
    args.func(args)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/commands/predict.py", line 205, in _predict
    predictor = _get_predictor(args)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/commands/predict.py", line 106, in _get_predictor
    archive = load_archive(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/models/archival.py", line 208, in load_archive
    model = _load_model(config.duplicate(), weights_path, serialization_dir, cuda_device)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/models/archival.py", line 242, in _load_model
    return Model.load(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/models/model.py", line 406, in load
    return model_class._load(config, serialization_dir, weights_file, cuda_device)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/models/model.py", line 304, in _load
    model = Model.from_params(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 595, in from_params
    return retyped_subclass.from_params(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 627, in from_params
    kwargs = create_kwargs(constructor_to_inspect, cls, params, **extras)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 198, in create_kwargs
    constructed_arg = pop_and_construct_arg(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 305, in pop_and_construct_arg
    return construct_arg(class_name, name, popped_params, annotation, default, **extras)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 339, in construct_arg
    return annotation.from_params(params=popped_params, **subextras)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 595, in from_params
    return retyped_subclass.from_params(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 627, in from_params
    kwargs = create_kwargs(constructor_to_inspect, cls, params, **extras)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 198, in create_kwargs
    constructed_arg = pop_and_construct_arg(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 305, in pop_and_construct_arg
    return construct_arg(class_name, name, popped_params, annotation, default, **extras)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 380, in construct_arg
    value_dict[key] = construct_arg(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 339, in construct_arg
    return annotation.from_params(params=popped_params, **subextras)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 595, in from_params
    return retyped_subclass.from_params(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/from_params.py", line 629, in from_params
    return constructor_to_call(**kwargs)  # type: ignore
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/modules/token_embedders/pretrained_transformer_embedder.py", line 74, in __init__
    self.transformer_model = cached_transformers.get(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/allennlp/common/cached_transformers.py", line 84, in get
    transformer = AutoModel.from_pretrained(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/transformers/models/auto/auto_factory.py", line 471, in from_pretrained
    return model_class.from_pretrained(
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2429, in from_pretrained
    state_dict = load_state_dict(resolved_archive_file)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/transformers/modeling_utils.py", line 413, in load_state_dict
    return safe_load_file(checkpoint_file)
  File "/home/husainmalwat/anaconda3/envs/GAR/lib/python3.8/site-packages/safetensors/torch.py", line 261, in load_file
    result[k] = f.get_tensor(k)
AttributeError: module 'torch' has no attribute 'frombuffer'

Can i directly run the evaluation script in my system without training

Would you explain each term in code to run the training script as well as evaluation script:
$ bash train_pipeline.sh <dataset_name> <train_data_path> <dev_data_path> <table_path> <db_dir>

Would you pls verify:
Dataset name: spider
train_data_path: /c/Users/Lenovo/GAR/datasets/train_spider.json
dev_data_path: /c/Users/Lenovo/GAR/datasets/dev.json
table_path: /c/Users/Lenovo/GAR/datasets/spider/tables.json
db_dir: /c/Users/Lenovo/GAR/datasets/spider/database

No database when using the application demo

In http://47.116.100.156:30279/#/chat , when I click "Choose", there is no database in the list.

There is also an error 未查找到可用表

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.