Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed because of a cast error
Error code: DatasetGenerationCastError
Exception: DatasetGenerationCastError
Message: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 3 new columns ({'email', 'timestamp', 'chat_history'})
This happened while the json dataset builder was generating data using
hf://datasets/LohithGummi/chatbot-logs/data/data_567b15e3-f8b3-4c23-a05a-f719f66828db.json (at revision 574919dfaefc53eb73f511874e35886f626f81ca)
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback: Traceback (most recent call last):
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1870, in _prepare_split_single
writer.write_table(table)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 622, in write_table
pa_table = table_cast(pa_table, self._schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2292, in table_cast
return cast_table_to_schema(table, schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2240, in cast_table_to_schema
raise CastError(
datasets.table.CastError: Couldn't cast
customer_id: int64
task: string
details: struct<customer_id: int64, query: string, reason: string, intent: string, feedback: string, rating: int64>
child 0, customer_id: int64
child 1, query: string
child 2, reason: string
child 3, intent: string
child 4, feedback: string
child 5, rating: int64
email: string
chat_history: list<item: struct<role: string, content: string>>
child 0, item: struct<role: string, content: string>
child 0, role: string
child 1, content: string
timestamp: timestamp[s]
to
{'customer_id': Value(dtype='int64', id=None), 'task': Value(dtype='string', id=None), 'details': {'intent': Value(dtype='string', id=None), 'customer_id': Value(dtype='int64', id=None), 'feedback': Value(dtype='string', id=None), 'rating': Value(dtype='int64', id=None)}}
because column names don't match
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1417, in compute_config_parquet_and_info_response
parquet_operations = convert_to_parquet(builder)
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1049, in convert_to_parquet
builder.download_and_prepare(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 924, in download_and_prepare
self._download_and_prepare(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1000, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1741, in _prepare_split
for job_id, done, content in self._prepare_split_single(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1872, in _prepare_split_single
raise DatasetGenerationCastError.from_cast_error(
datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 3 new columns ({'email', 'timestamp', 'chat_history'})
This happened while the json dataset builder was generating data using
hf://datasets/LohithGummi/chatbot-logs/data/data_567b15e3-f8b3-4c23-a05a-f719f66828db.json (at revision 574919dfaefc53eb73f511874e35886f626f81ca)
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
customer_id int64 | task string | details dict | email string | chat_history list | timestamp timestamp[us] |
|---|---|---|---|---|---|
9 | register_feedback | {
"intent": "warranty_claim",
"customer_id": 9,
"feedback": "You are helpful. Not quite 5 but 4 is what I can rate you out of 5.",
"rating": 4
} | null | null | null |
33 | defer_to_human | {
"customer_id": 33,
"query": "I can only hear sound from one side of the headphone.",
"reason": "Customer needs assistance with warranty claim for headphones.",
"intent": "warranty_claim",
"feedback": null,
"rating": null
} | null | null | null |
33 | register_feedback | {
"customer_id": 33,
"query": null,
"reason": null,
"intent": "warranty_claim",
"feedback": "This was helpful.",
"rating": 5
} | null | null | null |
null | null | null | john.miller@gmail.com | [
{
"role": "assistant",
"content": "welcome! I am Raha, how can I help you on this beautiful day?"
},
{
"role": "user",
"content": "Hi raha can you tell me my orders from october and november?"
},
{
"role": "assistant",
"content": "I can provide you with information about your orders ... | 2024-12-11T13:14:15 |
33 | defer_to_human | {
"customer_id": 33,
"query": "Warranty claim for headphones - sound issue",
"reason": "Customer needs to be connected to customer support for warranty claim.",
"intent": "warranty_claim",
"feedback": null,
"rating": null
} | null | null | null |
33 | register_feedback | {
"customer_id": 33,
"query": null,
"reason": null,
"intent": "warranty_claim",
"feedback": "this was quick and helpful.",
"rating": 5
} | null | null | null |
33 | defer_to_human | {
"customer_id": 33,
"query": "I can only hear sound from one side of the headphone.",
"reason": "The customer needs to connect with a support agent for warranty claim assistance.",
"intent": "warranty_claim",
"feedback": null,
"rating": null
} | null | null | null |
33 | register_feedback | {
"customer_id": 33,
"query": null,
"reason": null,
"intent": "warranty_claim",
"feedback": "Customer requested to connect with support agent for warranty claim.",
"rating": 5
} | null | null | null |
null | null | null | john.miller@gmail.com | [
{
"role": "assistant",
"content": "welcome! I am Raha, how can I help you on this beautiful day?"
},
{
"role": "user",
"content": "Hi raha can you tell me my orders from october and november?"
},
{
"role": "assistant",
"content": "I can provide you with information about your orders ... | 2024-12-11T13:13:50 |
9 | defer_to_human | {
"customer_id": 9,
"query": "Customer wants to cancel an order that is in transit and needs to talk to customer support.",
"reason": "The order is already in transit, and the customer wants to cancel it, which requires human intervention.",
"intent": "cancel_order"
} | null | null | null |
33 | register_feedback | {
"intent": "privacy_policy",
"customer_id": 33,
"feedback": "you were not helpful",
"rating": 3
} | null | null | null |
9 | register_feedback | {
"intent": "cancel_order",
"customer_id": 9,
"feedback": "You are a bit annoying but helpful.",
"rating": 4
} | null | null | null |
9 | register_feedback | {
"intent": "warranty_claim",
"customer_id": 9,
"feedback": "Helpful but a bit annoying at times.",
"rating": 4
} | null | null | null |
33 | register_feedback | {
"intent": "policy_query",
"customer_id": 33,
"feedback": "Not helpful with privacy policy query",
"rating": 3
} | null | null | null |
33 | register_feedback | {
"intent": "warranty_claim",
"customer_id": 33,
"feedback": "This was quick and helpful.",
"rating": 5
} | null | null | null |
No dataset card yet
- Downloads last month
- 3