wit chooses the entity with low confidence
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.5k
- Forks
- 353
- PR merge metrics
- No merged PRs in 30d
Description
I have a bot to get mobile number of user and send OTP, in webchat everything is fine but in skype, the skype gives the url to every mobile number which creates exception for the bot, but still it gets 3 entities, out which one is with conifdence 1 and have the correct/required values
{u'otp_value': [{u'suggested': True, u'confidence': 0.36571505592569503, u'type': u'value', u'value': u'>'}], u'contact_number': [{u'confidence': 1, u'type': u'value', u'value': u'+917809899999'}, {u'confidence': 1, u'type': u'value', u'value': u'+917809899999'}]}
but by default the wit processes the first entity and not the entity with highest confidence. How can i integrate this logic. I am using run_actions() to process the text received from the user
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the run_actions() entry point and trace how the returned entities are selected for processing. Reproduce the Skype payload shown in the issue and determine whether choosing the highest-confidence entity is configurable or requires a library change. Done means the behavior is clarified and, if appropriate, covered by a focused test or documented usage guidance.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100