Early accessGnani Evon v3.5 is now available as an API to early access registrants.
Route customer messages to the right queue without writing rules for every language. Send the message with a JSON schema, and get back the intent, the language and a short English summary.
When to use this
- Messages arrive in Hindi, Kannada, English or a mix, and you route them to teams or flows.
- You need a fixed set of labels that your code can switch on.
- You want an English summary for agents who do not read the customer’s language.
Classify one message
content (illustrative):
Classify a batch of messages
Classify a batch of messages
Send one request per message. On Free and Pay-as-you-go plans only one request can run at a time, so the loop sends them one after another and waits a second between them. OpenAI’s SDKs retry The output looks something like this:
429 responses for you.Python (OpenAI SDK)
How it works
- The
systemmessage, in English, names the labels and says what each field means. The customer’s message can be in another language. response_formatwithjson_schemamakes the reply a JSON object with exactly the keys you listed.reasoning_effort: "none"andtemperature: 0make the call fast and repeatable. Classification does not need thinking.- Your code checks
finish_reason, parsescontent, and falls back tootherfor an unexpected label.
Options
Gotchas
- Check
finish_reasonbefore parsing. Withlength, the JSON is cut off. - Validate the values, not just the keys. Map anything outside your list to
other. - Romanised and mixed-language text (“Mera parcel abhi tak nahi aaya”) is common in chat. Test with your own samples, and check the
languagefield before you route on it. - Batches count toward your limits. Each message is one request and uses your daily token quota. Keep the
systemmessage short: it is sent with every request.
Related
JSON output
json_object and json_schema in detail.Indian languages
Working with Indian scripts and mixed-language text.
Customer support bot
Answer the customer once you know the intent.
Limits
Request rates and the daily token quota.