Vietnamese web search
Tiếng Việtlang=viLatin script with extensive diacritics; retrieval is diacritic-aware.
Example
# Vietnamese sources only
curl -H "x-api-key: $UNLOB_API_KEY" \
"https://api.unlob.com/search?q=ch%C3%ADnh%20s%C3%A1ch%20kh%C3%AD%20h%E1%BA%ADu&lang=vi&limit=10"
# The same meaning, sources in any language
curl -H "x-api-key: $UNLOB_API_KEY" \
"https://api.unlob.com/search?q=ch%C3%ADnh%20s%C3%A1ch%20kh%C3%AD%20h%E1%BA%ADu&mode=semantic&limit=10"How multilingual retrieval works here
The conventional approach runs a separate index per language and translates queries between them, which multiplies infrastructure and loses meaning at every boundary. A single multilingual embedder places all 101 supported languages in one shared space, so texts with the same meaning land near each other regardless of the language they are written in.
The practical consequence is that a query in English can retrieve a Vietnamese passage directly, and vice versa — with no translation step, no per-language index, and no additional resident memory. Only semantic and hybrid modes do this; keyword mode matches tokens, and tokens are monolingual.
Common questions
How do I search Vietnamese web content?
Set lang=vi on any search request. You can also leave it unset — the embedding space holds 101 languages at once, so a query in any language retrieves relevant Vietnamese passages directly.
Do I need to translate my query into Vietnamese?
No. Semantic and hybrid modes cross languages natively. Translating would search for the translation rather than the meaning, which is usually worse. Use lang only when the results must be readable to a Vietnamese-speaking user.
Does keyword mode work for Vietnamese?
Within Vietnamese it does. What keyword mode cannot do is cross languages — token matching is monolingual by construction. Use semantic or hybrid mode if you want Vietnamese sources from a query in another language.
Search Vietnamese sources
10,000 free requests a month, no card. All 101 languages are available on every plan.