Add lexical/lambda default configuration for docs search

[eskibars]

Idea

Technical documentation in particular tends to have a lot of terms that may have never shown up in the neural net training data. This means that not only having a non-zero value for lambda is important, but that actually it needs to be higher than average typically for the best effect. I recommend we start with a value of 0.1 for now

cc @pwoznic -- we also should actually improve the documentation around lambda. Right now it's bundled into hybrid and it's not clear how to really use it from the docs without tab-switching to the playground

[cjcenizal]

When we experiment with various lambda values, we can try searching for “textless”, “custom dimensions”, and “query” to see how the quality of the results changes.

[eskibars]

@cjcenizal yes, we can test with these, but there are even more extreme examples of things that are even rarer. e.g. searching for lxml or epub should find https://docs.vectara.com/docs/api-reference/indexing-apis/file-upload/file-upload-filetypes, 272725718 should find the MMR reranker. AdminService should find https://docs.vectara.com/docs/api-reference/admin-apis/admin

[rshaxzod044-afk]

{
"id": "prompt_001",
"title": "Vazifa sarlavhasi",
"description": "Qisqacha vazifa ta'rifi (nimani, kim uchun, qanday uslubda).",
"input_example": {
"name": "Ism",
"context": "Qo'shimcha ma'lumot yoki cheklovlar"
},
"instructions": [
"1) Natija 200 belgidan oshmasin",
"2) Rasmiy / norasmiy ohang (tanlang)",
"3) Til: o'zbekcha"
],
"output_format": {
"type": "text",
"structure": ["title", "body", "closing"]
},
"metadata": {
"created_at": "2025-10-01",
"author": "Sizning ismingiz"
}
}