jeff.retrieval.query-routev1.4.0
Search source selection
Selects which document collection, database or tool should handle a query from a menu of sources. Can also indicate that several sources or no source are needed.
Example
Context
- menu
- - product_manuals: installation and user manuals for every heat pump and boiler the company sells - warranty_terms: the warranty terms for each product, by model and installation date - customer_orders: each customer's orders, installations and visits (a database) - pricing: current prices and offers
Input
How long is the warranty on an Aster 2 heat pump installed after March 2026?
Labels (the options)
- product_manuals
- Installation and user manuals for every heat pump and boiler the company sells
- warranty_terms
- The warranty terms for each product, by model and installation date
- customer_orders
- Each customer's orders, installations and visits (a database)
- pricing
- Current prices and offers
- none
- No source on the menu holds what the query needs, or no lookup is needed
- several
- The answer needs facts from two or more of these sources
- Answer (JSON)
- value warranty_terms, confidence 0.981
- Top options
- warranty_terms 0.981
- product_manuals 0.009
- customer_orders 0.005
A question about a product's warranty goes to the warranty_terms source.
import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client: decide = client.function("jeff.retrieval.query-route.source", context={ "menu": "- product_manuals: installation and user manuals for every heat pump and boiler the company sells\n- warranty_terms: the warranty terms for each product, by model and installation date\n- customer_orders: each customer's orders, installations and visits (a database)\n- pricing: current prices and offers", }, labels={ "product_manuals": "Installation and user manuals for every heat pump and boiler the company sells", "warranty_terms": "The warranty terms for each product, by model and installation date", "customer_orders": "Each customer's orders, installations and visits (a database)", "pricing": "Current prices and offers", "none": "No source on the menu holds what the query needs, or no lookup is needed", "several": "The answer needs facts from two or more of these sources", }) decision = decide("How long is the warranty on an Aster 2 heat pump installed after March 2026?") print(decision.value, decision.confidence)
More examples
When is my engineer coming?answer customer_orders · confidence 0.793
Context
- menu
- - product_manuals: installation and user manuals for every heat pump and boiler the company sells - warranty_terms: the warranty terms for each product, by model and installation date - customer_orders: each customer's orders, installations and visits (a database) - pricing: current prices and offers
Input
When is the engineer booked to come to my house, order FH-20871?
Labels (the options)
- product_manuals
- Installation and user manuals for every heat pump and boiler the company sells
- warranty_terms
- The warranty terms for each product, by model and installation date
- customer_orders
- Each customer's orders, installations and visits (a database)
- pricing
- Current prices and offers
- none
- No source on the menu holds what the query needs, or no lookup is needed
- several
- The answer needs facts from two or more of these sources
- Answer (JSON)
- value customer_orders, confidence 0.793
- Top options
- customer_orders 0.793
- none 0.198
- several 0.004
A question about when the engineer is booked for one customer's order goes to
customer_orders.import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client: decide = client.function("jeff.retrieval.query-route.source", context={ "menu": "- product_manuals: installation and user manuals for every heat pump and boiler the company sells\n- warranty_terms: the warranty terms for each product, by model and installation date\n- customer_orders: each customer's orders, installations and visits (a database)\n- pricing: current prices and offers", }, labels={ "product_manuals": "Installation and user manuals for every heat pump and boiler the company sells", "warranty_terms": "The warranty terms for each product, by model and installation date", "customer_orders": "Each customer's orders, installations and visits (a database)", "pricing": "Current prices and offers", "none": "No source on the menu holds what the query needs, or no lookup is needed", "several": "The answer needs facts from two or more of these sources", }) decision = decide("When is the engineer booked to come to my house, order FH-20871?") print(decision.value, decision.confidence)
Error code in the installation manualanswer product_manuals · confidence 0.88
Context
- menu
- - product_manuals: installation and user manuals for every heat pump and boiler the company sells - warranty_terms: the warranty terms for each product, by model and installation date - customer_orders: each customer's orders, installations and visits (a database) - pricing: current prices and offers
Input
What does error code E4 on the Aster 2 heat pump mean, and what does the installation manual say to do about it?
Labels (the options)
- product_manuals
- Installation and user manuals for every heat pump and boiler the company sells
- warranty_terms
- The warranty terms for each product, by model and installation date
- customer_orders
- Each customer's orders, installations and visits (a database)
- pricing
- Current prices and offers
- none
- No source on the menu holds what the query needs, or no lookup is needed
- several
- The answer needs facts from two or more of these sources
- Answer (JSON)
- value product_manuals, confidence 0.88
- Top options
- product_manuals 0.88
- several 0.08
- none 0.032
A question about an error code and what the installation manual says goes to
product_manuals.import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client: decide = client.function("jeff.retrieval.query-route.source", context={ "menu": "- product_manuals: installation and user manuals for every heat pump and boiler the company sells\n- warranty_terms: the warranty terms for each product, by model and installation date\n- customer_orders: each customer's orders, installations and visits (a database)\n- pricing: current prices and offers", }, labels={ "product_manuals": "Installation and user manuals for every heat pump and boiler the company sells", "warranty_terms": "The warranty terms for each product, by model and installation date", "customer_orders": "Each customer's orders, installations and visits (a database)", "pricing": "Current prices and offers", "none": "No source on the menu holds what the query needs, or no lookup is needed", "several": "The answer needs facts from two or more of these sources", }) decision = decide("What does error code E4 on the Aster 2 heat pump mean, and what does the installation manual say to do about it?") print(decision.value, decision.confidence)
Price of a new boileranswer pricing · confidence 0.995
Context
- menu
- - product_manuals: installation and user manuals for every heat pump and boiler the company sells - warranty_terms: the warranty terms for each product, by model and installation date - customer_orders: each customer's orders, installations and visits (a database) - pricing: current prices and offers
Input
How much is the Corrin 30 combi boiler at the moment, and is there an offer on?
Labels (the options)
- product_manuals
- Installation and user manuals for every heat pump and boiler the company sells
- warranty_terms
- The warranty terms for each product, by model and installation date
- customer_orders
- Each customer's orders, installations and visits (a database)
- pricing
- Current prices and offers
- none
- No source on the menu holds what the query needs, or no lookup is needed
- several
- The answer needs facts from two or more of these sources
- Answer (JSON)
- value pricing, confidence 0.995
- Top options
- pricing 0.995
- customer_orders 0.002
- several 0.001
A question about a boiler's current price and offers goes to
pricing.import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client: decide = client.function("jeff.retrieval.query-route.source", context={ "menu": "- product_manuals: installation and user manuals for every heat pump and boiler the company sells\n- warranty_terms: the warranty terms for each product, by model and installation date\n- customer_orders: each customer's orders, installations and visits (a database)\n- pricing: current prices and offers", }, labels={ "product_manuals": "Installation and user manuals for every heat pump and boiler the company sells", "warranty_terms": "The warranty terms for each product, by model and installation date", "customer_orders": "Each customer's orders, installations and visits (a database)", "pricing": "Current prices and offers", "none": "No source on the menu holds what the query needs, or no lookup is needed", "several": "The answer needs facts from two or more of these sources", }) decision = decide("How much is the Corrin 30 combi boiler at the moment, and is there an offer on?") print(decision.value, decision.confidence)
Weather forecast for the weekendanswer none · confidence 0.928
Context
- menu
- - product_manuals: installation and user manuals for every heat pump and boiler the company sells - warranty_terms: the warranty terms for each product, by model and installation date - customer_orders: each customer's orders, installations and visits (a database) - pricing: current prices and offers
Input
Will it rain in Manchester on Saturday?
Labels (the options)
- product_manuals
- Installation and user manuals for every heat pump and boiler the company sells
- warranty_terms
- The warranty terms for each product, by model and installation date
- customer_orders
- Each customer's orders, installations and visits (a database)
- pricing
- Current prices and offers
- none
- No source on the menu holds what the query needs, or no lookup is needed
- several
- The answer needs facts from two or more of these sources
- Answer (JSON)
- value none, confidence 0.928
- Top options
- none 0.928
- pricing 0.062
- customer_orders 0.005
A weather question is not something any source on the menu holds, so the answer is
none.import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client: decide = client.function("jeff.retrieval.query-route.source", context={ "menu": "- product_manuals: installation and user manuals for every heat pump and boiler the company sells\n- warranty_terms: the warranty terms for each product, by model and installation date\n- customer_orders: each customer's orders, installations and visits (a database)\n- pricing: current prices and offers", }, labels={ "product_manuals": "Installation and user manuals for every heat pump and boiler the company sells", "warranty_terms": "The warranty terms for each product, by model and installation date", "customer_orders": "Each customer's orders, installations and visits (a database)", "pricing": "Current prices and offers", "none": "No source on the menu holds what the query needs, or no lookup is needed", "several": "The answer needs facts from two or more of these sources", }) decision = decide("Will it rain in Manchester on Saturday?") print(decision.value, decision.confidence)
Use when
- Your assistant can search several sources and needs to choose where to look.
Avoid when
- You need to rewrite the query for a source; this adapter only selects the source.
Context and input
| Field | Kind | Description |
|---|---|---|
query | input | The user's query. |
menu | context | The sources a query can be sent to (document collections, indexes, databases, tools), written as tool definitions with names and descriptions. |
Functions
| Key | Interface | Instructions | Labels |
|---|---|---|---|
| source | route | Which of the sources on the menu should this query be sent to? Each source (a document collection, index, database or tool) is described on the menu. Choose the one source whose contents answer the query; judge by what each source holds, not by words the query shares with a source's name. none: no source on the menu holds what the query needs (it belongs to a source that is not listed), or the message needs no lookup at all (a greeting, thanks, or a request to reword text). several: answering needs facts from two or more different sources on the menu, because no single source holds all of them. | from the caller |
How it was measured
Test accuracy: the share of test rows whose top answer was right.
- 99.3% on the in-house test (2,000 rows). in-house: same generator as the training data
- 98.9% on a second in-house test of unseen cases (2,000 rows). in-house: same generator as the training data
When confident
From the calibration set: at or above the threshold confidence, how often the answer is right, and how often the adapter is that confident. Below it, escalate.
| Function | Right when confident | Confident on | Threshold | Calibration rows |
|---|---|---|---|---|
| source | 98.7% | 100.0% | 0.34 | 2,000 |
Base: Jeff v1.4. Adapter trained: 25 October 2026.
Base
jeff-base v1.4
Call it
jeff.retrieval.query-route.source, with placeholders for its input and context.
import os import jeff with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client: decide = client.function("jeff.retrieval.query-route.source", context={ "menu": "<menu>", }) decision = decide("<query>") print(decision.value, decision.confidence)
Download
Weights: mstrasser/jeff-adapter-query-route (v1.4)
Licence: Apache-2.0