curl --request POST \
--url https://platform-backend.getalchemystai.com/api/v1/context/search/steer \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"query": "What did the customer ask about pricing for the Scale plan?",
"similarity_threshold": 0.8,
"minimum_similarity_threshold": 0.5,
"scope": "internal"
}
'{
"answer": "<string>",
"model": "poolside/laguna-m.1",
"usage": {
"inputTokens": 123,
"outputTokens": 123,
"totalTokens": 123
},
"context": "<string>"
}{
"response": "Fields missing. Detailed error: {error details}"
}{
"success": false,
"error": "Error details",
"message": "Invalid job id",
"status": 400,
"statusText": "<string>"
}{
"success": false,
"error": "Error details",
"message": "Invalid job id",
"status": 400,
"statusText": "<string>"
}{
"success": false,
"error": "Error details",
"message": "Invalid job id",
"status": 400,
"statusText": "<string>"
}{
"response": "error"
}Search and summarize context based on steering prompt
This endpoint performs a context search using the context processor, joins all
matching context chunks into a single string, then sends that joined context
along with the user’s query to an LLM via OpenRouter (model
poolside/laguna-m.1 pinned to the poolside/fp4 provider) to produce a
natural-language answer grounded in the retrieved context.
By default the response only includes the generated answer. Pass
?context=true to also receive the joined context string that was used to
ground the answer.
curl --request POST \
--url https://platform-backend.getalchemystai.com/api/v1/context/search/steer \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"query": "What did the customer ask about pricing for the Scale plan?",
"similarity_threshold": 0.8,
"minimum_similarity_threshold": 0.5,
"scope": "internal"
}
'{
"answer": "<string>",
"model": "poolside/laguna-m.1",
"usage": {
"inputTokens": 123,
"outputTokens": 123,
"totalTokens": 123
},
"context": "<string>"
}{
"response": "Fields missing. Detailed error: {error details}"
}{
"success": false,
"error": "Error details",
"message": "Invalid job id",
"status": 400,
"statusText": "<string>"
}{
"success": false,
"error": "Error details",
"message": "Invalid job id",
"status": 400,
"statusText": "<string>"
}{
"success": false,
"error": "Error details",
"message": "Invalid job id",
"status": 400,
"statusText": "<string>"
}{
"response": "error"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Query Parameters
Controls the search mode:
- mode=fast -> prioritizes speed over completeness.
- mode=standard -> performs a comprehensive search (default if omitted).
fast, standard When set to true, the response includes the joined context string used
to ground the answer. Defaults to false (only answer, model, and
usage are returned).
Body
The search query and question to be answered using retrieved context
"What did the customer ask about pricing for the Scale plan?"
Maximum similarity threshold (must be >= minimum_similarity_threshold)
0 <= x <= 10.8
Minimum similarity threshold
0 <= x <= 10.5
The ID of the user making the request
"user123"
The steering prompt for the query - basically the way in which you want to get your answer as.
"Return only the basic details of the person in a structured JSON schema with the fields \"name\", \"status\", \"location\""
Search scope
internal, external Additional metadata for the search
Response
Successfully retrieved context and generated an answer.
The LLM-generated answer based on the retrieved context
The model used to generate the answer (currently poolside/laguna-m.1)
"poolside/laguna-m.1"
Token usage information from the LLM
Show child attributes
Show child attributes
The joined context retrieved from the context processor.
Only present when the request was made with ?context=true.