WatsonXClient

org.llm4s.llmconnect.provider.WatsonXClient
See theWatsonXClient companion class
object WatsonXClient

Attributes

Companion
class
Graph
Supertypes
class Object
trait Matchable
class Any
Self type

Members list

Value members

Concrete methods

Constructs a WatsonXClient, wrapping any construction-time exception in a Left.

Constructs a WatsonXClient, wrapping any construction-time exception in a Left.

Value parameters

config

model, credentials, project or space and endpoints.

exchangeLogging

optional provider exchange logging.

metrics

receives per-call latency and token-usage events.

Attributes

Concrete fields

val ErrorStopReasons: Set[String]

The stop_reason values that mean a generation did not finish: error, cancelled and time_limit. Compared after normalizeStopReason, so any case matches. Anything else is a normal stop: eos_token, stop_sequence, max_tokens and token_limit (length stops, as for other providers) and any value IBM adds later.

The stop_reason values that mean a generation did not finish: error, cancelled and time_limit. Compared after normalizeStopReason, so any case matches. Anything else is a normal stop: eos_token, stop_sequence, max_tokens and token_limit (length stops, as for other providers) and any value IBM adds later.

Attributes

val StopSequences: Seq[String]

Strings that stop generation, so a base or instruct model cannot write the next turn of the flattened prompt itself: the role markers [USER]:, [SYSTEM]: and [TOOL_RESULT: at the start of a line. Sent as parameters.stop_sequences (unverified against IBM's reference; the API documents an array of at most six strings).

Strings that stop generation, so a base or instruct model cannot write the next turn of the flattened prompt itself: the role markers [USER]:, [SYSTEM]: and [TOOL_RESULT: at the start of a line. Sent as parameters.stop_sequences (unverified against IBM's reference; the API documents an array of at most six strings).

Attributes