Sync from internal repo (2024-07-10)

.golangci.yml

@@ -20,3 +20,7 @@ linters-settings:
           - github.com/google
           - github.com/stretchr/testify
           - github.com/cenkalti/backoff
+  revive:
+    rules:
+      - name: var-naming
+        disabled: true

assemblyai.go

@@ -12,7 +12,7 @@ import (
 )
 
 const (
-	version              = "1.6.0"
+	version              = "1.7.0"
 	defaultBaseURLScheme = "https"
 	defaultBaseURLHost   = "api.assemblyai.com"
 )

lemur.go

@@ -5,23 +5,44 @@ import (
 )
 
 const (
-	// LeMUR Default is best at complex reasoning. It offers more nuanced
-	// responses and improved contextual comprehension.
+	// Claude 3.5 Sonnet is the most intelligent model to date, outperforming
+	// Claude 3 Opus on a wide range of evaluations, with the speed and cost of
+	// Claude 3 Sonnet.
+	LeMURModelAnthropicClaude3_5_Sonnet LeMURModel = "anthropic/claude-3-5-sonnet"
+
+	// Claude 3 Opus is good at handling complex analysis, longer tasks with
+	// many steps, and higher-order math and coding tasks.
+	LeMURModelAnthropicClaude3_Opus LeMURModel = "anthropic/claude-3-opus"
+
+	// Claude 3 Haiku is the fastest model that can execute lightweight actions.
+	LeMURModelAnthropicClaude3_Haiku LeMURModel = "anthropic/claude-3-haiku"
+
+	// Claude 3 Sonnet is a legacy model with a balanced combination of
+	// performance and speed for efficient, high-throughput tasks.
+	LeMURModelAnthropicClaude3_Sonnet LeMURModel = "anthropic/claude-3-sonnet"
+
+	// Claude 2.1 is a legacy model similar to Claude 2.0. The key difference is
+	// that it minimizes model hallucination and system prompts, has a larger
+	// context window, and performs better in citations.
+	LeMURModelAnthropicClaude2_1 LeMURModel = "anthropic/claude-2-1"
+
+	// Claude 2.0 is a legacy model that has good complex reasoning. It offers
+	// more nuanced responses and improved contextual comprehension.
+	LeMURModelAnthropicClaude2 LeMURModel = "anthropic/claude-2"
+
+	// Legacy model. The same as [LeMURModelAnthropicClaude2].
 	LeMURModelDefault LeMURModel = "default"
 
-	// LeMUR Basic is a simplified model optimized for speed and cost. LeMUR
-	// Basic can complete requests up to 20% faster than Default.
+	// Claude Instant is a legacy model that is optimized for speed and cost.
+	// Claude Instant can complete requests up to 20% faster than Claude 2.0.
+	LeMURModelAnthropicClaudeInstant1_2 LeMURModel = "anthropic/claude-instant-1-2"
+
+	// Legacy model. The same as [LeMURModelAnthropicClaudeInstant1_2].
 	LeMURModelBasic LeMURModel = "basic"
 
-	// Claude 2.1 is similar to Default, with key improvements: it minimizes
-	// model hallucination and system prompts, has a larger context window, and
-	// performs better in citations.
+	// Mistral 7B is an open source model that works well for summarization and
+	// answering questions.
 	LeMURModelAssemblyAIMistral7B LeMURModel = "assemblyai/mistral-7b"
-
-	// LeMUR Mistral 7B is an LLM self-hosted by AssemblyAI. It's the fastest
-	// and cheapest of the LLM options. We recommend it for use cases like basic
-	// summaries and factual Q&A.
-	LeMURModelAnthropicClaude2_1 LeMURModel = "anthropic/claude-2-1"
 )
 
 // LeMURService groups the operations related to LeMUR.

types.go

@@ -136,7 +136,6 @@ type LeMURBaseParams struct {
 	Context interface{} `json:"context,omitempty"`
 
 	// The model that is used for the final prompt after compression is performed.
-	// Defaults to "default".
 	FinalModel LeMURModel `json:"final_model,omitempty"`
 
 	// Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000.
@@ -307,6 +306,11 @@ type RealtimeTemporaryTokenResponse struct {
 // Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.
 type RedactPIIAudioQuality string
 
+// The notification when the redacted audio is ready.
+type RedactedAudioNotification struct {
+	RedactedAudioResponse
+}
+
 type RedactedAudioResponse struct {
 	// The URL of the redacted audio file
 	RedactedAudioURL *string `json:"redacted_audio_url,omitempty"`
@@ -580,13 +584,15 @@ type Transcript struct {
 	// Whether webhook authentication details were provided
 	WebhookAuth *bool `json:"webhook_auth,omitempty"`
 
-	// The header name which should be sent back with webhook calls
+	// The header name to be sent with the transcript completed or failed webhook requests
 	WebhookAuthHeaderName *string `json:"webhook_auth_header_name,omitempty"`
 
-	// The status code we received from your server when delivering your webhook, if a webhook URL was provided
+	// The status code we received from your server when delivering the transcript completed or failed webhook request, if a webhook URL was provided
 	WebhookStatusCode *int64 `json:"webhook_status_code,omitempty"`
 
-	// The URL to which we send webhooks upon transcription completion
+	// The URL to which we send webhook requests.
+	// We sends two different types of webhook requests.
+	// One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.
 	WebhookURL *string `json:"webhook_url,omitempty"`
 
 	// The list of custom vocabulary to boost transcription probability for
@@ -737,13 +743,13 @@ type TranscriptOptionalParams struct {
 	// The list of custom topics
 	Topics []string `json:"topics,omitempty"`
 
-	// The header name which should be sent back with webhook calls
+	// The header name to be sent with the transcript completed or failed webhook requests
 	WebhookAuthHeaderName *string `json:"webhook_auth_header_name,omitempty"`
 
-	// Specify a header name and value to send back with a webhook call for added security
+	// The header value to send back with the transcript completed or failed webhook requests for added security
 	WebhookAuthHeaderValue *string `json:"webhook_auth_header_value,omitempty"`
 
-	// The URL to which AssemblyAI send webhooks upon transcription completion
+	// The URL to which we send webhook requests. We sends two different types of webhook requests. One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.
 	WebhookURL *string `json:"webhook_url,omitempty"`
 
 	// The list of custom vocabulary to boost transcription probability for
@@ -823,6 +829,9 @@ type TranscriptUtterance struct {
 	Words []TranscriptWord `json:"words,omitempty"`
 }
 
+// The notifications sent to the webhook URL.
+type TranscriptWebhookNotification struct{}
+
 type TranscriptWord struct {
 	Confidence *float64 `json:"confidence,omitempty"`