Class: AssemblyAI::LemurClient

Inherits:
Object
  • Object
show all
Defined in:
lib/assemblyai/lemur/client.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(request_client:) ⇒ AssemblyAI::LemurClient

Parameters:



22
23
24
 
# File 'lib/assemblyai/lemur/client.rb', line 22

def initialize(request_client:)
  @request_client = request_client
end

Instance Attribute Details

#request_client ⇒ AssemblyAI::RequestClient (readonly)

Returns:



18
19
20
 
# File 'lib/assemblyai/lemur/client.rb', line 18

def request_client
  @request_client
end

Instance Method Details

#action_items(transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil, temperature: nil, answer_format: nil, request_options: nil) ⇒ AssemblyAI::Lemur::LemurActionItemsResponse

Use LeMUR to generate a list of action items from a transcript

Examples:

api = AssemblyAI::Client.new(
  environment: AssemblyAI::Environment::DEFAULT,
  base_url: "https://api.example.com",
  api_key: "YOUR_API_KEY"
)
api.lemur.action_items(answer_format: "Bullet Points")

Parameters:

  • transcript_ids (Array<String>) (defaults to: nil) —

    A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR.

  • input_text (String) (defaults to: nil) —

    Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR.

  • context (String, Hash{String => Object}) (defaults to: nil) —

    Context to provide the model. This can be a string or a free-form JSON value.

  • final_model (AssemblyAI::Lemur::LemurModel) (defaults to: nil) —

    The model that is used for the final prompt after compression is performed.

  • max_output_size (Integer) (defaults to: nil) —

    Max output size in tokens, up to 4000

  • temperature (Float) (defaults to: nil) —

    The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive.

  • answer_format (String) (defaults to: nil) —

    How you want the action items to be returned. This can be any text. Defaults to “Bullet Points”.

  • request_options (AssemblyAI::RequestOptions) (defaults to: nil)

Returns:



203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
 
# File 'lib/assemblyai/lemur/client.rb', line 203

def action_items(transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil,
                 temperature: nil, answer_format: nil, request_options: nil)
  response = @request_client.conn.post do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.body = {
      **(request_options&.additional_body_parameters || {}),
      transcript_ids: transcript_ids,
      input_text: input_text,
      context: context,
      final_model: final_model,
      max_output_size: max_output_size,
      temperature: temperature,
      answer_format: answer_format
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/lemur/v3/generate/action-items"
  end
  AssemblyAI::Lemur::LemurActionItemsResponse.from_json(json_object: response.body)
end

#get_response(request_id:, request_options: nil) ⇒ AssemblyAI::Lemur::LemurStringResponse, AssemblyAI::Lemur::LemurQuestionAnswerResponse

Retrieve a LeMUR response that was previously generated.

Examples:

api = AssemblyAI::Client.new(
  environment: AssemblyAI::Environment::DEFAULT,
  base_url: "https://api.example.com",
  api_key: "YOUR_API_KEY"
)
api.lemur.get_response(request_id: "request_id")

Parameters:

  • request_id (String) —

    The ID of the LeMUR request you previously made. This would be found in the response of the original request.

  • request_options (AssemblyAI::RequestOptions) (defaults to: nil)

Returns:



237
238
239
240
241
242
243
244
245
 
# File 'lib/assemblyai/lemur/client.rb', line 237

def get_response(request_id:, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/lemur/v3/#{request_id}"
  end
  AssemblyAI::Lemur::LemurResponse.from_json(json_object: response.body)
end

#purge_request_data(request_id:, request_options: nil) ⇒ AssemblyAI::Lemur::PurgeLemurRequestDataResponse

Delete the data for a previously submitted LeMUR request.

The LLM response data, as well as any context provided in the original request
will be removed.

Examples:

api = AssemblyAI::Client.new(
  environment: AssemblyAI::Environment::DEFAULT,
  base_url: "https://api.example.com",
  api_key: "YOUR_API_KEY"
)
api.lemur.purge_request_data(request_id: "request_id")

Parameters:

  • request_id (String) —

    The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request.

  • request_options (AssemblyAI::RequestOptions) (defaults to: nil)

Returns:



262
263
264
265
266
267
268
269
270
 
# File 'lib/assemblyai/lemur/client.rb', line 262

def purge_request_data(request_id:, request_options: nil)
  response = @request_client.conn.delete do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/lemur/v3/#{request_id}"
  end
  AssemblyAI::Lemur::PurgeLemurRequestDataResponse.from_json(json_object: response.body)
end

#question_answer(questions:, transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil, temperature: nil, request_options: nil) ⇒ AssemblyAI::Lemur::LemurQuestionAnswerResponse

Question & Answer allows you to ask free-form questions about a single

transcript or a group of transcripts.
The questions can be any whose answers you find useful, such as judging whether
a caller is likely to become a customer or whether all items on a meeting's
agenda were covered.

Examples:

api = AssemblyAI::Client.new(
  environment: AssemblyAI::Environment::DEFAULT,
  base_url: "https://api.example.com",
  api_key: "YOUR_API_KEY"
)
api.lemur.question_answer(questions: [{ question: "Where are there wildfires?", answer_format: "List of countries in ISO 3166-1 alpha-2 format", answer_options: ["US", "CA"] }, { question: "Is global warming affecting wildfires?", answer_options: ["yes", "no"] }])

Parameters:

  • transcript_ids (Array<String>) (defaults to: nil) —

    A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR.

  • input_text (String) (defaults to: nil) —

    Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR.

  • context (String, Hash{String => Object}) (defaults to: nil) —

    Context to provide the model. This can be a string or a free-form JSON value.

  • final_model (AssemblyAI::Lemur::LemurModel) (defaults to: nil) —

    The model that is used for the final prompt after compression is performed.

  • max_output_size (Integer) (defaults to: nil) —

    Max output size in tokens, up to 4000

  • temperature (Float) (defaults to: nil) —

    The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive.

  • questions (Array<Hash>) —

    A list of questions to askRequest of type Array<AssemblyAI::Lemur::LemurQuestion>, as a Hash

    • :question (String)

    • :context (Hash)

    • :answer_format (String)

    • :answer_options (Array<String>)

  • request_options (AssemblyAI::RequestOptions) (defaults to: nil)

Returns:



156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
# File 'lib/assemblyai/lemur/client.rb', line 156

def question_answer(questions:, transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil,
                    temperature: nil, request_options: nil)
  response = @request_client.conn.post do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.body = {
      **(request_options&.additional_body_parameters || {}),
      transcript_ids: transcript_ids,
      input_text: input_text,
      context: context,
      final_model: final_model,
      max_output_size: max_output_size,
      temperature: temperature,
      questions: questions
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/lemur/v3/generate/question-answer"
  end
  AssemblyAI::Lemur::LemurQuestionAnswerResponse.from_json(json_object: response.body)
end

#summary(transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil, temperature: nil, answer_format: nil, request_options: nil) ⇒ AssemblyAI::Lemur::LemurSummaryResponse

Custom Summary allows you to distill a piece of audio into a few impactful

sentences.
You can give the model context to obtain more targeted results while outputting
the results in a variety of formats described in human language.

Examples:

api = AssemblyAI::Client.new(
  environment: AssemblyAI::Environment::DEFAULT,
  base_url: "https://api.example.com",
  api_key: "YOUR_API_KEY"
)
api.lemur.summary

Parameters:

  • transcript_ids (Array<String>) (defaults to: nil) —

    A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR.

  • input_text (String) (defaults to: nil) —

    Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR.

  • context (String, Hash{String => Object}) (defaults to: nil) —

    Context to provide the model. This can be a string or a free-form JSON value.

  • final_model (AssemblyAI::Lemur::LemurModel) (defaults to: nil) —

    The model that is used for the final prompt after compression is performed.

  • max_output_size (Integer) (defaults to: nil) —

    Max output size in tokens, up to 4000

  • temperature (Float) (defaults to: nil) —

    The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive.

  • answer_format (String) (defaults to: nil) —

    How you want the summary to be returned. This can be any text. Examples: “TLDR”, “bullet points”

  • request_options (AssemblyAI::RequestOptions) (defaults to: nil)

Returns:



102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
 
# File 'lib/assemblyai/lemur/client.rb', line 102

def summary(transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil,
            temperature: nil, answer_format: nil, request_options: nil)
  response = @request_client.conn.post do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.body = {
      **(request_options&.additional_body_parameters || {}),
      transcript_ids: transcript_ids,
      input_text: input_text,
      context: context,
      final_model: final_model,
      max_output_size: max_output_size,
      temperature: temperature,
      answer_format: answer_format
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/lemur/v3/generate/summary"
  end
  AssemblyAI::Lemur::LemurSummaryResponse.from_json(json_object: response.body)
end

#task(prompt:, transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil, temperature: nil, request_options: nil) ⇒ AssemblyAI::Lemur::LemurTaskResponse

Use the LeMUR task endpoint to input your own LLM prompt.

Examples:

api = AssemblyAI::Client.new(
  environment: AssemblyAI::Environment::DEFAULT,
  base_url: "https://api.example.com",
  api_key: "YOUR_API_KEY"
)
api.lemur.task(prompt: "List all the locations affected by wildfires.")

Parameters:

  • transcript_ids (Array<String>) (defaults to: nil) —

    A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR.

  • input_text (String) (defaults to: nil) —

    Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR.

  • context (String, Hash{String => Object}) (defaults to: nil) —

    Context to provide the model. This can be a string or a free-form JSON value.

  • final_model (AssemblyAI::Lemur::LemurModel) (defaults to: nil) —

    The model that is used for the final prompt after compression is performed.

  • max_output_size (Integer) (defaults to: nil) —

    Max output size in tokens, up to 4000

  • temperature (Float) (defaults to: nil) —

    The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive.

  • prompt (String) —

    Your text to prompt the model to produce a desired output, including any context you want to pass into the model.

  • request_options (AssemblyAI::RequestOptions) (defaults to: nil)

Returns:



52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/assemblyai/lemur/client.rb', line 52

def task(prompt:, transcript_ids: nil, input_text: nil, context: nil, final_model: nil, max_output_size: nil,
         temperature: nil, request_options: nil)
  response = @request_client.conn.post do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.body = {
      **(request_options&.additional_body_parameters || {}),
      transcript_ids: transcript_ids,
      input_text: input_text,
      context: context,
      final_model: final_model,
      max_output_size: max_output_size,
      temperature: temperature,
      prompt: prompt
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/lemur/v3/generate/task"
  end
  AssemblyAI::Lemur::LemurTaskResponse.from_json(json_object: response.body)
end