""" At the command line, only need to run once to install the package via pip: $ pip install google-generativeai """ import google.generativeai as genai genai.configure(api_key="YOUR API KEY") defaults = { 'model': 'models/text-bison-001', 'temperature': 0.7, 'candidate_count': 1, 'top_k': 40, 'top_p': 0.95, 'max_output_tokens': 1024, } prompt = """The student was so excited for the big science fair tomorrow, but they had forgotten to do their project. They had been so busy with soccer practice and their other extracurricular activities that they had completely lost track of time. They knew that they would have to stay up late to finish their project, but they were determined to do it. They worked for hours, and finally, just before midnight, they were finished. They were so tired, but they were also relieved. They knew that they had done their best, and they were confident that they would do well in the science fair. Please turn this paragraph into a bulleted list.""" response = genai.generate_text( **defaults, prompt=prompt ) print(response.result)

const { TextServiceClient } = require("@google-ai/generativelanguage"); const { GoogleAuth } = require("google-auth-library"); const MODEL_NAME = "models/text-bison-001"; const API_KEY = "YOUR API KEY"; const client = new TextServiceClient({ authClient: new GoogleAuth().fromAPIKey(API_KEY), }); const promptString = "The student was so excited for the big science fair tomorrow, but they had forgotten to do their project. They had been so busy with soccer practice and their other extracurricular activities that they had completely lost track of time. They knew that they would have to stay up late to finish their project, but they were determined to do it. They worked for hours, and finally, just before midnight, they were finished. They were so tired, but they were also relieved. They knew that they had done their best, and they were confident that they would do well in the science fair.\n\nPlease turn this paragraph into a bulleted list."; client.generateText({ // required, which model to use to generate the result model: MODEL_NAME, // optional, 0.0 always uses the highest-probability result temperature: 0.7, // optional, how many candidate results to generate candidateCount: 1, // optional, number of most probable tokens to consider for generation top_k: 40, // optional, for nucleus sampling decoding strategy top_p: 0.95, // optional, maximum number of output tokens to generate max_output_tokens: 1024, prompt: { text: promptString, }, }).then(result => { console.log(JSON.stringify(result, null, 2)); });