Giter Club home page Giter Club logo

gemini-ai's Issues

Ways to pass temperature or max tokens?

Thanks for this project!

Is there a way to pass temperature or max tokens? Ideally I'd tell it to respond and keep it under X length - I can sometimes get it to work passing that in the request (under 200 characters) but sometimes you'll ask it something and it'll reply with ridiculously long answer.

I tried looking at the rest API but can't make head or tails of it - any tips on finding useful docs for google apis? They all seem to be automatic dumps without any actual info. https://cloud.google.com/vertex-ai/docs/reference/rest

Support for system instructions

Does it support giving system instructions while creating the model?

Example in python:

model = genai.GenerativeModel(model_name="gemini-1.5-pro-latest",
                              generation_config=generation_config,
                              system_instruction=system_instruction,
                              safety_settings=safety_settings)

Using Safety Settings

Hi, @gbaptista.

Is it possible to use Safety Settings in the gem? I'm attempting to analyze certain content, but the process concludes due to a high HARM_CATEGORY_DANGEROUS_CONTENT reason. According to the Gemini API documentation, Safety Settings can be applied in this context, but I've been unsuccessful in make it work with the gem. Specifically, I'm using gemini-pro-vision to scan an image of a pesticide.

safetySettings: {
HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
}

I will appreciate your help with this. Thanks.

JFYI - Your code also works with Ultra and Embeddings!

I've tried to substitute 'gemini-pro' with other strings provided by the Gemini Vertex AI playground code, and JFYI they both works:

GeminiModel = "gemini-1.0-pro-001" # This works as 'gemini-pro'
GeminiModel = "gemini-1.0-ultra-001" # this also works! Yuppie!

JFYI - Looking fwd to speaking to you in person (Laurencio is arranging a chat).

Riccardo

Streaming is not working

Hey @gbaptista,
Good job on the integration with Gemini models! I was trying this gem out for a project of mine and I couldn't get streaming to actually work. I tried connecting to both vertex-ai-api and generative-language-api. As well as passing server_sent_events: true option to both client initializer and stream_generate_content method.

Initializing a client

client = Gemini.new(
  credentials: {
    service: 'vertex-ai-api',
    file_path: 'google-credentials.json',
    region: 'us-east4'
  },
  options: { model: 'gemini-pro', server_sent_events: true }
)

Running a request

client.stream_generate_content({ contents: { role: 'user', parts: { text: 'generate a short story...' } } }, server_sent_events: true) do |event|
  puts event
end

It just spits out all the puts and return results all at once. I thought there was some output buffering happening so that it outputs everything together, but the block gets called as data comes in, so I tried this:

client.stream_generate_content({ contents: { role: 'user', parts: { text: 'generate a short story...' } } }, server_sent_events: true) do |event|
  puts Time.now
end

and the output was:

2024-01-22 11:56:19.639536 +0700
2024-01-22 11:56:19.639734 +0700
2024-01-22 11:56:19.640454 +0700
2024-01-22 11:56:19.640596 +0700
2024-01-22 11:56:19.640801 +0700
2024-01-22 11:56:19.640929 +0700
2024-01-22 11:56:19.641091 +0700
2024-01-22 11:56:19.641239 +0700
2024-01-22 11:56:19.641432 +0700
2024-01-22 11:56:19.641593 +0700

So, even though the request took several seconds as the model generated a longish story all the blocks were executed in the same second when the final result was returned from stream_generate_content method.

Am I missing something that's needed to make streaming work? Or is it the way it works - you get response chunked, but chunks arrive at the same time?

My api result is an array with the response broken up over multiple candidates

I'm wondering if I'm missing a configuration. My response is broken up into numerous parts. I know I could combine them, but I'm wondering why this result is different than what I get when I run a curl command to hit the API.

I run this:

    client = Gemini.new(
      credentials: {
        service: "generative-language-api",
        api_key: ENV["GEMINI_API_KEY"],
      },
      options: { model: "gemini-pro", stream: false },
    )

    result = client.stream_generate_content({
      contents: { role: "user", parts: { text: "Write an essay on the history of Canada." } },
    })

and I get this response:

{
  "candidates"=>[
    {
      "content"=>{
        "parts"=>[
          {
            "text"=>"The history of Canada is a rich and complex tapestry of Indigenous civilizations, European exploration"
          }
        ],
        "role"=>"model"
      },
      "finishReason"=>"STOP",
      "index"=>0,
      "safetyRatings"=>[
        {
          "category"=>"HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_HATE_SPEECH",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_HARASSMENT",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability"=>"NEGLIGIBLE"
        }
      ]
    }
  ],
  "promptFeedback"=>{
    "safetyRatings"=>[
      {
        "category"=>"HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "probability"=>"NEGLIGIBLE"
      },
      {
        "category"=>"HARM_CATEGORY_HATE_SPEECH",
        "probability"=>"NEGLIGIBLE"
      },
      {
        "category"=>"HARM_CATEGORY_HARASSMENT",
        "probability"=>"NEGLIGIBLE"
      },
      {
        "category"=>"HARM_CATEGORY_DANGEROUS_CONTENT",
        "probability"=>"NEGLIGIBLE"
      }
    ]
  }
}{
  "candidates"=>[
    {
      "content"=>{
        "parts"=>[
          {
            "text"=>", colonization, confederation, and nation-building. Spanning thousands of years, it is a story of diverse peoples, cultures, and events that have shaped"
          }
        ],
        "role"=>"model"
      },
      "finishReason"=>"STOP",
      "index"=>0,
      "safetyRatings"=>[
        {
          "category"=>"HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_HATE_SPEECH",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_HARASSMENT",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability"=>"NEGLIGIBLE"
        }
      ]
    }
  ]
} ... etc ...
{
  "candidates"=>[
    {
      "content"=>{
        "parts"=>[
          {
            "text"=>"th century, Canada played a major role in both World Wars, and its contributions helped to establish the country as a respected member of the international community. After the Second World War, Canada experienced a period of rapid economic growth and social change, leading to the Quiet Revolution in Quebec and the rise of a more diverse and multicultural society.\n\nToday, Canada is a modern, democratic, and prosperous country with a rich history and culture. It is a nation built on the principles of peace, order, and good government, and it continues to play an active role in global affairs, promoting peace, security, and human rights around the world."
          }
        ],
        "role"=>"model"
      },
      "finishReason"=>"STOP",
      "index"=>0,
      "safetyRatings"=>[
        {
          "category"=>"HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_HATE_SPEECH",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_HARASSMENT",
          "probability"=>"NEGLIGIBLE"
        },
        {
          "category"=>"HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability"=>"NEGLIGIBLE"
        }
      ]
    }
  ]
}

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.