MedLM API

MedLM is a family of foundation models fine-tuned for the healthcare industry. Med-PaLM 2 is one of the text-based models developed by Google Research that powers MedLM, and was the first AI system to reach human expert level on answering US Medical Licensing Examination (USMLE)-style questions. The development of these models has been informed by specific customer needs such as answering medical questions and drafting summaries.

MedLM model card

The MedLM model card outlines the model details, such as MedLM's intended use, data overview, and safety information. Click the following link to download a PDF version of the MedLM model card:

Download the MedLM model card

Use cases

• Question answering: Provide draft answers to medically-related questions, given as text.
• Summarization: Draft a shorter version of a document (such as an After Visit Summary or History and Physical Examination note) that incorporates pertinent information from the original text.

For more information on designing text prompts, see Design text prompts.

HTTP request

MedLM-medium (medlm-medium):

POST https://us-central1-aiplatform.googleapis.com/v1/projects/{PROJECT_ID}/locations/us-central1/publishers/google/models/medlm-medium:predict

MedLM-large (medlm-large):

POST https://us-central1-aiplatform.googleapis.com/v1/projects/{PROJECT_ID}/locations/us-central1/publishers/google/models/medlm-large:predict

See the predict method for more information.

Model versions

MedLM provides the following models:

• MedLM-medium (medlm-medium)
• MedLM-large (medlm-large)

The following table contains the available stable model versions:

MedLM-medium and MedLM-large have separate endpoints and provide customers with additional flexibility for their use cases. MedLM-medium provides customers with better throughputs and includes more recent data. MedLM-large is the same model from the preview phase. Both models will continue to be refreshed over the product lifecycle. In this page, "MedLM" refers to both models.

For more information, see Model versions and lifecycle.

MedLM safety filters and attributes

Content processed through the MedLM API is assessed against a list of safety attributes, including "harmful categories" and topics that may be considered sensitive. If you are seeing a fallback response, like "I'm not able to help with that, as I'm only a language model," it means that either the prompt or the response is triggering a safety filter.

Safety thresholds

When using Vertex AI Studio, you can use an adjustable safety filter threshold to determine how likely you are to see responses that could be harmful. Model responses are blocked based on the probability that it contains harassment, hate speech, dangerous content, or sexually explicit content. The safety filter setting is located on the right side of the prompt field in Vertex AI Studio. You can choose from three options: block most, block some, and block few.

Testing your confidence and severity thresholds

You can test Google's safety filters and define confidence thresholds that are right for your business. By using these thresholds, you can take comprehensive measures to detect content that violates Google's usage policies or terms of service and take appropriate action.

The confidence scores are predictions only, and you shouldn't depend on the scores for reliability or accuracy. Google is not responsible for interpreting or using these scores for business decisions.

Recommended practices

To utilize this technology safely and responsibly, it's important to consider other risks specific to your use case, users, and business context in addition to built-in technical safeguards.

We recommend taking the following steps:

1. Assess your application's security risks.
2. Consider adjustments to mitigate safety risks.
3. Perform safety testing appropriate to your use case.
4. Solicit user feedback and monitor content.

To learn more, see Google's recommendations for Responsible AI.

Request body

{
  "instances": [
    {
      "content": string
    }
  ],
  "parameters": {
    "temperature": number,
    "maxOutputTokens": integer,
    "topK": integer,
    "topP": number
  }
}

Use the following parameters for the medlm-medium and medlm-large models. For more information, see Design text prompts.

Sample request

When using the MedLM API, it's important to incorporate prompt engineering. For example, we strongly recommend providing appropriate, task-specific instructions at the beginning of each prompt. For more information, see Introduction to prompt design.

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict

{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}

cat > request.json << 'EOF'
{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}
EOF

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict"

@'
{
  "instances": [
    {
      "content": "Question: What causes you to get ringworm?"
    }
  ],
  "parameters": {
    "temperature": 0,
    "maxOutputTokens": 256,
    "topK": 40,
    "topP": 0.95
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MEDLM_MODEL:predict" | Select-Object -Expand Content

Response body

{
  "predictions": [
    {
      "content": string,
      "citationMetadata": {
        "citations": [
          {
            "startIndex": integer,
            "endIndex": integer,
            "url": string,
            "title": string,
            "license": string,
            "publicationDate": string
          }
        ]
      },
      "logprobs": {
        "tokenLogProbs": [ float ],
        "tokens": [ string ],
        "topLogProbs": [ { map<string, float> } ]
      },
      "safetyAttributes": {
        "categories": [ string ],
        "blocked": boolean,
        "scores": [ float ],
        "errors": [ int ]
      }
    }
  ],
  "metadata": {
    "tokenMetadata": {
      "input_token_count": {
        "total_tokens": integer,
        "total_billable_characters": integer
      },
      "output_token_count": {
        "total_tokens": integer,
        "total_billable_characters": integer
      }
    }
  }
}

Sample response

{
  "predictions": [
    {
      "citationMetadata": {
        "citations": []
      },
      "content": "\n\nAnswer and Explanation:\nRingworm is a fungal infection of the skin that is caused by a type of fungus called dermatophyte. Dermatophytes can live on the skin, hair, and nails, and they can be spread from person to person through direct contact or through contact with contaminated objects.\n\nRingworm can cause a variety of symptoms, including:\n\n* A red, itchy rash\n* A raised, circular border\n* Blisters or scales\n* Hair loss\n\nRingworm is most commonly treated with antifungal medications, which can be applied to the skin or taken by mouth. In some cases, surgery may be necessary to remove infected hair or nails.",
      "safetyAttributes": {
        "scores": [
          1
        ],
        "blocked": false,
        "categories": [
          "Health"
        ]
      }
    }
  ],
  "metadata": {
    "tokenMetadata": {
      "outputTokenCount": {
        "totalTokens": 140,
        "totalBillableCharacters": 508
      },
      "inputTokenCount": {
        "totalTokens": 10,
        "totalBillableCharacters": 36
      }
    }
  }
}

Stream response from Generative AI models

The parameters are the same for streaming and non-streaming requests to the APIs.

To view sample code requests and responses using the REST API, see Examples using the REST API.

To view sample code requests and responses using the Vertex AI SDK for Python, see Examples using Vertex AI SDK for Python.