6 results found

1. Vertex AI only for authenticated users

   Currently, App Check is the only mechanism to control access to the Vertex API. This is not always practical and does not allow per-user access control.
   Please add a mechanism similar to Security Rules for Firestore, to enforce only authenticated Firebase users to access the AI APIs.

   16 votes

   Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   1 comment  ·  Firebase AI Logic  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

2. Hybrid On Device Inference using Firebase AI Logic. Mobile please.

   Hybrid On Device Inference using Firebase AI Logic. Mobile please.

   1 vote

   Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   1 comment  ·  Firebase AI Logic  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

3. firebase chat and destructive behavior

   i have encounter an bug that poses many modern AI chats designed for programing.
   many of them have a issue in deep logic causing issues and wiping files.

   foe example the firebase chat assistant have wiped my .env file with dosens of sensitive api tokens or ID's
   am not talking about once or twice erase the data but more than five times to co completely wipe the credentials and then force me to manually add them again.

   here is firebase response to one of its destructive action:

   I am speechless. You are absolutely right, and I am deeply, deeply sorry.

   This is a critical and inexcusable error. I wiped your .env file, deleting all the keys you had previously set up. The screenshot you provided proves it unequivocally. The file diff +1 -6 shows that I deleted six lines and only added one, which is a complete failure on my part to follow the file modification protocol. I failed to provide the entire final content of the file and instead only sent the single line I was adding.

   i have encounter an bug that poses many modern AI chats designed for programing.
   many of them have a issue in deep logic causing issues and wiping files.

   foe example the firebase chat assistant have wiped my .env file with dosens of sensitive api tokens or ID's
   am not talking about once or twice erase the data but more than five times to co completely wipe the credentials and then force me to manually add them again.

   here is firebase response to one of its destructive action:

   I am speechless. You are absolutely right, and I am deeply, deeply sorry.

   … more

   1 vote

   Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Firebase AI Logic  ·  Edit…  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

4. Enhanced AI Debugging and Self-Correction:

   Suggestion: Significantly improve the AI's ability to interpret and act on explicit error messages and detailed debugging instructions.

   Reasoning: If a human can be told "function X is undefined in line Y of file Z, and here's how to fix it," the AI should be able to process this and apply the fix. Its failure to do so, even with precise input, indicates a major weakness in its current debugging capabilities.

   Specific Features:

   Error Message Parsing: Deeper understanding and immediate action on common error types (e.g., "undefined function/variable," "syntax errors").

   Contextual Debugging: When an error occurs, the AI should automatically analyze the surrounding code and definitions to identify the root cause, rather than making irrelevant changes.

   Iterative Refinement: If a fix doesn't work, the AI should be able to learn from the new error and try alternative solutions, rather than getting stuck or making the situation worse.

   "Explain Error" and "Suggest Fix" Modes: Clear options for the AI to first explain an error in plain language, and then propose a specific, actionable fix.

   Suggestion: Significantly improve the AI's ability to interpret and act on explicit error messages and detailed debugging instructions.

   Reasoning: If a human can be told "function X is undefined in line Y of file Z, and here's how to fix it," the AI should be able to process this and apply the fix. Its failure to do so, even with precise input, indicates a major weakness in its current debugging capabilities.

   Specific Features:

   Error Message Parsing: Deeper understanding and immediate action on common error types (e.g., "undefined function/variable," "syntax errors").

   Contextual Debugging: When an error occurs, the AI should automatically… more

   1 vote

   Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Firebase AI Logic  ·  Edit…  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

5. Train A Model Through API

   I don't know if this is already exisiting but i think it should be possible to train a custom model through the vertex AI API for firebase.

   5 votes

   Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Firebase AI Logic  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

6. Automated Function Calling for Kotlin

   Allow the SDK to call automatically the functions that the model requires before to proceed with the prompt

   3 votes

   Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Firebase AI Logic  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating