[PR #11054] [CLOSED] feat - human-in-loop self-prompting via filters #9447

New Issue

GiteaMirror · 2025-11-11T18:22:48-06:00

GiteaMirror commented

2025-11-11 18:22:48 -06:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/11054
Author: @i-am-david-fernandez
Created: 3/2/2025
Status: ❌ Closed

Base: dev ← Head: feature/insert-prompt-via-filter

📝 Commits (1)

531bf96 Added function to set the prompt from a completed chat payload.

📊 Changes

1 file changed (+14 additions, -0 deletions)

View changed files

📝 src/lib/components/chat/Chat.svelte (+14 -0)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions and describe your changes before submitting a pull request.

Before submitting, make sure you've checked the following:

Target branch: Please verify that the pull request targets the dev branch.
Description: Provide a concise description of the changes made in this pull request.
Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
Documentation: Have you updated relevant documentation Open WebUI Docs, or other documentation sources?
Dependencies: Are there any new dependencies? Have you updated the dependency versions in the documentation?
Testing: Have you written and run sufficient tests for validating the changes?
Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
Prefix: To cleary categorize this pull request, prefix the pull request title, using one of the following:
- BREAKING CHANGE: Significant changes that may affect compatibility
- build: Changes that affect the build system or external dependencies
- ci: Changes to our continuous integration processes or workflows
- chore: Refactor, cleanup, or other non-functional code changes
- docs: Documentation update or addition
- feat: Introduces a new feature or enhancement to the codebase
- fix: Bug fix or error correction
- i18n: Internationalization or localization changes
- perf: Performance improvement
- refactor: Code restructuring for better maintainability, readability, or scalability
- style: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc.)
- test: Adding missing tests or correcting existing tests
- WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

[Concisely describe the changes made in this pull request, including any relevant motivation and impact (e.g., fixing a bug, adding a feature, or improving performance)]

Certain broader AI/LLM functions require the ability for an LLM to self-prompt, that is, provide itself with a subsequent prompt in order to direct its subsequent responses. As a first step, and to aid safety and security, this should retain the human-in-the-loop such that the human operator may review and approve of the prompt, rather than have it automatically submitted.

Open-WebUI already has the ability, via Outlet Filters, to programatically extract content from an LLM's response; what is missing is the ability to feed any extracted material back via the (next) prompt. This PR adds this capability.

Added

[List any new features, functionalities, or additions]

This changeset adds a single new frontend function to ease programmatic setting of the (next) prompt, i.e., prefilling the prompt text input. If a "chat completed" payload contains an optional prompt field, this function is called to prefill the prompt with the payload-supplied value.

Changed

[List any changes, updates, refactorings, or optimizations]

N/A

Deprecated

[List any deprecated functionality or features that have been removed]

N/A

Removed

[List any removed features, files, or functionalities]

N/A

Fixed

[List any fixes, corrections, or bug fixes]

N/A

Security

[List any new or updated security-related changes, including vulnerability fixes]

N/A

Breaking Changes

BREAKING CHANGE: [List any breaking changes affecting compatibility or functionality]

N/A

Additional Information

[Insert any additional context, notes, or explanations for the changes]
- [Reference any related issues, commits, or other relevant information]

A minimal Filter to prefill the prompt is as follows:

from pydantic import BaseModel
from typing import Optional

class Filter:
    class Valves(BaseModel):
        pass

    class UserValves(BaseModel):
        pass

    def __init__(self):
        self.valves = self.Valves()
        pass

    def outlet(self, body: dict, __user__: Optional[dict] = None) -> dict:
        body["prompt"] = "This is the next prompt."
        return body

This simply provides a fixed value ("This is the next prompt.") to be the next prompt, but illustrates the mechanism by which an Outlet Filter may provide a prompt. Additional processing/logic would allow arbitrary prompts to be provided, typically as a result of processing the LLM response.

See also https://github.com/open-webui/open-webui/discussions/11041.

Screenshots or Videos

[Attach any relevant screenshots or videos demonstrating the changes]

N/A

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/11054 **Author:** [@i-am-david-fernandez](https://github.com/i-am-david-fernandez) **Created:** 3/2/2025 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `feature/insert-prompt-via-filter` --- ### 📝 Commits (1) - [`531bf96`](https://github.com/open-webui/open-webui/commit/531bf966b8412112e4f46c13aabb32a2fd0402a2) Added function to set the prompt from a completed chat payload. ### 📊 Changes **1 file changed** (+14 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `src/lib/components/chat/Chat.svelte` (+14 -0) </details> ### 📄 Description # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) and describe your changes before submitting a pull request. **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Please verify that the pull request targets the `dev` branch. - [x] **Description:** Provide a concise description of the changes made in this pull request. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [x] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources? - [x] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation? - [x] **Testing:** Have you written and run sufficient tests for validating the changes? - [x] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Prefix:** To cleary categorize this pull request, prefix the pull request title, using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry ### Description - [Concisely describe the changes made in this pull request, including any relevant motivation and impact (e.g., fixing a bug, adding a feature, or improving performance)] Certain broader AI/LLM functions require the ability for an LLM to self-prompt, that is, provide itself with a subsequent prompt in order to direct its subsequent responses. As a first step, and to aid safety and security, this should retain the human-in-the-loop such that the human operator may review and approve of the prompt, rather than have it automatically submitted. Open-WebUI already has the ability, via `Outlet` `Filters`, to programatically extract content from an LLM's response; what is missing is the ability to feed any extracted material back via the (next) prompt. This PR adds this capability. ### Added - [List any new features, functionalities, or additions] This changeset adds a single new frontend function to ease programmatic setting of the (next) prompt, i.e., prefilling the prompt text input. If a "chat completed" payload contains an optional `prompt` field, this function is called to prefill the prompt with the payload-supplied value. ### Changed - [List any changes, updates, refactorings, or optimizations] N/A ### Deprecated - [List any deprecated functionality or features that have been removed] N/A ### Removed - [List any removed features, files, or functionalities] N/A ### Fixed - [List any fixes, corrections, or bug fixes] N/A ### Security - [List any new or updated security-related changes, including vulnerability fixes] N/A ### Breaking Changes - **BREAKING CHANGE**: [List any breaking changes affecting compatibility or functionality] N/A --- ### Additional Information - [Insert any additional context, notes, or explanations for the changes] - [Reference any related issues, commits, or other relevant information] A minimal `Filter` to prefill the prompt is as follows: ```python from pydantic import BaseModel from typing import Optional class Filter: class Valves(BaseModel): pass class UserValves(BaseModel): pass def __init__(self): self.valves = self.Valves() pass def outlet(self, body: dict, __user__: Optional[dict] = None) -> dict: body["prompt"] = "This is the next prompt." return body ``` This simply provides a fixed value ("This is the next prompt.") to be the next prompt, but illustrates the mechanism by which an `Outlet` `Filter` may provide a prompt. Additional processing/logic would allow arbitrary prompts to be provided, typically as a result of processing the LLM response. See also https://github.com/open-webui/open-webui/discussions/11041. ### Screenshots or Videos - [Attach any relevant screenshots or videos demonstrating the changes] N/A --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2025-11-11 18:22:48 -06:00

GiteaMirror closed this issue

2025-11-11 18:22:48 -06:00

GiteaMirror referenced this issue

2026-04-19 21:41:34 -05:00

[GH-ISSUE #9447] Allow anon users #15509

GiteaMirror referenced this issue

2026-04-25 05:07:16 -05:00

[GH-ISSUE #9447] Allow anon users #31037

GiteaMirror referenced this issue

2026-05-05 15:53:47 -05:00

[GH-ISSUE #9447] Allow anon users #54174