LibreChat/api/app/clients/tools/structured/StableDiffusion.js
Danny Avila ad74350036
🚧 chore: merge latest dev build (#4288)
* fix: agent initialization, add `collectedUsage` handling

* style: improve side panel styling

* refactor(loadAgent): Optimize order agent project ID retrieval

* feat: code execution

* fix: typing issues

* feat: ExecuteCode content part

* refactor: use local state for default collapsed state of analysis content parts

* fix: code parsing in ExecuteCode component

* chore: bump agents package, export loadAuthValues

* refactor: Update handleTools.js to use EnvVar for code execution tool authentication

* WIP

* feat: download code outputs

* fix(useEventHandlers): type issues

* feat: backend handling for code outputs

* Refactor: Remove console.log statement in Part.tsx

* refactor: add attachments to TMessage/messageSchema

* WIP: prelim handling for code outputs

* feat: attachments rendering

* refactor: improve attachments rendering

* fix: attachments, nullish edge case, handle attachments from event stream, bump agents package

* fix filename download

* fix: tool assignment for 'run code' on agent creation

* fix: image handling by adding attachments

* refactor: prevent agent creation without provider/model

* refactor: remove unnecessary space in agent creation success message

* refactor: select first model if selecting provider from empty on form

* fix: Agent avatar bug

* fix: `defaultAgentFormValues` causing boolean typing issue and typeerror

* fix: capabilities counting as tools, causing duplication of them

* fix: formatted messages edge case where consecutive content text type parts with the latter having tool_call_ids would cause consecutive AI messages to be created. furthermore, content could not be an array for tool_use messages (anthropic limitation)

* chore: bump @librechat/agents dependency to version 1.6.9

* feat: bedrock agents

* feat: new Agents icon

* feat: agent titling

* feat: agent landing

* refactor: allow sharing agent globally only if user is admin or author

* feat: initial AgentPanelSkeleton

* feat: AgentPanelSkeleton

* feat: collaborative agents

* chore: add potential authorName as part of schema

* chore: Remove unnecessary console.log statement

* WIP: agent model parameters

* chore: ToolsDialog typing and tool related localization chnages

* refactor: update tool instance type (latest langchain class), and rename google tool to 'google' proper

* chore: add back tools

* feat: Agent knowledge files upload

* refactor: better verbiage for disabled knowledge

* chore: debug logs for file deletions

* chore: debug logs for file deletions

* feat: upload/delete agent knowledge/file-search files

* feat: file search UI for agents

* feat: first pass, file search tool

* chore: update default agent capabilities and info
2024-09-30 17:17:57 -04:00

161 lines
5.9 KiB
JavaScript

// Generates image using stable diffusion webui's api (automatic1111)
const fs = require('fs');
const { z } = require('zod');
const path = require('path');
const axios = require('axios');
const sharp = require('sharp');
const { v4: uuidv4 } = require('uuid');
const { Tool } = require('@langchain/core/tools');
const { FileContext } = require('librechat-data-provider');
const paths = require('~/config/paths');
const { logger } = require('~/config');
class StableDiffusionAPI extends Tool {
constructor(fields) {
super();
/** @type {string} User ID */
this.userId = fields.userId;
/** @type {Express.Request | undefined} Express Request object, only provided by ToolService */
this.req = fields.req;
/** @type {boolean} Used to initialize the Tool without necessary variables. */
this.override = fields.override ?? false;
/** @type {boolean} Necessary for output to contain all image metadata. */
this.returnMetadata = fields.returnMetadata ?? false;
if (fields.uploadImageBuffer) {
/** @type {uploadImageBuffer} Necessary for output to contain all image metadata. */
this.uploadImageBuffer = fields.uploadImageBuffer.bind(this);
}
this.name = 'stable-diffusion';
this.url = fields.SD_WEBUI_URL || this.getServerURL();
this.description_for_model = `// Generate images and visuals using text.
// Guidelines:
// - ALWAYS use {{"prompt": "7+ detailed keywords", "negative_prompt": "7+ detailed keywords"}} structure for queries.
// - ALWAYS include the markdown url in your final response to show the user: ![caption](/images/id.png)
// - Visually describe the moods, details, structures, styles, and/or proportions of the image. Remember, the focus is on visual attributes.
// - Craft your input by "showing" and not "telling" the imagery. Think in terms of what you'd want to see in a photograph or a painting.
// - Here's an example for generating a realistic portrait photo of a man:
// "prompt":"photo of a man in black clothes, half body, high detailed skin, coastline, overcast weather, wind, waves, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"
// "negative_prompt":"semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, out of frame, low quality, ugly, mutation, deformed"
// - Generate images only once per human query unless explicitly requested by the user`;
this.description =
'You can generate images using text with \'stable-diffusion\'. This tool is exclusively for visual content.';
this.schema = z.object({
prompt: z
.string()
.describe(
'Detailed keywords to describe the subject, using at least 7 keywords to accurately describe the image, separated by comma',
),
negative_prompt: z
.string()
.describe(
'Keywords we want to exclude from the final image, using at least 7 keywords to accurately describe the image, separated by comma',
),
});
}
replaceNewLinesWithSpaces(inputString) {
return inputString.replace(/\r\n|\r|\n/g, ' ');
}
getMarkdownImageUrl(imageName) {
const imageUrl = path
.join(this.relativePath, this.userId, imageName)
.replace(/\\/g, '/')
.replace('public/', '');
return `![generated image](/${imageUrl})`;
}
getServerURL() {
const url = process.env.SD_WEBUI_URL || '';
if (!url && !this.override) {
throw new Error('Missing SD_WEBUI_URL environment variable.');
}
return url;
}
async _call(data) {
const url = this.url;
const { prompt, negative_prompt } = data;
const payload = {
prompt,
negative_prompt,
cfg_scale: 4.5,
steps: 22,
width: 1024,
height: 1024,
};
let generationResponse;
try {
generationResponse = await axios.post(`${url}/sdapi/v1/txt2img`, payload);
} catch (error) {
logger.error('[StableDiffusion] Error while generating image:', error);
return 'Error making API request.';
}
const image = generationResponse.data.images[0];
/** @type {{ height: number, width: number, seed: number, infotexts: string[] }} */
let info = {};
try {
info = JSON.parse(generationResponse.data.info);
} catch (error) {
logger.error('[StableDiffusion] Error while getting image metadata:', error);
}
const file_id = uuidv4();
const imageName = `${file_id}.png`;
const { imageOutput: imageOutputPath, clientPath } = paths;
const filepath = path.join(imageOutputPath, this.userId, imageName);
this.relativePath = path.relative(clientPath, imageOutputPath);
if (!fs.existsSync(path.join(imageOutputPath, this.userId))) {
fs.mkdirSync(path.join(imageOutputPath, this.userId), { recursive: true });
}
try {
const buffer = Buffer.from(image.split(',', 1)[0], 'base64');
if (this.returnMetadata && this.uploadImageBuffer && this.req) {
const file = await this.uploadImageBuffer({
req: this.req,
context: FileContext.image_generation,
resize: false,
metadata: {
buffer,
height: info.height,
width: info.width,
bytes: Buffer.byteLength(buffer),
filename: imageName,
type: 'image/png',
file_id,
},
});
const generationInfo = info.infotexts[0].split('\n').pop();
return {
...file,
prompt,
metadata: {
negative_prompt,
seed: info.seed,
info: generationInfo,
},
};
}
await sharp(buffer)
.withMetadata({
iptcpng: {
parameters: info.infotexts[0],
},
})
.toFile(filepath);
this.result = this.getMarkdownImageUrl(imageName);
} catch (error) {
logger.error('[StableDiffusion] Error while saving the image:', error);
}
return this.result;
}
}
module.exports = StableDiffusionAPI;