From e8b724c22bed4b6ed01e34ba661228c348f50378 Mon Sep 17 00:00:00 2001 From: "A.J. Shulman" Date: Tue, 22 Oct 2024 13:47:46 -0400 Subject: fixed websearch tool endpoint so it only returns displayable results in Dash; also fixed type checking but needs to be improved --- src/server/ApiManagers/AssistantManager.ts | 64 ++++++++++++++++++++++++++---- 1 file changed, 57 insertions(+), 7 deletions(-) (limited to 'src/server/ApiManagers') diff --git a/src/server/ApiManagers/AssistantManager.ts b/src/server/ApiManagers/AssistantManager.ts index 8447a4934..d7b72bac7 100644 --- a/src/server/ApiManagers/AssistantManager.ts +++ b/src/server/ApiManagers/AssistantManager.ts @@ -9,7 +9,7 @@ */ import { Readability } from '@mozilla/readability'; -import axios from 'axios'; +import axios, { AxiosResponse } from 'axios'; import { spawn } from 'child_process'; import * as fs from 'fs'; import { writeFile } from 'fs'; @@ -115,29 +115,79 @@ export default class AssistantManager extends ApiManager { }, }); - // Register Google Web Search Results API route register({ method: Method.POST, subscription: '/getWebSearchResults', secureHandler: async ({ req, res }) => { const { query, max_results } = req.body; - try { - // Fetch search results using Google Custom Search API - const response = await customsearch.cse.list({ + const MIN_VALID_RESULTS_RATIO = 0.75; // 3/4 threshold + let startIndex = 1; // Start at the first result initially + let validResults: any[] = []; + + const fetchSearchResults = async (start: number) => { + return customsearch.cse.list({ q: query, cx: process.env._CLIENT_GOOGLE_SEARCH_ENGINE_ID, key: process.env._CLIENT_GOOGLE_API_KEY, safe: 'active', num: max_results, + start, // This controls which result index the search starts from }); + }; + + const filterResultsByXFrameOptions = async (results: any[]) => { + const filteredResults = await Promise.all( + results.map(async result => { + try { + const urlResponse: AxiosResponse = await axios.head(result.url, { timeout: 5000 }); + const xFrameOptions = urlResponse.headers['x-frame-options']; + if (xFrameOptions && xFrameOptions.toUpperCase() === 'SAMEORIGIN') { + return result; + } + } catch (error) { + console.error(`Error checking x-frame-options for URL: ${result.url}`, error); + } + return null; // Exclude the result if it doesn't match + }) + ); + return filteredResults.filter(result => result !== null); // Remove null results + }; - const results = + try { + // Fetch initial search results + let response = await fetchSearchResults(startIndex); + let initialResults = response.data.items?.map(item => ({ url: item.link, snippet: item.snippet, })) || []; - res.send({ results }); + // Filter the initial results + validResults = await filterResultsByXFrameOptions(initialResults); + + // If valid results are less than 3/4 of max_results, fetch more results + while (validResults.length < max_results * MIN_VALID_RESULTS_RATIO) { + // Increment the start index by the max_results to fetch the next set of results + startIndex += max_results; + response = await fetchSearchResults(startIndex); + + const additionalResults = + response.data.items?.map(item => ({ + url: item.link, + snippet: item.snippet, + })) || []; + + const additionalValidResults = await filterResultsByXFrameOptions(additionalResults); + validResults = [...validResults, ...additionalValidResults]; // Combine valid results + + // Break if no more results are available + if (additionalValidResults.length === 0 || response.data.items?.length === 0) { + break; + } + } + + // Return the filtered valid results + res.send({ results: validResults.slice(0, max_results) }); // Limit the results to max_results } catch (error) { console.error('Error performing web search:', error); res.status(500).send({ -- cgit v1.2.3-70-g09d2 From a99b38e4cdc4ec995cf2d56e94980987d6f31cbb Mon Sep 17 00:00:00 2001 From: "A.J. Shulman" Date: Wed, 30 Oct 2024 14:17:03 -0400 Subject: before changing the get result endpoint --- src/server/ApiManagers/AssistantManager.ts | 39 ++++++++++++++++++------------ src/server/chunker/pdf_chunker.py | 33 +++++++++++++------------ 2 files changed, 41 insertions(+), 31 deletions(-) (limited to 'src/server/ApiManagers') diff --git a/src/server/ApiManagers/AssistantManager.ts b/src/server/ApiManagers/AssistantManager.ts index d7b72bac7..cfa95cb4e 100644 --- a/src/server/ApiManagers/AssistantManager.ts +++ b/src/server/ApiManagers/AssistantManager.ts @@ -495,10 +495,12 @@ function spawnPythonProcess(jobId: string, file_name: string, file_data: string) const requirementsPath = path.join(__dirname, '../chunker/requirements.txt'); const pythonScriptPath = path.join(__dirname, '../chunker/pdf_chunker.py'); + const outputDirectory = pathToDirectory(Directory.chunk_images); + function runPythonScript() { const pythonPath = process.platform === 'win32' ? path.join(venvPath, 'Scripts', 'python') : path.join(venvPath, 'bin', 'python3'); - const pythonProcess = spawn(pythonPath, [pythonScriptPath, jobId, file_name, file_data]); + const pythonProcess = spawn(pythonPath, [pythonScriptPath, jobId, file_name, file_data, outputDirectory]); let pythonOutput = ''; let stderrOutput = ''; @@ -510,23 +512,30 @@ function spawnPythonProcess(jobId: string, file_name: string, file_data: string) pythonProcess.stderr.on('data', data => { stderrOutput += data.toString(); const lines = stderrOutput.split('\n'); + stderrOutput = lines.pop() || ''; // Save the last partial line back to stderrOutput lines.forEach(line => { if (line.trim()) { - try { - const parsedOutput = JSON.parse(line); - if (parsedOutput.job_id && parsedOutput.progress !== undefined) { - jobProgress[parsedOutput.job_id] = { - step: parsedOutput.step, - progress: parsedOutput.progress, - }; - } else if (parsedOutput.progress !== undefined) { - jobProgress[jobId] = { - step: parsedOutput.step, - progress: parsedOutput.progress, - }; + if (line.startsWith('PROGRESS:')) { + const jsonString = line.substring('PROGRESS:'.length); + try { + const parsedOutput = JSON.parse(jsonString); + if (parsedOutput.job_id && parsedOutput.progress !== undefined) { + jobProgress[parsedOutput.job_id] = { + step: parsedOutput.step, + progress: parsedOutput.progress, + }; + } else if (parsedOutput.progress !== undefined) { + jobProgress[jobId] = { + step: parsedOutput.step, + progress: parsedOutput.progress, + }; + } + } catch (err) { + console.error('Error parsing progress JSON:', jsonString, err); } - } catch (err) { - console.error('Progress log from Python:', line, err); + } else { + // Log other stderr output + console.error('Python stderr:', line); } } }); diff --git a/src/server/chunker/pdf_chunker.py b/src/server/chunker/pdf_chunker.py index 4fe3b9dbf..7a3244fbc 100644 --- a/src/server/chunker/pdf_chunker.py +++ b/src/server/chunker/pdf_chunker.py @@ -54,8 +54,9 @@ def update_progress(job_id, step, progress_value): "step": step, "progress": progress_value } - print(json.dumps(progress_data), file=sys.stderr) # Use stderr for progress logs - sys.stderr.flush() # Ensure it's sent immediately + print(f"PROGRESS:{json.dumps(progress_data)}", file=sys.stderr) + sys.stderr.flush() + class ElementExtractor: @@ -664,7 +665,7 @@ class Document: Represents a document being processed, such as a PDF, handling chunking, embedding, and summarization. """ - def __init__(self, file_data: bytes, file_name: str, job_id: str): + def __init__(self, file_data: bytes, file_name: str, job_id: str, output_folder: str): """ Initialize the Document with file data, file name, and job ID. @@ -672,6 +673,7 @@ class Document: :param file_name: The name of the file being processed. :param job_id: The job ID associated with this document processing task. """ + self.output_folder = output_folder self.file_data = file_data self.file_name = file_name self.job_id = job_id @@ -680,14 +682,13 @@ class Document: self.chunks = [] # List to hold text and visual chunks self.num_pages = 0 # Number of pages in the document (if applicable) self.summary = "" # The generated summary for the document - self._process() # Start processing the document def _process(self): """ Process the document: extract chunks, embed them, and generate a summary. """ - pdf_chunker = PDFChunker(output_folder="output") # Initialize the PDF chunker + pdf_chunker = PDFChunker(output_folder=self.output_folder) self.chunks = asyncio.run(pdf_chunker.chunk_pdf(self.file_data, self.file_name, self.doc_id, self.job_id)) # Extract chunks self.num_pages = self._get_pdf_pages() # Get the number of pages in the document @@ -796,8 +797,7 @@ class Document: "doc_id": self.doc_id }, indent=2) # Convert the document's attributes to JSON format - -def process_document(file_data, file_name, job_id): +def process_document(file_data, file_name, job_id, output_folder): """ Top-level function to process a document and return the JSON output. @@ -806,28 +806,28 @@ def process_document(file_data, file_name, job_id): :param job_id: The job ID for this document processing task. :return: The processed document's data in JSON format. """ - new_document = Document(file_data, file_name, job_id) # Create a new Document object - return new_document.to_json() # Return the document's JSON data - + new_document = Document(file_data, file_name, job_id, output_folder) + return new_document.to_json() def main(): """ Main entry point for the script, called with arguments from Node.js. """ - if len(sys.argv) != 4: - print(json.dumps({"error": "Invalid arguments"}), file=sys.stderr) # Print error if incorrect number of arguments + if len(sys.argv) != 5: + print(json.dumps({"error": "Invalid arguments"}), file=sys.stderr) return - job_id = sys.argv[1] # Get the job ID from command-line arguments - file_name = sys.argv[2] # Get the file name from command-line arguments - file_data = sys.argv[3] # Get the base64-encoded file data from command-line arguments + job_id = sys.argv[1] + file_name = sys.argv[2] + file_data = sys.argv[3] + output_folder = sys.argv[4] # Get the output folder from arguments try: # Decode the base64 file data file_bytes = base64.b64decode(file_data) # Process the document - document_result = process_document(file_bytes, file_name, job_id) + document_result = process_document(file_bytes, file_name, job_id, output_folder) # Pass output_folder # Output the final result as JSON to stdout print(document_result) @@ -839,5 +839,6 @@ def main(): sys.stderr.flush() + if __name__ == "__main__": main() # Execute the main function when the script is run -- cgit v1.2.3-70-g09d2 From 07516f420ab38fbc63d54f3421bf33a493037ae8 Mon Sep 17 00:00:00 2001 From: "A.J. Shulman" Date: Wed, 30 Oct 2024 15:31:38 -0400 Subject: much better RAG with image retrieval fixed significantly and much faster (only saving images in one place and remembering where they are saved) --- src/server/ApiManagers/AssistantManager.ts | 54 +++++++++++------------------- src/server/chunker/pdf_chunker.py | 41 ++++++++++++----------- 2 files changed, 41 insertions(+), 54 deletions(-) (limited to 'src/server/ApiManagers') diff --git a/src/server/ApiManagers/AssistantManager.ts b/src/server/ApiManagers/AssistantManager.ts index cfa95cb4e..4d2068014 100644 --- a/src/server/ApiManagers/AssistantManager.ts +++ b/src/server/ApiManagers/AssistantManager.ts @@ -23,6 +23,7 @@ import { AI_Document } from '../../client/views/nodes/chatbot/types/types'; import { Method } from '../RouteManager'; import { filesDirectory, publicDirectory } from '../SocketData'; import ApiManager, { Registration } from './ApiManager'; +import { getServerPath } from '../../client/util/reportManager/reportManagerUtils'; // Enumeration of directories where different file types are stored export enum Directory { @@ -349,47 +350,16 @@ export default class AssistantManager extends ApiManager { method: Method.GET, subscription: '/getResult/:jobId', secureHandler: async ({ req, res }) => { - const { jobId } = req.params; // Get the job ID from the URL parameters - // Check if the job result is available + const { jobId } = req.params; if (jobResults[jobId]) { const result = jobResults[jobId] as AI_Document & { status: string }; - // If the result contains image or table chunks, save the base64 data as image files if (result.chunks && Array.isArray(result.chunks)) { - await Promise.all( - result.chunks.map(chunk => { - if (chunk.metadata && (chunk.metadata.type === 'image' || chunk.metadata.type === 'table')) { - const files_directory = '/files/chunk_images/'; - const directory = path.join(publicDirectory, files_directory); - - // Ensure the directory exists or create it - if (!fs.existsSync(directory)) { - fs.mkdirSync(directory); - } - - const fileName = path.basename(chunk.metadata.file_path); // Get the file name from the path - const filePath = path.join(directory, fileName); // Create the full file path - - // Check if the chunk contains base64 encoded data - if (chunk.metadata.base64_data) { - // Decode the base64 data and write it to a file - const buffer = Buffer.from(chunk.metadata.base64_data, 'base64'); - fs.promises.writeFile(filePath, buffer).then(() => { - // Update the file path in the chunk's metadata - chunk.metadata.file_path = path.join(files_directory, fileName); - chunk.metadata.base64_data = undefined; // Remove the base64 data from the metadata - }); - } else { - console.warn(`No base64_data found for chunk: ${fileName}`); - } - } - }) - ); result.status = 'completed'; } else { result.status = 'pending'; } - res.json(result); // Send the result back to the client + res.json(result); } else { res.status(202).send({ status: 'pending' }); } @@ -417,7 +387,7 @@ export default class AssistantManager extends ApiManager { // If the chunk is an image or table, read the corresponding file and encode it as base64 if (chunk.metadata.type === 'image' || chunk.metadata.type === 'table') { try { - const filePath = serverPathToFile(Directory.chunk_images, chunk.metadata.file_path); // Get the file path + const filePath = path.join(pathToDirectory(Directory.chunk_images), chunk.metadata.file_path); // Get the file path readFileAsync(filePath).then(imageBuffer => { const base64Image = imageBuffer.toString('base64'); // Convert the image to base64 @@ -549,10 +519,24 @@ function spawnPythonProcess(jobId: string, file_name: string, file_data: string) jobProgress[jobId] = { step: 'Complete', progress: 100 }; } catch (err) { console.error('Error parsing final JSON result:', err); + jobResults[jobId] = { error: 'Failed to parse final result' }; } } else { console.error(`Python process exited with code ${code}`); - jobResults[jobId] = { error: 'Python process failed' }; + // Check if there was an error message in stderr + if (stderrOutput) { + // Try to parse the last line as JSON + const lines = stderrOutput.trim().split('\n'); + const lastLine = lines[lines.length - 1]; + try { + const errorOutput = JSON.parse(lastLine); + jobResults[jobId] = errorOutput; + } catch (err) { + jobResults[jobId] = { error: 'Python process failed' }; + } + } else { + jobResults[jobId] = { error: 'Python process failed' }; + } } }); } diff --git a/src/server/chunker/pdf_chunker.py b/src/server/chunker/pdf_chunker.py index 7a3244fbc..130987343 100644 --- a/src/server/chunker/pdf_chunker.py +++ b/src/server/chunker/pdf_chunker.py @@ -64,13 +64,15 @@ class ElementExtractor: A class that uses a YOLO model to extract tables and images from a PDF page. """ - def __init__(self, output_folder: str): + def __init__(self, output_folder: str, doc_id: str): """ Initializes the ElementExtractor with the output folder for saving images and the YOLO model. :param output_folder: Path to the folder where extracted elements will be saved. """ - self.output_folder = output_folder + self.doc_id = doc_id + self.output_folder = os.path.join(output_folder, doc_id) + os.makedirs(self.output_folder, exist_ok=True) self.model = YOLO('keremberke/yolov8m-table-extraction') # Load YOLO model for table extraction self.model.overrides['conf'] = 0.25 # Set confidence threshold for detection self.model.overrides['iou'] = 0.45 # Set Intersection over Union (IoU) threshold @@ -114,20 +116,18 @@ class ElementExtractor: # Save the full page with the red outline table_filename = f"table_page{page_num + 1}_{idx + 1}.png" + file_path_for_client = f"{self.doc_id}/{table_filename}" table_path = os.path.join(self.output_folder, table_filename) page_with_outline.save(table_path) - # Convert the full-page image with red outline to base64 - base64_data = self.image_to_base64(page_with_outline) - tables.append({ 'metadata': { "type": "table", "location": [x1 / img.width, y1 / img.height, x2 / img.width, y2 / img.height], - "file_path": table_path, + "file_path": file_path_for_client, "start_page": page_num, "end_page": page_num, - "base64_data": base64_data, + "base64_data": self.image_to_base64(page_with_outline) } }) @@ -173,21 +173,19 @@ class ElementExtractor: # Save the full page with the red outline image_filename = f"image_page{page_num + 1}_{img_index + 1}.png" + file_path_for_client = f"{self.doc_id}/{image_filename}" image_path = os.path.join(self.output_folder, image_filename) page_with_outline.save(image_path) - # Convert the full-page image with red outline to base64 - base64_data = self.image_to_base64(page_with_outline) - images.append({ 'metadata': { "type": "image", "location": [x1 / page.rect.width, y1 / page.rect.height, x2 / page.rect.width, y2 / page.rect.height], - "file_path": image_path, + "file_path": file_path_for_client, "start_page": page_num, "end_page": page_num, - "base64_data": base64_data, + "base64_data": self.image_to_base64(image) } }) @@ -269,7 +267,7 @@ class PDFChunker: The main class responsible for chunking PDF files into text and visual elements (tables/images). """ - def __init__(self, output_folder: str = "output", image_batch_size: int = 5) -> None: + def __init__(self, output_folder: str = "output", doc_id: str = '', image_batch_size: int = 5) -> None: """ Initializes the PDFChunker with an output folder and an element extractor for visual elements. @@ -279,7 +277,8 @@ class PDFChunker: self.client = Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY")) # Initialize the Anthropic API client self.output_folder = output_folder self.image_batch_size = image_batch_size # Batch size for image processing - self.element_extractor = ElementExtractor(output_folder) # Initialize the element extractor + self.doc_id = doc_id # Add doc_id + self.element_extractor = ElementExtractor(output_folder, doc_id) async def chunk_pdf(self, file_data: bytes, file_name: str, doc_id: str, job_id: str) -> List[Dict[str, Any]]: """ @@ -364,6 +363,7 @@ class PDFChunker: for j, elem in enumerate(batch, start=1): if j in summaries: elem['metadata']['text'] = re.sub(r'^(Image|Table):\s*', '', summaries[j]) + elem['metadata']['base64_data'] = '' processed_elements.append(elem) progress = ((i // image_batch_size) + 1) / total_batches * 100 # Calculate progress @@ -629,10 +629,11 @@ class PDFChunker: return summaries - except Exception: - #print(f"Error in batch_summarize_images: {str(e)}") - #print("Returning placeholder summaries") - return {number: "Error: No summary available" for number in images} + except Exception as e: + # Print errors to stderr so they don't interfere with JSON output + print(json.dumps({"error": str(e)}), file=sys.stderr) + sys.stderr.flush() + class DocumentType(Enum): """ @@ -688,7 +689,7 @@ class Document: """ Process the document: extract chunks, embed them, and generate a summary. """ - pdf_chunker = PDFChunker(output_folder=self.output_folder) + pdf_chunker = PDFChunker(output_folder=self.output_folder, doc_id=self.doc_id) # Initialize PDFChunker self.chunks = asyncio.run(pdf_chunker.chunk_pdf(self.file_data, self.file_name, self.doc_id, self.job_id)) # Extract chunks self.num_pages = self._get_pdf_pages() # Get the number of pages in the document @@ -823,6 +824,8 @@ def main(): output_folder = sys.argv[4] # Get the output folder from arguments try: + os.makedirs(output_folder, exist_ok=True) + # Decode the base64 file data file_bytes = base64.b64decode(file_data) -- cgit v1.2.3-70-g09d2 From 89424e0a8efc6cf3364a2fd1ffc85c9d0d837453 Mon Sep 17 00:00:00 2001 From: bobzel Date: Fri, 22 Nov 2024 10:27:33 -0500 Subject: added initial Firefly endpoint and hanged smartDrawHandler to generate an image and an svg. --- src/client/util/bezierFit.ts | 3 +- src/client/views/MainView.tsx | 32 ++++++++++++-- .../nodes/chatbot/chatboxcomponents/ChatBox.tsx | 3 +- src/client/views/pdf/AnchorMenu.tsx | 9 ++-- src/client/views/smartdraw/SmartDrawHandler.tsx | 29 ++++++------ src/server/ApiManagers/DataVizManager.ts | 2 +- src/server/ApiManagers/FireflyManager.ts | 51 ++++++++++++++++++++++ src/server/DashUploadUtils.ts | 3 +- src/server/index.ts | 3 +- webpack.config.js | 7 ++- 10 files changed, 113 insertions(+), 29 deletions(-) create mode 100644 src/server/ApiManagers/FireflyManager.ts (limited to 'src/server/ApiManagers') diff --git a/src/client/util/bezierFit.ts b/src/client/util/bezierFit.ts index d52460023..84b27e84c 100644 --- a/src/client/util/bezierFit.ts +++ b/src/client/util/bezierFit.ts @@ -703,7 +703,6 @@ export function SVGToBezier(name: SVGType, attributes: any): Point[] { coordList.push({ X: parseInt(match[1]), Y: parseInt(match[2]) }); coordList.push({ X: parseInt(match[1]), Y: parseInt(match[2]) }); coordList.push({ X: parseInt(match[3]), Y: parseInt(match[4]) }); - coordList.push({ X: parseInt(match[3]), Y: parseInt(match[4]) }); lastPt = { X: parseInt(match[3]), Y: parseInt(match[4]) }; } else if (match[0].startsWith('C')) { coordList.push({ X: parseInt(match[5]), Y: parseInt(match[6]) }); @@ -720,7 +719,7 @@ export function SVGToBezier(name: SVGType, attributes: any): Point[] { } }); const hasZ = attributes.d.match(/Z/); - if (hasZ) { + if (hasZ || attributes.fill) { coordList.push(lastPt); coordList.push(startPt); coordList.push(startPt); diff --git a/src/client/views/MainView.tsx b/src/client/views/MainView.tsx index 7779d339f..0d071fe4f 100644 --- a/src/client/views/MainView.tsx +++ b/src/client/views/MainView.tsx @@ -8,7 +8,7 @@ import { observer } from 'mobx-react'; import * as React from 'react'; import ResizeObserver from 'resize-observer-polyfill'; import '../../../node_modules/browndash-components/dist/styles/global.min.css'; -import { ClientUtils, lightOrDark, returnEmptyFilter, returnFalse, returnTrue, returnZero, setupMoveUpEvents } from '../../ClientUtils'; +import { ClientUtils, returnEmptyFilter, returnFalse, returnTrue, returnZero, setupMoveUpEvents } from '../../ClientUtils'; import { emptyFunction } from '../../Utils'; import { Doc, DocListCast, GetDocFromUrl, Opt, returnEmptyDoclist } from '../../fields/Doc'; import { DocData } from '../../fields/DocSymbols'; @@ -1023,10 +1023,36 @@ export class MainView extends ObservableReactComponent { {[ ...SnappingManager.HorizSnapLines.map(l => ( - + )), ...SnappingManager.VertSnapLines.map(l => ( - + )), ]} diff --git a/src/client/views/nodes/chatbot/chatboxcomponents/ChatBox.tsx b/src/client/views/nodes/chatbot/chatboxcomponents/ChatBox.tsx index a61705250..3ef6bdd8b 100644 --- a/src/client/views/nodes/chatbot/chatboxcomponents/ChatBox.tsx +++ b/src/client/views/nodes/chatbot/chatboxcomponents/ChatBox.tsx @@ -431,7 +431,7 @@ export class ChatBox extends ViewBoxAnnotatableComponent() { doc = Docs.Create.FunctionPlotDocument([], options); break; case 'dataviz': - case 'data_viz': + case 'data_viz': { const { fileUrl, id } = await Networking.PostToServer('/createCSV', { filename: (options.title as string).replace(/\s+/g, '') + '.csv', data: data, @@ -439,6 +439,7 @@ export class ChatBox extends ViewBoxAnnotatableComponent() { doc = Docs.Create.DataVizDocument(fileUrl, { ...options, text: RTFCast(data) }); this.addCSVForAnalysis(doc, id); break; + } case 'chat': doc = Docs.Create.ChatDocument(options); break; diff --git a/src/client/views/pdf/AnchorMenu.tsx b/src/client/views/pdf/AnchorMenu.tsx index 5ab9b556c..fe03f32a5 100644 --- a/src/client/views/pdf/AnchorMenu.tsx +++ b/src/client/views/pdf/AnchorMenu.tsx @@ -131,12 +131,15 @@ export class AnchorMenu extends AntimodeMenu { /** * Creates a GPT drawing based on selected text. */ - gptDraw = async (e: React.PointerEvent) => { + gptDraw = (e: React.PointerEvent) => { try { SmartDrawHandler.Instance.AddDrawing = this.createDrawingAnnotation; runInAction(() => (this._isLoading = true)); - await SmartDrawHandler.Instance.drawWithGPT({ X: e.clientX, Y: e.clientY }, this._selectedText, 5, 100, true); - runInAction(() => (this._isLoading = false)); + SmartDrawHandler.Instance.drawWithGPT({ X: e.clientX, Y: e.clientY }, this._selectedText, 5, 100, true)?.then( + action(() => { + this._isLoading = false; + }) + ); } catch (err) { console.error(err); } diff --git a/src/client/views/smartdraw/SmartDrawHandler.tsx b/src/client/views/smartdraw/SmartDrawHandler.tsx index d0f6566a5..342b91bd9 100644 --- a/src/client/views/smartdraw/SmartDrawHandler.tsx +++ b/src/client/views/smartdraw/SmartDrawHandler.tsx @@ -13,6 +13,7 @@ import { Doc, DocListCast } from '../../../fields/Doc'; import { DocData } from '../../../fields/DocSymbols'; import { InkData, InkField, InkTool } from '../../../fields/InkField'; import { BoolCast, ImageCast, NumCast, StrCast } from '../../../fields/Types'; +import { Networking } from '../../Network'; import { GPTCallType, gptAPICall, gptDrawingColor } from '../../apis/gpt/GPT'; import { Docs } from '../../documents/Documents'; import { SettingsManager } from '../../util/SettingsManager'; @@ -21,7 +22,8 @@ import { SVGToBezier, SVGType } from '../../util/bezierFit'; import { InkingStroke } from '../InkingStroke'; import { ObservableReactComponent } from '../ObservableReactComponent'; import { MarqueeView } from '../collections/collectionFreeForm'; -import { ActiveInkArrowEnd, ActiveInkArrowStart, ActiveInkDash, ActiveInkFillColor, ActiveInkBezierApprox, ActiveInkColor, ActiveInkWidth, ActiveIsInkMask, DocumentView } from '../nodes/DocumentView'; +import { ActiveInkArrowEnd, ActiveInkArrowStart, ActiveInkBezierApprox, ActiveInkColor, ActiveInkDash, ActiveInkFillColor, ActiveInkWidth, ActiveIsInkMask, DocumentView, DocumentViewInternal } from '../nodes/DocumentView'; +import { OpenWhere } from '../nodes/OpenWhere'; import './SmartDrawHandler.scss'; export interface DrawingOptions { @@ -230,20 +232,21 @@ export class SmartDrawHandler extends ObservableReactComponent { * Calls GPT API to create a drawing based on user input. */ @action - drawWithGPT = async (startPt: { X: number; Y: number }, input: string, complexity: number, size: number, autoColor: boolean) => { - if (input === '') return; - this._lastInput = { text: input, complexity: complexity, size: size, autoColor: autoColor, x: startPt.X, y: startPt.Y }; - const res = await gptAPICall(`"${input}", "${complexity}", "${size}"`, GPTCallType.DRAW, undefined, true); - if (!res) { - console.error('GPT call failed'); - return; - } - const strokeData = await this.parseSvg(res, startPt, false, autoColor); - const drawingDoc = strokeData && this.CreateDrawingDoc(strokeData.data, strokeData.lastInput, strokeData.lastRes); - drawingDoc && this.AddDrawing(drawingDoc, this._lastInput, res); + drawWithGPT = (startPt: { X: number; Y: number }, prompt: string, complexity: number, size: number, autoColor: boolean) => { + if (prompt === '') return; + this._lastInput = { text: prompt, complexity: complexity, size: size, autoColor: autoColor, x: startPt.X, y: startPt.Y }; + + Networking.PostToServer('/queryFireflyImage', { prompt }).then(img => DocumentViewInternal.addDocTabFunc(Docs.Create.ImageDocument(img, { title: prompt }), OpenWhere.addRight)); + + const result = gptAPICall(`"${prompt}", "${complexity}", "${size}"`, GPTCallType.DRAW, undefined, true).then(res => + this.parseSvg(res, startPt, false, autoColor).then(strokeData => { + const drawingDoc = strokeData && this.CreateDrawingDoc(strokeData.data, strokeData.lastInput, strokeData.lastRes); + drawingDoc && this.AddDrawing(drawingDoc, this._lastInput, res); + }) + ); this._errorOccurredOnce = false; - return strokeData; + return result; }; /** diff --git a/src/server/ApiManagers/DataVizManager.ts b/src/server/ApiManagers/DataVizManager.ts index 88f22992d..d2028f23b 100644 --- a/src/server/ApiManagers/DataVizManager.ts +++ b/src/server/ApiManagers/DataVizManager.ts @@ -9,7 +9,7 @@ export default class DataVizManager extends ApiManager { register({ method: Method.GET, subscription: '/csvData', - secureHandler: async ({ req, res }) => { + secureHandler: ({ req, res }) => { const uri = req.query.uri as string; return new Promise(resolve => { diff --git a/src/server/ApiManagers/FireflyManager.ts b/src/server/ApiManagers/FireflyManager.ts new file mode 100644 index 000000000..04fa8f065 --- /dev/null +++ b/src/server/ApiManagers/FireflyManager.ts @@ -0,0 +1,51 @@ +import { DashUploadUtils } from '../DashUploadUtils'; +import { _invalid, _success, Method } from '../RouteManager'; +import ApiManager, { Registration } from './ApiManager'; + +export default class FireflyManager extends ApiManager { + askFirefly = (prompt: string = 'a realistic illustration of a cat coding') => { + const fetched = fetch('https://ims-na1.adobelogin.com/ims/token/v3', { + method: 'POST', + headers: { + 'Content-Type': 'application/x-www-form-urlencoded', + }, + body: `grant_type=client_credentials&client_id=${process.env._CLIENT_FIREFLY_CLIENT_ID}&client_secret=${process.env._CLIENT_FIREFLY_SECRET}&scope=openid,AdobeID,session,additional_info,read_organizations,firefly_api,ff_apis`, + }) + .then(response => response.json()) + .then((data: { access_token: string }) => + fetch('https://firefly-api.adobe.io/v3/images/generate', { + method: 'POST', + headers: [ + ['Content-Type', 'application/json'], + ['Accept', 'application/json'], + ['x-api-key', process.env._CLIENT_FIREFLY_CLIENT_ID ?? ''], + ['Authorization', `Bearer ${data.access_token}`], + ], + body: `{ "prompt": "${prompt}" }`, + }) + .then(response => response.json().then(json => JSON.stringify((json.outputs?.[0] as { image: { url: string } })?.image))) + .catch(error => { + console.error('Error:', error); + return ''; + }) + ) + .catch(error => { + console.error('Error:', error); + return ''; + }); + return fetched; + }; + protected initialize(register: Registration): void { + register({ + method: Method.POST, + subscription: '/queryFireflyImage', + secureHandler: ({ req, res }) => + this.askFirefly(req.body.prompt).then(fire => + DashUploadUtils.UploadImage(JSON.parse(fire).url).then(info => { + if (info instanceof Error) _invalid(res, info.message); + else _success(res, info.accessPaths.agnostic.client); + }) + ), + }); + } +} diff --git a/src/server/DashUploadUtils.ts b/src/server/DashUploadUtils.ts index 1e55a885a..032d13d43 100644 --- a/src/server/DashUploadUtils.ts +++ b/src/server/DashUploadUtils.ts @@ -369,7 +369,8 @@ export namespace DashUploadUtils { */ export const UploadInspectedImage = async (metadata: Upload.InspectionResults, filename: string, prefix = '', cleanUp = true): Promise => { const { requestable, source, ...remaining } = metadata; - const resolved = filename || `${prefix}upload_${Utils.GenerateGuid()}.${remaining.contentType.split('/')[1].toLowerCase()}`; + const dfltSuffix = remaining.contentType.split('/')[1].toLowerCase(); + const resolved = filename || `${prefix}upload_${Utils.GenerateGuid()}.${dfltSuffix === 'xml' ? 'jpg' : dfltSuffix}`; const { images } = Directory; const information: Upload.ImageInformation = { accessPaths: { diff --git a/src/server/index.ts b/src/server/index.ts index 88dbd232d..1f9af9ee0 100644 --- a/src/server/index.ts +++ b/src/server/index.ts @@ -7,6 +7,7 @@ import AssistantManager from './ApiManagers/AssistantManager'; import DataVizManager from './ApiManagers/DataVizManager'; import DeleteManager from './ApiManagers/DeleteManager'; import DownloadManager from './ApiManagers/DownloadManager'; +import FireflyManager from './ApiManagers/FireflyManager'; import GeneralGoogleManager from './ApiManagers/GeneralGoogleManager'; import SessionManager from './ApiManagers/SessionManager'; import UploadManager from './ApiManagers/UploadManager'; @@ -71,6 +72,7 @@ function routeSetter({ addSupervisedRoute, logRegistrationOutcome }: RouteManage new GeneralGoogleManager(), /* new GooglePhotosManager(), */ new DataVizManager(), new AssistantManager(), + new FireflyManager(), ]; // initialize API Managers @@ -112,7 +114,6 @@ function routeSetter({ addSupervisedRoute, logRegistrationOutcome }: RouteManage }); const serve: PublicHandler = ({ req, res }) => { - // eslint-disable-next-line new-cap const detector = new mobileDetect(req.headers['user-agent'] || ''); const filename = detector.mobile() !== null ? 'mobile/image.html' : 'index.html'; res.sendFile(path.join(__dirname, '../../deploy/' + filename)); diff --git a/webpack.config.js b/webpack.config.js index e1afc64e5..67417fb02 100644 --- a/webpack.config.js +++ b/webpack.config.js @@ -1,4 +1,4 @@ -/* eslint-disable @typescript-eslint/no-var-requires */ +/* eslint-disable @typescript-eslint/no-require-imports */ const path = require('path'); const webpack = require('webpack'); const HtmlWebpackPlugin = require('html-webpack-plugin'); @@ -36,7 +36,6 @@ function transferEnvironmentVariables() { } const resolvedClientSide = Object.keys(parsed).reduce((mapping, envKey) => { if (envKey.startsWith(prefix)) { - // eslint-disable-next-line mapping[`process.env.${envKey.replace(prefix, '')}`] = JSON.stringify(parsed[envKey]); } return mapping; @@ -112,7 +111,7 @@ module.exports = { test: /\.scss|css$/, exclude: /\.module\.scss$/i, use: [ - { loader: 'style-loader' }, // eslint-disable-next-line prettier/prettier + { loader: 'style-loader' }, // { loader: 'css-loader' }, { loader: 'sass-loader' }, ], @@ -127,7 +126,7 @@ module.exports = { { test: /\.module\.scss$/i, use: [ - { loader: 'style-loader' }, // eslint-disable-next-line prettier/prettier + { loader: 'style-loader' }, // { loader: 'css-loader', options: { modules: true } }, { loader: 'sass-loader' }, ], -- cgit v1.2.3-70-g09d2 From 50fb7536822269b3735e2fc7e3e70ca816529799 Mon Sep 17 00:00:00 2001 From: bobzel Date: Fri, 22 Nov 2024 10:53:40 -0500 Subject: Update FireflyManager.ts --- src/server/ApiManagers/FireflyManager.ts | 37 +++++++++++++++----------------- 1 file changed, 17 insertions(+), 20 deletions(-) (limited to 'src/server/ApiManagers') diff --git a/src/server/ApiManagers/FireflyManager.ts b/src/server/ApiManagers/FireflyManager.ts index 04fa8f065..a110d112f 100644 --- a/src/server/ApiManagers/FireflyManager.ts +++ b/src/server/ApiManagers/FireflyManager.ts @@ -3,32 +3,29 @@ import { _invalid, _success, Method } from '../RouteManager'; import ApiManager, { Registration } from './ApiManager'; export default class FireflyManager extends ApiManager { - askFirefly = (prompt: string = 'a realistic illustration of a cat coding') => { - const fetched = fetch('https://ims-na1.adobelogin.com/ims/token/v3', { + getBearerToken = () => + fetch('https://ims-na1.adobelogin.com/ims/token/v3', { method: 'POST', headers: { 'Content-Type': 'application/x-www-form-urlencoded', }, body: `grant_type=client_credentials&client_id=${process.env._CLIENT_FIREFLY_CLIENT_ID}&client_secret=${process.env._CLIENT_FIREFLY_SECRET}&scope=openid,AdobeID,session,additional_info,read_organizations,firefly_api,ff_apis`, + }).catch(error => { + console.error('Error:', error); + return ''; + }); + askFirefly = (prompt: string = 'a realistic illustration of a cat coding') => { + const fetched = fetch('https://firefly-api.adobe.io/v3/images/generate', { + method: 'POST', + headers: [ + ['Content-Type', 'application/json'], + ['Accept', 'application/json'], + ['x-api-key', process.env._CLIENT_FIREFLY_CLIENT_ID ?? ''], + ['Authorization', `Bearer ${process.env._CLIENT_FIREFLY_BEARER_TOKEN}`], + ], + body: `{ "prompt": "${prompt}" }`, }) - .then(response => response.json()) - .then((data: { access_token: string }) => - fetch('https://firefly-api.adobe.io/v3/images/generate', { - method: 'POST', - headers: [ - ['Content-Type', 'application/json'], - ['Accept', 'application/json'], - ['x-api-key', process.env._CLIENT_FIREFLY_CLIENT_ID ?? ''], - ['Authorization', `Bearer ${data.access_token}`], - ], - body: `{ "prompt": "${prompt}" }`, - }) - .then(response => response.json().then(json => JSON.stringify((json.outputs?.[0] as { image: { url: string } })?.image))) - .catch(error => { - console.error('Error:', error); - return ''; - }) - ) + .then(response => response.json().then(json => JSON.stringify((json.outputs?.[0] as { image: { url: string } })?.image))) .catch(error => { console.error('Error:', error); return ''; -- cgit v1.2.3-70-g09d2 From 2fee49a7cd342331633bf39d1ac837838d252a18 Mon Sep 17 00:00:00 2001 From: bobzel Date: Fri, 22 Nov 2024 15:00:07 -0500 Subject: switched to providing secret instead of bearer token for adobe api access --- src/server/ApiManagers/FireflyManager.ts | 34 ++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 15 deletions(-) (limited to 'src/server/ApiManagers') diff --git a/src/server/ApiManagers/FireflyManager.ts b/src/server/ApiManagers/FireflyManager.ts index a110d112f..5e3ba1f83 100644 --- a/src/server/ApiManagers/FireflyManager.ts +++ b/src/server/ApiManagers/FireflyManager.ts @@ -15,21 +15,25 @@ export default class FireflyManager extends ApiManager { return ''; }); askFirefly = (prompt: string = 'a realistic illustration of a cat coding') => { - const fetched = fetch('https://firefly-api.adobe.io/v3/images/generate', { - method: 'POST', - headers: [ - ['Content-Type', 'application/json'], - ['Accept', 'application/json'], - ['x-api-key', process.env._CLIENT_FIREFLY_CLIENT_ID ?? ''], - ['Authorization', `Bearer ${process.env._CLIENT_FIREFLY_BEARER_TOKEN}`], - ], - body: `{ "prompt": "${prompt}" }`, - }) - .then(response => response.json().then(json => JSON.stringify((json.outputs?.[0] as { image: { url: string } })?.image))) - .catch(error => { - console.error('Error:', error); - return ''; - }); + const fetched = this.getBearerToken().then(response => + response.json().then((data: { access_token: string }) => + fetch('https://firefly-api.adobe.io/v3/images/generate', { + method: 'POST', + headers: [ + ['Content-Type', 'application/json'], + ['Accept', 'application/json'], + ['x-api-key', process.env._CLIENT_FIREFLY_CLIENT_ID ?? ''], + ['Authorization', `Bearer ${data.access_token}`], + ], + body: `{ "prompt": "${prompt}" }`, + }) + .then(response => response.json().then(json => JSON.stringify((json.outputs?.[0] as { image: { url: string } })?.image))) + .catch(error => { + console.error('Error:', error); + return ''; + }) + ) + ); return fetched; }; protected initialize(register: Registration): void { -- cgit v1.2.3-70-g09d2