diff options
Diffstat (limited to 'src/server')
| -rw-r--r-- | src/server/ApiManagers/AssistantManager.ts | 157 | ||||
| -rw-r--r-- | src/server/ApiManagers/DataVizManager.ts | 2 | ||||
| -rw-r--r-- | src/server/DashUploadUtils.ts | 15 | ||||
| -rw-r--r-- | src/server/chunker/pdf_chunker.py | 70 | ||||
| -rw-r--r-- | src/server/index.ts | 3 |
5 files changed, 150 insertions, 97 deletions
diff --git a/src/server/ApiManagers/AssistantManager.ts b/src/server/ApiManagers/AssistantManager.ts index 8447a4934..4d2068014 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'; @@ -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 { @@ -115,29 +116,79 @@ 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({ @@ -299,47 +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' }); } @@ -367,7 +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 @@ -445,10 +465,12 @@ 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 = ''; @@ -460,23 +482,30 @@ 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); } } }); @@ -490,10 +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/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<void>(resolve => { diff --git a/src/server/DashUploadUtils.ts b/src/server/DashUploadUtils.ts index 1e55a885a..351351ca5 100644 --- a/src/server/DashUploadUtils.ts +++ b/src/server/DashUploadUtils.ts @@ -1,3 +1,4 @@ +/* eslint-disable no-use-before-define */ import axios from 'axios'; import { exec, spawn } from 'child_process'; import { green, red } from 'colors'; @@ -47,7 +48,8 @@ if (isMainThread) { async function workerResampleImage(message: { imgSourcePath: string; outputPath: string; origSuffix: string; unlinkSource: boolean }) { const { imgSourcePath, outputPath, origSuffix, unlinkSource } = message; - const sizes = !origSuffix ? [{ width: 400, suffix: SizeSuffix.Medium }] : DashUploadUtils.imageResampleSizes(path.extname(imgSourcePath)); + const extension = path.extname(imgSourcePath); + const sizes = !origSuffix ? [{ width: 400, suffix: SizeSuffix.Medium }] : DashUploadUtils.imageResampleSizes(extension === '.xml' ? '.png' : extension); // prettier-ignore Jimp.read(imgSourcePath) .then(img => @@ -60,7 +62,7 @@ if (isMainThread) { } } -// eslint-disable-next-line @typescript-eslint/no-var-requires +// eslint-disable-next-line @typescript-eslint/no-require-imports const requestImageSize = require('../client/util/request-image-size'); export enum SizeSuffix { @@ -369,7 +371,8 @@ export namespace DashUploadUtils { */ export const UploadInspectedImage = async (metadata: Upload.InspectionResults, filename: string, prefix = '', cleanUp = true): Promise<Upload.ImageInformation> => { 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: { @@ -400,10 +403,10 @@ export namespace DashUploadUtils { writtenFiles = {}; } } else { - const unlinkSrcWhenFinished = isLocal().test(source) && cleanUp; + const unlinkSrcWhenFinished = cleanUp; // isLocal().test(source) && cleanUp; try { writtenFiles = await outputResizedImages(metadata.source, resolved, unlinkSrcWhenFinished); - } catch (e) { + } catch { // input is a blob or other, try reading it to create a metadata source file. const reqSource = request(metadata.source); const readStream: Stream = reqSource instanceof Promise ? await reqSource : reqSource; @@ -415,7 +418,7 @@ export namespace DashUploadUtils { .on('error', () => rej()); }); writtenFiles = await outputResizedImages(readSource, resolved, unlinkSrcWhenFinished); - fs.unlink(readSource, err => console.log("Couldn't unlink temporary image file:" + readSource, err)); + //fs.unlink(readSource, err => console.log("Couldn't unlink temporary image file:" + readSource, err)); } } Array.from(Object.keys(writtenFiles)).forEach(suffix => { diff --git a/src/server/chunker/pdf_chunker.py b/src/server/chunker/pdf_chunker.py index 4fe3b9dbf..48b2dbf97 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: @@ -63,13 +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 @@ -116,17 +119,16 @@ class ElementExtractor: 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) + file_path_for_client = f"{self.doc_id}/{table_filename}" 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) } }) @@ -175,18 +177,17 @@ class ElementExtractor: 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) + file_path_for_client = f"{self.doc_id}/{image_filename}" 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) } }) @@ -268,7 +269,7 @@ 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. @@ -278,7 +279,8 @@ 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]]: """ @@ -363,6 +365,7 @@ 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 @@ -628,10 +631,11 @@ 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): """ @@ -664,7 +668,7 @@ 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 +676,7 @@ 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 +685,13 @@ 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, 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 @@ -796,8 +800,7 @@ 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 +809,30 @@ 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: + os.makedirs(output_folder, exist_ok=True) + # 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 +844,6 @@ def main(): sys.stderr.flush() + if __name__ == "__main__": main() # Execute the main function when the script is run 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)); |