aboutsummaryrefslogtreecommitdiff
path: root/src/server/ApiManagers/AssistantManager.ts
diff options
context:
space:
mode:
Diffstat (limited to 'src/server/ApiManagers/AssistantManager.ts')
-rw-r--r--src/server/ApiManagers/AssistantManager.ts157
1 files changed, 100 insertions, 57 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' };
+ }
}
});
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-10-06 13:55:29 +0000