mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-09-22 08:12:00 +02:00

* 🪶 feat: Add Support for Uploading Plaintext Files feat: delineate between OCR and text handling in fileConfig field of config file - also adds support for passing in mimetypes as just plain file extensions feat: add showLabel bool to support future synthetic component DynamicDropdownInput feat: add new combination dropdown-input component in params panel to support file type token limits refactor: move hovercard to side to align with other hovercards chore: clean up autogenerated comments feat: add delineation to file upload path between text and ocr configured filetypes feat: add token limit checks during file upload refactor: move textParsing out of ocrEnabled logic refactor: clean up types for filetype config refactor: finish decoupling DynamicDropdownInput from fileTokenLimits fix: move image token cost function into file to fix circular dependency causing unittest to fail and remove unused var for linter chore: remove out of scope code following review refactor: make fileTokenLimit conform to existing styles chore: remove unused localization string chore: undo changes to DynamicInput and other strays feat: add fileTokenLimit to all provider config panels fix: move textParsing back into ocr tool_resource block for now so that it doesn't interfere with other upload types * 📤 feat: Add RAG API Endpoint Support for Text Parsing (#8849) * feat: implement RAG API integration for text parsing with fallback to native parsing * chore: remove TODO now that placeholder and fllback are implemented * ✈️ refactor: Migrate Text Parsing to TS (#8892) * refactor: move generateShortLivedToken to packages/api * refactor: move textParsing logic into packages/api * refactor: reduce nesting and dry code with createTextFile * fix: add proper source handling * fix: mock new parseText and parseTextNative functions in jest file * ci: add test coverage for textParser * 💬 feat: Add Audio File Support to Upload as Text (#8893) * feat: add STT support for Upload as Text * refactor: move processAudioFile to packages/api * refactor: move textParsing from utils to files * fix: remove audio/mp3 from unsupported mimetypes test since it is now supported * ✂️ feat: Configurable File Token Limits and Truncation (#8911) * feat: add configurable fileTokenLimit default value * fix: add stt to fileConfig merge logic * fix: add fileTokenLimit to mergeFileConfig logic so configurable value is actually respected from yaml * feat: add token limiting to parsed text files * fix: add extraction logic and update tests so fileTokenLimit isnt sent to LLM providers * fix: address comments * refactor: rename textTokenLimiter.ts to text.ts * chore: update form-data package to address CVE-2025-7783 and update package-lock * feat: use default supported mime types for ocr on frontend file validation * fix: should be using logger.debug not console.debug * fix: mock existsSync in text.spec.ts * fix: mock logger rather than every one of its function calls * fix: reorganize imports and streamline file upload processing logic * refactor: update createTextFile function to use destructured parameters and improve readability * chore: update file validation to use EToolResources for improved type safety * chore: update import path for types in audio processing module * fix: update file configuration access and replace console.debug with logger.debug for improved logging --------- Co-authored-by: Dustin Healy <dustinhealy1@gmail.com> Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>
186 lines
6.6 KiB
JavaScript
186 lines
6.6 KiB
JavaScript
const { z } = require('zod');
|
|
const axios = require('axios');
|
|
const { tool } = require('@langchain/core/tools');
|
|
const { logger } = require('@librechat/data-schemas');
|
|
const { generateShortLivedToken } = require('@librechat/api');
|
|
const { Tools, EToolResources } = require('librechat-data-provider');
|
|
const { filterFilesByAgentAccess } = require('~/server/services/Files/permissions');
|
|
const { getFiles } = require('~/models/File');
|
|
|
|
/**
|
|
*
|
|
* @param {Object} options
|
|
* @param {ServerRequest} options.req
|
|
* @param {Agent['tool_resources']} options.tool_resources
|
|
* @param {string} [options.agentId] - The agent ID for file access control
|
|
* @returns {Promise<{
|
|
* files: Array<{ file_id: string; filename: string }>,
|
|
* toolContext: string
|
|
* }>}
|
|
*/
|
|
const primeFiles = async (options) => {
|
|
const { tool_resources, req, agentId } = options;
|
|
const file_ids = tool_resources?.[EToolResources.file_search]?.file_ids ?? [];
|
|
const agentResourceIds = new Set(file_ids);
|
|
const resourceFiles = tool_resources?.[EToolResources.file_search]?.files ?? [];
|
|
|
|
// Get all files first
|
|
const allFiles = (await getFiles({ file_id: { $in: file_ids } }, null, { text: 0 })) ?? [];
|
|
|
|
// Filter by access if user and agent are provided
|
|
let dbFiles;
|
|
if (req?.user?.id && agentId) {
|
|
dbFiles = await filterFilesByAgentAccess({
|
|
files: allFiles,
|
|
userId: req.user.id,
|
|
role: req.user.role,
|
|
agentId,
|
|
});
|
|
} else {
|
|
dbFiles = allFiles;
|
|
}
|
|
|
|
dbFiles = dbFiles.concat(resourceFiles);
|
|
|
|
let toolContext = `- Note: Semantic search is available through the ${Tools.file_search} tool but no files are currently loaded. Request the user to upload documents to search through.`;
|
|
|
|
const files = [];
|
|
for (let i = 0; i < dbFiles.length; i++) {
|
|
const file = dbFiles[i];
|
|
if (!file) {
|
|
continue;
|
|
}
|
|
if (i === 0) {
|
|
toolContext = `- Note: Use the ${Tools.file_search} tool to find relevant information within:`;
|
|
}
|
|
toolContext += `\n\t- ${file.filename}${
|
|
agentResourceIds.has(file.file_id) ? '' : ' (just attached by user)'
|
|
}`;
|
|
files.push({
|
|
file_id: file.file_id,
|
|
filename: file.filename,
|
|
});
|
|
}
|
|
|
|
return { files, toolContext };
|
|
};
|
|
|
|
/**
|
|
*
|
|
* @param {Object} options
|
|
* @param {ServerRequest} options.req
|
|
* @param {Array<{ file_id: string; filename: string }>} options.files
|
|
* @param {string} [options.entity_id]
|
|
* @returns
|
|
*/
|
|
const createFileSearchTool = async ({ req, files, entity_id }) => {
|
|
return tool(
|
|
async ({ query }) => {
|
|
if (files.length === 0) {
|
|
return 'No files to search. Instruct the user to add files for the search.';
|
|
}
|
|
const jwtToken = generateShortLivedToken(req.user.id);
|
|
if (!jwtToken) {
|
|
return 'There was an error authenticating the file search request.';
|
|
}
|
|
|
|
/**
|
|
*
|
|
* @param {import('librechat-data-provider').TFile} file
|
|
* @returns {{ file_id: string, query: string, k: number, entity_id?: string }}
|
|
*/
|
|
const createQueryBody = (file) => {
|
|
const body = {
|
|
file_id: file.file_id,
|
|
query,
|
|
k: 5,
|
|
};
|
|
if (!entity_id) {
|
|
return body;
|
|
}
|
|
body.entity_id = entity_id;
|
|
logger.debug(`[${Tools.file_search}] RAG API /query body`, body);
|
|
return body;
|
|
};
|
|
|
|
const queryPromises = files.map((file) =>
|
|
axios
|
|
.post(`${process.env.RAG_API_URL}/query`, createQueryBody(file), {
|
|
headers: {
|
|
Authorization: `Bearer ${jwtToken}`,
|
|
'Content-Type': 'application/json',
|
|
},
|
|
})
|
|
.catch((error) => {
|
|
logger.error('Error encountered in `file_search` while querying file:', error);
|
|
return null;
|
|
}),
|
|
);
|
|
|
|
const results = await Promise.all(queryPromises);
|
|
const validResults = results.filter((result) => result !== null);
|
|
|
|
if (validResults.length === 0) {
|
|
return 'No results found or errors occurred while searching the files.';
|
|
}
|
|
|
|
const formattedResults = validResults
|
|
.flatMap((result, fileIndex) =>
|
|
result.data.map(([docInfo, distance]) => ({
|
|
filename: docInfo.metadata.source.split('/').pop(),
|
|
content: docInfo.page_content,
|
|
distance,
|
|
file_id: files[fileIndex]?.file_id,
|
|
page: docInfo.metadata.page || null,
|
|
})),
|
|
)
|
|
// TODO: results should be sorted by relevance, not distance
|
|
.sort((a, b) => a.distance - b.distance)
|
|
// TODO: make this configurable
|
|
.slice(0, 10);
|
|
|
|
const formattedString = formattedResults
|
|
.map(
|
|
(result, index) =>
|
|
`File: ${result.filename}\nAnchor: \\ue202turn0file${index} (${result.filename})\nRelevance: ${(1.0 - result.distance).toFixed(4)}\nContent: ${
|
|
result.content
|
|
}\n`,
|
|
)
|
|
.join('\n---\n');
|
|
|
|
const sources = formattedResults.map((result) => ({
|
|
type: 'file',
|
|
fileId: result.file_id,
|
|
content: result.content,
|
|
fileName: result.filename,
|
|
relevance: 1.0 - result.distance,
|
|
pages: result.page ? [result.page] : [],
|
|
pageRelevance: result.page ? { [result.page]: 1.0 - result.distance } : {},
|
|
}));
|
|
|
|
return [formattedString, { [Tools.file_search]: { sources } }];
|
|
},
|
|
{
|
|
name: Tools.file_search,
|
|
responseFormat: 'content_and_artifact',
|
|
description: `Performs semantic search across attached "${Tools.file_search}" documents using natural language queries. This tool analyzes the content of uploaded files to find relevant information, quotes, and passages that best match your query. Use this to extract specific information or find relevant sections within the available documents.
|
|
|
|
**CITE FILE SEARCH RESULTS:**
|
|
Use anchor markers immediately after statements derived from file content. Reference the filename in your text:
|
|
- File citation: "The document.pdf states that... \\ue202turn0file0"
|
|
- Page reference: "According to report.docx... \\ue202turn0file1"
|
|
- Multi-file: "Multiple sources confirm... \\ue200\\ue202turn0file0\\ue202turn0file1\\ue201"
|
|
|
|
**ALWAYS mention the filename in your text before the citation marker. NEVER use markdown links or footnotes.**`,
|
|
schema: z.object({
|
|
query: z
|
|
.string()
|
|
.describe(
|
|
"A natural language query to search for relevant information in the files. Be specific and use keywords related to the information you're looking for. The query will be used for semantic similarity matching against the file contents.",
|
|
),
|
|
}),
|
|
},
|
|
);
|
|
};
|
|
|
|
module.exports = { createFileSearchTool, primeFiles };
|