🔍 feat: Mistral OCR API / Upload Files as Text (#6274)

* refactor: move `loadAuthValues` to `~/services/Tools/credentials`

* feat: add createAxiosInstance function to configure axios with proxy support

* WIP: First pass mistral ocr

* refactor: replace getConvoFiles with getToolFiles for improved file retrieval logic

* refactor: improve document formatting in encodeAndFormat function

* refactor: remove unused resendFiles parameter from buildOptions function (this option comes from the agent config)

* fix: update getFiles call to include files with `text` property as well

* refactor: move file handling to `initializeAgentOptions`

* refactor: enhance addImageURLs method to handle OCR text and improve message formatting

* refactor: update message formatting to handle OCR text in various content types

* refactor: remove unused resendFiles property from compactAgentsSchema

* fix: add error handling for Mistral OCR document upload and logging

* refactor: integrate OCR capability into file upload options and configuration

* refactor: skip processing for text source files in delete request, as they are directly tied to database

* feat: add metadata field to ExtendedFile type and update PanelColumns and PanelTable components for localization and metadata handling

* fix: source icon styling

* wip: first pass, frontend file context agent resources

* refactor: add hover card with contextual information for File Context (OCR) in FileContext component

* feat: enhance file processing by integrating file retrieval for OCR resources in agent initialization

* feat: implement OCR config; fix: agent resource deletion for ocr files

* feat: enhance agent initialization by adding OCR capability check in resource priming

* ci: fix `~/config` module mock

* ci: add OCR property expectation in AppService tests

* refactor: simplify OCR config loading by removing environment variable extraction, to be done when OCR is actually performed

* ci: add unit test to ensure environment variable references are not parsed in OCR config

* refactor: disable base64 image inclusion in OCR request

* refactor: enhance OCR configuration handling by validating environment variables and providing defaults

* refactor: use file stream from disk for mistral ocr api
This commit is contained in:
Danny Avila 2025-03-10 17:23:46 -04:00 committed by GitHub
parent 9db00edfc4
commit ded3cd8876
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
48 changed files with 1621 additions and 131 deletions

View file

@ -21,6 +21,7 @@ const {
} = require('../');
const { primeFiles: primeCodeFiles } = require('~/server/services/Files/Code/process');
const { createFileSearchTool, primeFiles: primeSearchFiles } = require('./fileSearch');
const { loadAuthValues } = require('~/server/services/Tools/credentials');
const { createMCPTool } = require('~/server/services/MCP');
const { loadSpecs } = require('./loadSpecs');
const { logger } = require('~/config');
@ -90,45 +91,6 @@ const validateTools = async (user, tools = []) => {
}
};
const loadAuthValues = async ({ userId, authFields, throwError = true }) => {
let authValues = {};
/**
* Finds the first non-empty value for the given authentication field, supporting alternate fields.
* @param {string[]} fields Array of strings representing the authentication fields. Supports alternate fields delimited by "||".
* @returns {Promise<{ authField: string, authValue: string} | null>} An object containing the authentication field and value, or null if not found.
*/
const findAuthValue = async (fields) => {
for (const field of fields) {
let value = process.env[field];
if (value) {
return { authField: field, authValue: value };
}
try {
value = await getUserPluginAuthValue(userId, field, throwError);
} catch (err) {
if (field === fields[fields.length - 1] && !value) {
throw err;
}
}
if (value) {
return { authField: field, authValue: value };
}
}
return null;
};
for (let authField of authFields) {
const fields = authField.split('||');
const result = await findAuthValue(fields);
if (result) {
authValues[result.authField] = result.authValue;
}
}
return authValues;
};
/** @typedef {typeof import('@langchain/core/tools').Tool} ToolConstructor */
/** @typedef {import('@langchain/core/tools').Tool} Tool */
@ -348,7 +310,6 @@ const loadTools = async ({
module.exports = {
loadToolWithAuth,
loadAuthValues,
validateTools,
loadTools,
};