Files
zeekay 7e26aa9653 feat(rag): finish the cutover — retrieval + vector cleanup on the one surface
The first pass moved ingestion; these are the paths that still read RAG_API_URL,
which the universe change removes. Left as-is they would have silently degraded:
file_search and the context handler would stop retrieving, and deleting an S3 object
would orphan its embeddings.

- file_search (api/app/clients/tools/util/fileSearch.js) queries through RagClient;
  `req` is threaded from handleTools (as `options.req`, the same value that file
  already passes to resolveTenantBearer for images) so retrieval runs on the user's
  own IAM bearer instead of a chat-minted short-lived token.
- createContextHandlers uses the client for both shapes (full context + top-k),
  normalised to { data } so its callers are untouched.
- deleting an S3 object now drops the file's chunks via the same client rather than
  the legacy deleteRagFile (which reads RAG_API_URL and would have no-op'd) —
  best-effort, so a retrieval-side failure never blocks the object delete.

Dead code removed with the paths they served: the axios import and createQueryBody
body-builder in fileSearch, the deleteRagFile import in S3 crud.

Tests 11/11 (7 client + 4 key convention; the S3 spec mocks the client). Lint clean
on every touched file — the one remaining handleTools prettier error is pre-existing
(3 on clean main, 1 after this).

packages/api/src/files/{text,rag}.ts and app/checks.ts still name RAG_API_URL; all
three already guard on it and degrade gracefully (native text parsing, no-op delete,
a startup log), so they are inert once the var is gone — they come out with the
package's own pass rather than being half-migrated here.
2026-07-26 14:13:26 -07:00

185 lines
6.8 KiB
JavaScript

const { tool } = require('@langchain/core/tools');
const { logger } = require('@hanzochat/data-schemas');
const ragClient = require('~/server/services/RagClient');
const { generateShortLivedToken } = require('@hanzochat/api');
const { Tools, EToolResources } = require('@hanzochat/data-provider');
const { filterFilesByAgentAccess } = require('~/server/services/Files/permissions');
const { getFiles } = require('~/models');
const fileSearchJsonSchema = {
type: 'object',
properties: {
query: {
type: 'string',
description:
"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.",
},
},
required: ['query'],
};
/**
*
* @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 {string} options.userId
* @param {Array<{ file_id: string; filename: string }>} options.files
* @param {string} [options.entity_id]
* @param {boolean} [options.fileCitations=false] - Whether to include citation instructions
* @returns
*/
const createFileSearchTool = async ({ req, userId, files, entity_id, fileCitations = false }) => {
return tool(
async ({ query }) => {
if (files.length === 0) {
return ['No files to search. Instruct the user to add files for the search.', undefined];
}
const jwtToken = generateShortLivedToken(userId);
if (!jwtToken) {
return ['There was an error authenticating the file search request.', undefined];
}
const queryPromises = files.map((file) =>
ragClient
.query(req, {
query,
file_id: file.file_id,
k: +process.env.FILE_SEARCH_RESULTS || 5,
...(entity_id ? { store: entity_id } : {}),
})
.then((data) => ({ data }))
.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.', undefined];
}
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,
})),
)
.sort((a, b) => a.distance - b.distance)
.slice(0, 10);
if (formattedResults.length === 0) {
return [
'No content found in the files. The files may not have been processed correctly or you may need to refine your query.',
undefined,
];
}
const formattedString = formattedResults
.map(
(result, index) =>
`File: ${result.filename}${
fileCitations ? `\nAnchor: \\ue202turn0file${index} (${result.filename})` : ''
}\nRelevance: ${(1.0 - result.distance).toFixed(4)}\nContent: ${result.content}\n`,
)
.join('\n---\n');
const sources = formattedResults.map((result) => ({
type: 'file',
fileId: result.file_id,
content: result.content,
fileName: result.filename,
relevance: 1.0 - result.distance,
pages: result.page ? [result.page] : [],
pageRelevance: result.page ? { [result.page]: 1.0 - result.distance } : {},
}));
return [formattedString, { [Tools.file_search]: { sources, fileCitations } }];
},
{
name: Tools.file_search,
responseFormat: 'content_and_artifact',
description: `Performs semantic search across attached "${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.${
fileCitations
? `
**CITE FILE SEARCH RESULTS:**
Use the EXACT anchor markers shown below (copy them verbatim) 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"
**CRITICAL:** Output these escape sequences EXACTLY as shown (e.g., \\ue202turn0file0). Do NOT substitute with other characters like † or similar symbols.
**ALWAYS mention the filename in your text before the citation marker. NEVER use markdown links or footnotes.**`
: ''
}`,
schema: fileSearchJsonSchema,
},
);
};
module.exports = { createFileSearchTool, primeFiles, fileSearchJsonSchema };