OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.
Python
import path from "path";
import { ACTIVE_PROVIDER_CONFIG } from "../config/provider";
import { expect, test } from "../utils/fixtures";
import logger from "../utils/logger";
import { navigateToHome } from "../utils/navigation";
const TEST_DOCUMENT = "OpenRAG.Index.Test.Document.txt";
const TEST_DOCUMENT_PATH = path.join(__dirname, "../test-data", TEST_DOCUMENT);
const UNIQUE_SEARCH_TOKEN = "OPENSEARCH-7419-ZX";
test(`Opensearch Indexing - ${ACTIVE_PROVIDER_CONFIG.provider} @33219220`, async ({
page,
settings,
knowledge,
cleanupDocuments,
}) => {
test.setTimeout(180000);
// Navigate to the application
await navigateToHome(page);
logger.info(
`\nπ§ͺ Testing Opensearch Indexing with ${ACTIVE_PROVIDER_CONFIG.provider}`,
);
logger.info(` π§Ή Cleaning up existing test document...`);
try {
await knowledge.deleteDocument(TEST_DOCUMENT);
logger.info(` β Test document cleaned up`);
} catch (_error) {
logger.info(` βΉοΈ No existing test document to clean up`);
}
// Step 2: Set embedding model for active provider
logger.info(
` βοΈ Setting embedding model for ${ACTIVE_PROVIDER_CONFIG.provider}...`,
);
await settings.clickTab("Ingestion");
await settings.selectModel(
"Embedding model",
ACTIVE_PROVIDER_CONFIG.embedding,
);
logger.info(
` β Embedding model set to: ${ACTIVE_PROVIDER_CONFIG.embedding}`,
);
// Step 3: Ingest the test document
logger.info(` π Ingesting test document...`);
const ingestedFileName = await knowledge.ingestFile(TEST_DOCUMENT_PATH);
logger.info(` β Document ingested: ${ingestedFileName}`);
// Register for cleanup
await cleanupDocuments([TEST_DOCUMENT]);
// Step 4: Wait for document to be indexed (Active status)
logger.info(` β³ Waiting for document to be indexed...`);
await knowledge.verifyDocumentActive(TEST_DOCUMENT);
logger.info(` β Document is indexed and active`);
// Step 5: Search for the unique token
// Note: Search works for content within documents, not document names
logger.info(` π Searching for unique token: ${UNIQUE_SEARCH_TOKEN}`);
const searchResults = await knowledge.getSearchResults(UNIQUE_SEARCH_TOKEN);
logger.info(` π Search results: ${searchResults.length} document(s) found`);
searchResults.forEach((doc, index) => {
logger.info(` ${index + 1}. ${doc}`);
});
// Step 6: Verify results
// The test document must be in the results (other documents may also appear)
const targetDocumentFound = searchResults.includes(TEST_DOCUMENT);
if (!targetDocumentFound) {
throw new Error(
`β FAILED: Test document "${TEST_DOCUMENT}" not found in search results for token "${UNIQUE_SEARCH_TOKEN}"\n` +
` Search returned ${searchResults.length} document(s): ${searchResults.join(", ")}\n` +
` This means the document was not properly indexed or the search functionality is not working.`,
);
}
// Success!
if (searchResults.length === 1) {
logger.info(` β
SUCCESS: "${TEST_DOCUMENT}" found as the only result`);
} else {
const otherDocs = searchResults.filter((doc) => doc !== TEST_DOCUMENT);
logger.info(` β
SUCCESS: "${TEST_DOCUMENT}" found in results`);
logger.info(
` βΉοΈ Also found ${otherDocs.length} other document(s): ${otherDocs.join(", ")}`,
);
}
logger.info(` β Opensearch indexing verified for Azure OpenAI\n`);
// Assertions for Playwright reporting
expect(targetDocumentFound).toBe(true);
expect(searchResults).toContain(TEST_DOCUMENT);
});