run-llama / create-llama

The easiest way to get started with LlamaIndex
MIT License
926 stars 116 forks source link

extractText is not a function #384

Open Robing opened 6 days ago

Robing commented 6 days ago

When uploading a PDF file in the chat window, an error occurs stating 'extractText is not a function'.

[Upload API] TypeError: extractText is not a function at readPDF (webpack-internal:///(rsc)/./nodemodules/.pnpm/llamaindex@0.6.22@aws-sdk+client-sso-oidc@3.670.0_@aws-sdk+client-sts@3.670.0@aws-sdk+cred_4cqb3jcjwdzlpa5cxd3sxc2oxe/node_modules/llamaindex/dist/readers/PDFReader.js:30:18) at async PDFReader.loadDataAsContent (webpack-internal:///(rsc)/./nodemodules/.pnpm/llamaindex@0.6.22@aws-sdk+client-sso-oidc@3.670.0_@aws-sdk+client-sts@3.670.0@aws-sdk+cred_4cqb3jcjwdzlpa5cxd3sxc2oxe/node_modules/llamaindex/dist/readers/PDFReader.js:15:38) at async loadDocuments (webpack-internal:///(rsc)/./app/api/chat/llamaindex/documents/helper.ts:67:12) at async parseFile (webpack-internal:///(rsc)/./app/api/chat/llamaindex/documents/helper.ts:50:23) at async uploadDocument (webpack-internal:///(rsc)/./app/api/chat/llamaindex/documents/upload.ts:54:23) at async POST (webpack-internal:///(rsc)/./app/api/chat/upload/route.ts:29:75) at async /Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/compiled/next-server/app-route.runtime.dev.js:6:55778 at async eO.execute (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/compiled/next-server/app-route.runtime.dev.js:6:46527) at async eO.handle (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/compiled/next-server/app-route.runtime.dev.js:6:57112) at async doRender (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1__react@18.3.1/node_modules/next/dist/server/base-server.js:1352:42) at async cacheEntry.responseCache.get.routeKind (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/base-server.js:1574:28) at async DevServer.renderToResponseWithComponentsImpl (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/base-server.js:1482:28) at async DevServer.renderPageComponent (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1__react@18.3.1/node_modules/next/dist/server/base-server.js:1908:24) at async DevServer.renderToResponseImpl (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/base-server.js:1946:32) at async DevServer.pipeImpl (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/base-server.js:921:25) at async NextNodeServer.handleCatchallRenderRequest (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1__react@18.3.1/node_modules/next/dist/server/next-server.js:272:17) at async DevServer.handleRequestImpl (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/base-server.js:817:17) at async /Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/dev/next-dev-server.js:339:20 at async Span.traceAsyncFn (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1__react@18.3.1/node_modules/next/dist/trace/trace.js:154:20) at async DevServer.handleRequest (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/dev/next-dev-server.js:336:24) at async invokeRender (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/lib/router-server.js:173:21) at async handleRequest (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1__react@18.3.1/node_modules/next/dist/server/lib/router-server.js:350:24) at async requestHandlerImpl (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1react@18.3.1/node_modules/next/dist/server/lib/router-server.js:374:13) at async Server.requestListener (/Users/robin/mychat-pdf2/nodemodules/.pnpm/next@14.2.15@opentelemetry+api@1.9.0_react-dom@18.3.1_react@18.3.1__react@18.3.1/node_modules/next/dist/server/lib/start-server.js:141:13)

marcusschiesser commented 5 days ago

@leehuwuj that might be related to our refactoring?

Robing commented 3 days ago

image @leehuwuj @marcusschiesser This issue might be related to package building. The unpdf module seems to be ignored after the build process.

marcusschiesser commented 2 days ago

@himself65 as we upgraded LITS - anything that got changed there?

himself65 commented 2 days ago

its in llamaindex/core/utils

himself65 commented 2 days ago

It might be a regression, i should re-export it in index.edge.ts in llamaindex package

marcusschiesser commented 1 day ago

@himself65 it's a different error, it's not about extractText from LITS but from unpdf. https://github.com/run-llama/LlamaIndexTS/pull/1369 fixes this error - I keep this ticket open, until we update create-llama