mirror of
https://github.com/run-llama/create-llama.git
synced 2026-07-15 13:15:42 -04:00
Whenever I try to use create-llama through CLI, it throws the error: The data stream is hanging. Did you forget to close it with data.close()? #19
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @crown-king on GitHub (Jun 12, 2024).
Here's a full copy of what I did on the CLI and the respective output:
Microsoft Windows [Version 10.0.22631.3593]
(c) Microsoft Corporation. All rights reserved.
C:\Users\lamak>npx create-llama@latest --ask-models
√ What is your project named? ... my-app
√ Which template would you like to use? » Chat
√ Which framework would you like to use? » NextJS
√ Would you like to set up observability? » No
√ Which model provider would you like to use » Gemini
√ Please provide your Google API key (or leave blank to use GOOGLE_API_KEY env variable): .
√ Which LLM model would you like to use? » gemini-1.5-pro-latest
√ Which embedding model would you like to use? » text-embedding-004
√ Which data source would you like to use? » Use an example PDF
√ Would you like to add another data source? » No
√ Would you like to use LlamaParse (improved parser for RAG - requires API key)? ... no / yes
√ Would you like to use a vector database? » No, just store the data in the file system
√ Would you like to build an agent using tools? If so, select the tools here, otherwise just press enter »
√ How would you like to proceed? » Generate code, install dependencies, and run the app (~2 min)
Creating a new LlamaIndex app in C:\Users\lamak\my-app.
Using npm.
Initializing project with template: streaming
Using vector DB: none
No tools selected - use optimized context chat engine
Installing dependencies:
@radix-ui/react-collapsible
@radix-ui/react-hover-card
@radix-ui/react-slot
ai
ajv
class-variance-authority
clsx
dotenv
llamaindex
lucide-react
next
pdf2json
react
react-dom
react-markdown
react-syntax-highlighter
remark
remark-code-import
remark-gfm
remark-math
rehype-katex
supports-color
tailwind-merge
vaul
@llamaindex/pdf-viewer
@e2b/code-interpreter
uuid
Installing devDependencies:
@types/node
@types/react
@types/react-dom
@types/react-syntax-highlighter
autoprefixer
cross-env
eslint
eslint-config-next
eslint-config-prettier
postcss
prettier
prettier-plugin-organize-imports
tailwindcss
tsx
typescript
@types/uuid
npm warn deprecated inflight@1.0.6: This module is not supported, and leaks memory. Do not use it. Check out lru-cache if you want a good and tested way to coalesce async requests by a key value, which is much more comprehensive and powerful.
npm warn deprecated @humanwhocodes/config-array@0.11.14: Use @eslint/config-array instead
npm warn deprecated rimraf@3.0.2: Rimraf versions prior to v4 are no longer supported
npm warn deprecated glob@7.2.3: Glob versions prior to v9 are no longer supported
npm warn deprecated @humanwhocodes/object-schema@2.0.3: Use @eslint/object-schema instead
npm warn deprecated fs-promise@2.0.3: Use mz or fs-extra^3.0 with Promise Support
npm warn deprecated dommatrix@1.0.3: dommatrix is no longer maintained. Please use @thednp/dommatrix.
added 986 packages, and audited 989 packages in 2m
291 packages are looking for funding
run npm fund for details
3 high severity vulnerabilities
Some issues need review, and may require choosing
a different dependency.
Run npm audit for details.
Created '.env' file. Please check the settings.
Generating context data...
Copying data from path: C:\Users\lamak\AppData\Local\npm-cache_npx\7bfc2205dda2d438\node_modules\create-llama\dist\templates\components\data\101.pdf
Running npm run generate to generate the context data.
my-app@0.1.0 generate
tsx app\api\chat\engine\generate.ts
Using 'gemini' model provider
Generating storage context...
No valid data found at path: cache\doc_store.json starting new store.
No valid data found at path: cache\index_store.json starting new store.
No valid data found at path: cache\vector_store.json starting new store.
Storage context successfully generated in 10.826s.
Finished generating storage.
Initialized a git repository.
Success! Created my-app at C:\Users\lamak\my-app
Now have a look at the README.md (file://C:\Users\lamak\my-app/README.md) and learn how to get started.
Running app in C:\Users\lamak\my-app...
my-app@0.1.0 dev
next dev
▲ Next.js 14.2.4
Local: http://localhost:3000/
Environments: .env
✓ Starting...
✓ Ready in 2.6s
○ Compiling / ...
✓ Compiled / in 10s (2917 modules)
GET / 200 in 11380ms
○ Compiling /favicon.ico ...
✓ Compiled /api/chat/config in 5.7s (2812 modules)
✓ Compiled in 0ms (1489 modules)
✓ Compiled in 0ms (1489 modules)
✓ Compiled /api/chat in 1ms (1489 modules)
GET /favicon.ico 200 in 4956ms
✓ Compiled (2363 modules)
GET /api/chat/config 200 in 6989ms
Using 'gemini' model provider
GET /api/chat/config 200 in 932ms
GET /api/chat/config 200 in 11ms
GET /api/chat/config 200 in 10ms
The data stream is hanging. Did you forget to close it with data.close()?
POST /api/chat 200 in 7783ms
@crown-king commented on GitHub (Jun 12, 2024):
Thanks for that marcus, apologies for opening the issue there, looking forward to the solution to this here :)
@marcusschiesser commented on GitHub (Jun 13, 2024):
It's actually just a warning generated by vercel/ai, see https://github.com/vercel/ai/blob/e0d0d4670f5f6f4f0f6a0b3325ff6c71d9fcc2f3/packages/core/streams/stream-data.ts#L23-L28
It's shown after 3 seconds and only in DEV mode.
After 3 seconds the LLM is usually not finished streaming, so I don't see any impact, and I would ignore this warning.