Comments (5)
Resolved by looking at the exports in package.json and altering the import. That being said, Typescript won't accept the import so I need to @ts-ignore
it
// @ts-ignore
import { PineconeDb } from '@llm-tools/embedjs/vectorDb/pinecone';
// @ts-ignore
import { LmdbCache } from '@llm-tools/embedjs/cache/lmdb'
Otherwise I get
TS2307: Cannot find module @llm-tools/embedjs/cache/lmdb or its corresponding type declarations.
from embedjs.
This should not be the case. Look at the sample project written in TS -
I have updated the documentation to make it clear what the import paths should be. For your TS error, could you share with me your tsconfig.json file and node version?
from embedjs.
Thanks for updating the documentation! Will definitely help others with future debugging if needed.
It's worth noting i'm in a monorepo so there might be an issue with that?
Heres my tsconfig
(just using one from another project, so nothing really intentionally configured)
{
"compilerOptions": {
"module": "commonjs",
"rootDir": ".",
"declaration": true,
"removeComments": true,
"emitDecoratorMetadata": true,
"experimentalDecorators": true,
"allowSyntheticDefaultImports": true,
"esModuleInterop": true,
"target": "es2020",
"sourceMap": true,
"outDir": "./dist",
"baseUrl": "./",
"incremental": true,
"skipLibCheck": true,
"strictNullChecks": false,
"noImplicitAny": false,
"strictBindCallApply": false,
"forceConsistentCasingInFileNames": false,
"noFallthroughCasesInSwitch": false,
"allowJs": true
},
"include": [
"src/**/*",
"libs/**/*"
],
"exclude": ["node_modules"]
}
Node Version: 20.12.0
from embedjs.
Thanks for sharing the tsconfig. Did this ever work for you since then? I haven't tested the library with monorepos yet but I suppose I can take a look - but it will take a bit.
from embedjs.
I am closing this issue for now, feel free to reopen it if issue persists. I am planning to move the library itself to a monorepo setup in some time, this should make things easier I suppose.
from embedjs.
Related Issues (20)
- Getting Started and Documentation Clarification HOT 2
- Limit token usage output parameter across all queried llm models
- Error during npm install HOT 11
- Allow conversation history to persist HOT 5
- Add Groq for super fast inference with LLM's (supported by Langchain)
- Add Amazon Bedrock (included in langchain)
- Add OllamaEmbedding (It is available in langchain) HOT 2
- Windows install problem version 0.0.89 HOT 2
- I'm trying to install the package on my window and get the following error: HOT 2
- response duplicate HOT 1
- Add Support for In Memory Vector Store Which stores everything in memory or in a flat file
- Add support for Elasticsearch for Vector database
- Maximum context length exceeded HOT 3
- throw new Error("OpenAI or Azure OpenAI API key or Token Provider not found"); HOT 2
- No Verbose option: unable to debug where the issue is. Also unable to track progress HOT 1
- Revisit - Embeddings Tokens In, Out, Total and Cost - Critical for hosting and using this library HOT 2
- Documentation needs to be updated for loaders (overlap and chunksize) as causing undefined errors when migrating
- Dependency issue when attempting to use vectordb (LanceDB) HOT 1
- issue for conversations path in package.json HOT 2
- Don't understand if embedder is working or not
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from embedjs.