Comments (2)
Not a bug sadly. Our saving mechanism does nothing to save anything regarding the embed model, the llm, or any other service context settings. (these are not things we can easily save to disk and reconstruct)
You can pass in the service context again when loading from disk
index2 = load_index_from_storage(storage_context=STORAGE_CONTEXT, index_id="123", service_context=service_context)
or set the global as you mentioned 👍🏻
set_global_service_context(service_context)
from llama_index.
I see, thanks.
I think it was this index2 = load_index_from_storage(storage_context=STORAGE_CONTEXT, index_id="123", service_context=service_context)
that was missing from documentation (I looked for this but didn't see the option. Thanks!
from llama_index.
Related Issues (20)
- [Question]: AttributeError: 'NoneType' object has no attribute 'search' HOT 5
- [Question]: why PostgresKVStore table class does not match my postgres vector table schema? HOT 2
- [Bug]: GoogleDriveReader Must specify `client_config` or `service_account_key` HOT 2
- [Question]: Got empty response when using KnowledgeGraphRAGRetriever with Neo4jGraphStore HOT 3
- [Bug]: JSONalyzeQueryEngine predict() missing 1 required positional argument: 'text' HOT 1
- [Bug]: Some notebooks set OPENAI_API_TOKEN instead of OPENAI_API_KEY
- [Bug]: llm_completion_callback ignores prompt keyword argument HOT 1
- [Documentation]: DOI not found HOT 1
- [Bug]: ImportError: cannot import name 'BaseRetriever' from partially initialized module 'llama_index.core.base.base_retriever' HOT 2
- [Question]: Dumb llama3 with llamaindex, but not with ollama HOT 6
- [Question]: Can llama-index milvus vector store use Milvus'es built-in embedding models that they provide instead of using openai for embedding? HOT 4
- [Bug]: DEFAULT_RESPONSE_SYNTHESIS_PROMPT missing HOT 1
- [Bug]: Using flask restful server and got [Session and connector has to use same event loop] error HOT 8
- GPU OOM during the embedding process HOT 1
- [Question]: Is there a way to change response_mode in response_synthesizer dynamically? HOT 3
- [Bug]: Chatml messages_to_prompt HOT 1
- [Question]: SimpleDirectoryReader failed to load 1 file (but other 100 files are fine) HOT 3
- [Bug]: LLAMA INDEX is becoming a Dependency Hell itself HOT 11
- [Feature Request]: Track OpenAI LLM Usage Cost
- [Feature Request]: Allow trafilatura kwargs for additional options
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 llama_index.