Comments (7)
I'm taking a stab at this here.
I'll finish up the tests in the next day or so, and open a PR.
from ragatouille.
Ouch, saw this issue yesterday and started planning an implementation. Just got started so almost saw your note in time @anirudhdharmarajan ...
from ragatouille.
Looking forward for your implementation. @anirudhdharmarajan
from ragatouille.
PR's up, would love any feedback on the approach I took for this (and a couple other related things that got pulled in 😅
from ragatouille.
Live in 0.0.5a thanks to @anirudhdharmarajan's amazing work!
cc @LarsAC @0-hero @tm17-abcgen
from ragatouille.
Thankyou, just raised a PR on llama-hub too run-llama/llama-hub#893
from ragatouille.
Hey!
We don't currently support this, but it'd be relatively simple to add (though take more space on-disk!).
Right now, when an independent is create, we also export a collection.json
, which contains all the documents inside it. This is useful so we can return the document: the index only store the passage ids (they correspond to the indices in the list contained in collection.json
)
Apart from limited time, there's nothing stopping us from also storing a metadata.json
file, which would be a list of dictionaries (or of a Metadata
Pedantic object exported to dict, for easier validation), where the entry at index i
would contain the metadata associated with passage_id i
.
If you'd like to try to implement this, feel free! Otherwise it's definitely on the list of nice-to-have features that we'll circle to eventually.
from ragatouille.
Related Issues (20)
- Stuck at " Loading segmented_maxsim_cpp extension (set COLBERT_LOAD_TORCH_EXTENSION_VERBOSE=True for more info)..." HOT 1
- ImportError: cannot import name 'PromptTemplate' from 'llama_index' (unknown location)
- Compatibility with LangChain 0.2.0 HOT 3
- How to extract embeddings generated by Colbert? HOT 2
- Idea: Make CorpusProcessor (and splitter_fn / preprocessing_fn) to have access to metadata
- Embedding Model with Existing Index
- How to index collection using generator function?
- Training script is not working as is
- Making deletions will alter the collection.json file, hence the search function unusable because we access the collection using list indices.
- can't access my finetuned model
- Use base model or sentence transformer
- ragatouille requires a version of numpy uncompatible with python
- ValueError: RAGatouille is not installed. Please install it with `pip install ragatouille`.
- Documentation (API Reference): missing params in description tables
- Question -- Symmetric search
- How to use highly capable Decoder only models (LLMs) with RAGatouille -- is it even advisable?
- RuntimeError when indexing with FAISS
- RAGAtouille cpu only installation
- Typescript support of RAGatouille
- Question: rerank does not use index
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 ragatouille.