From cbc3790aea99442bc7fc40165ad1d6afead5577c Mon Sep 17 00:00:00 2001 From: Kristian Aune Date: Wed, 22 Jan 2025 13:17:25 +0100 Subject: [PATCH] Fix links --- en/cross-encoders.md | 2 +- en/onnx.md | 5 ++--- en/use-case-text-image-search.md | 29 ++++++----------------------- 3 files changed, 9 insertions(+), 27 deletions(-) diff --git a/en/cross-encoders.md b/en/cross-encoders.md index 752cd88a4a..e28e0639fc 100644 --- a/en/cross-encoders.md +++ b/en/cross-encoders.md @@ -221,7 +221,7 @@ Quantization of model weights can drastically improve serving efficiency on CPU. ## Examples -The [Transformers](https://github.com/vespa-engine/sample-apps/tree/master/transformers) +The [MS Marco](https://github.com/vespa-engine/sample-apps/tree/master/msmarco-ranking) sample application demonstrates using cross-encoders. ## Using cross-encoders with multi-vector indexing diff --git a/en/onnx.md b/en/onnx.md index 28f6a727c1..da8d7681fb 100644 --- a/en/onnx.md +++ b/en/onnx.md @@ -131,9 +131,8 @@ over multiple files, is currently not supported. ## Examples -The [transformers](https://github.com/vespa-engine/sample-apps/tree/master/transformers) -sample application uses a cross-encoder model to -[re-rank documents](https://github.com/vespa-engine/sample-apps/blob/master/transformers/application/schemas/msmarco.sd). +The [MS Marco](https://github.com/vespa-engine/sample-apps/tree/master/msmarco-ranking) +sample application uses a cross-encoder model to re-rank documents. The [simple-semantic-search](https://github.com/vespa-engine/sample-apps/tree/master/simple-semantic-search) sample application uses onnx models for embedding inference. [custom-embeddings](https://github.com/vespa-engine/sample-apps/tree/master/custom-embeddings) has an example of a PyTorch model that is exported to onnx format for use in re-ranking. diff --git a/en/use-case-text-image-search.md b/en/use-case-text-image-search.md index ee5a5b8f6e..429d27039e 100644 --- a/en/use-case-text-image-search.md +++ b/en/use-case-text-image-search.md @@ -3,11 +3,10 @@ title: "Use Case - Text-Image Search" --- -The [text-image use -case](https://github.com/vespa-engine/sample-apps/tree/master/text-image-search/) is an example -of a text-to-image search application. Taking a textual query, such as "two -people bicycling", it will return images containing two people on bikes. This -application is built using [CLIP (Contrastive Language-Image +The [text-image use case](https://github.com/vespa-engine/sample-apps/tree/master/text-image-search/) is an example +of a text-to-image search application. +Taking a textual query, such as "two people bicycling", it will return images containing two people on bikes. +This application is built using [CLIP (Contrastive Language-Image Pre-Training)](https://github.com/openai/CLIP) which enables "zero-shot prediction". This means that the system can return sensible results for images it hasn't seen during training, allowing it to process and index any image. In this @@ -15,18 +14,9 @@ use case, we use the [Flickr8k](https://github.com/jbrownlee/Datasets/blob/maste dataset, which was not used during training of the CLIP model. -To start the application, please follow the instructions in the +To start the application, follow the instructions in the [README](https://github.com/vespa-engine/sample-apps/blob/master/text-image-search/README.md). - -This sample application can be used in two different ways. The first is by -using a [Python-based search -app](https://github.com/vespa-engine/sample-apps/blob/master/text-image-search/src/python/README.md), -which is suitable for exploration and analysis. The other is a [stand-alone -Vespa -application](https://github.com/vespa-engine/sample-apps/blob/master/text-image-search/README.md), -which is more suitable for production. - -After deploying the application, you can ask questions like this: +After deploying the application, you can ask questions like: ``` http://localhost:8080/search/?input=two+people+bicylcing @@ -34,12 +24,6 @@ http://localhost:8080/search/?input=two+people+bicylcing ### Highlighted features -* [PyVespa](https://pyvespa.readthedocs.io/en/latest/index.html) - - PyVespa is the official Python API for Vespa. This can be used to easily - create, modify, deploy and interact with Vespa instances. The main - goal of the library is to allow for faster prototyping and to facilitate - Machine Learning experiments for Vespa applications. * [Approximate nearest neighbors using an HNSW index](approximate-nn-hnsw.html) @@ -73,4 +57,3 @@ http://localhost:8080/search/?input=two+people+bicylcing class with data in `services.xml`, and the resulting object is dependency injected to the component during construction. This application uses custom config to set up the token vocabulary used in tokenization. -