Update resources of AI Engineer roadmap (#8369)
Vedansh
3 weeks ago
committed by
GitHub
parent
bcb76b4ef3
commit
7e39785289
26 changed files with 41 additions and 29 deletions
@ -1,3 +1,8 @@ |
||||
# Open-Source Embeddings |
||||
|
||||
Open-source embeddings are pre-trained vector representations of data, usually text, that are freely available for use and modification. These embeddings capture semantic meanings, making them useful for tasks like semantic search, text classification, and clustering. Examples include Word2Vec, GloVe, and FastText, which represent words as vectors based on their context in large corpora, and more advanced models like Sentence-BERT and CLIP that provide embeddings for sentences and images. Open-source embeddings allow developers to leverage pre-trained models without starting from scratch, enabling faster development and experimentation in natural language processing and other AI applications. |
||||
Open-source embeddings are pre-trained vector representations of data, usually text, that are freely available for use and modification. These embeddings capture semantic meanings, making them useful for tasks like semantic search, text classification, and clustering. Examples include Word2Vec, GloVe, and FastText, which represent words as vectors based on their context in large corpora, and more advanced models like Sentence-BERT and CLIP that provide embeddings for sentences and images. Open-source embeddings allow developers to leverage pre-trained models without starting from scratch, enabling faster development and experimentation in natural language processing and other AI applications. |
||||
|
||||
Learn more from the following resources: |
||||
|
||||
- [@official@Embeddings](https://platform.openai.com/docs/guides/embeddings) |
||||
- [@article@A Guide to Open-Source Embedding Models](https://www.bentoml.com/blog/a-guide-to-open-source-embedding-models) |
||||
@ -1,3 +1,7 @@ |
||||
# Performing Similarity Search |
||||
|
||||
In a similarity search, the process begins by converting the user’s query (such as a piece of text or an image) into an embedding—a vector representation that captures the query’s semantic meaning. This embedding is generated using a pre-trained model, such as BERT for text or a neural network for images. Once the query is converted into a vector, it is compared to the embeddings stored in the vector database. |
||||
In a similarity search, the process begins by converting the user’s query (such as a piece of text or an image) into an embedding—a vector representation that captures the query’s semantic meaning. This embedding is generated using a pre-trained model, such as BERT for text or a neural network for images. Once the query is converted into a vector, it is compared to the embeddings stored in the vector database. |
||||
|
||||
Visit the following resources to learn more: |
||||
|
||||
- [@article@What is Similarity Search & How Does it work?](https://www.truefoundry.com/blog/similarity-search) |
||||
Loading…
Reference in new issue