Experience the power of our new embedding models, trained on legally approved data for business usage
Exciting news! Our latest release introduces the watsonx Embeddings API, allowing you to generate vectorized representations of input text and capture semantic relationships
๐ช๐ต๐ฎ๐'๐ ๐ป๐ฒ๐:
1. Embeddings generation endpoint in our REST API
2. Two initial models: slate.125m.english.rtrvr and slate.30m.english.rtrvr (knowledge distilled)
3. Accessible through REST API endpoint or Python SDK
๐ช๐ต๐ฎ๐ ๐ฎ๐ฟ๐ฒ ๐๐ฒ๐
๐ ๐ฒ๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด๐?
Text embeddings are numerical representations of sentences or passages, allowing computers to quickly and efficiently compare and analyze semantic meanings.
๐ช๐ต๐ฎ๐ ๐๐ต๐ถ๐ ๐บ๐ฒ๐ฎ๐ป๐ ๐ณ๐ผ๐ฟ ๐๐ผ๐:
Embedding models are crucial for Generative AI applications, offering semantic and syntactic fidelity with efficient computing and storage.
๐ฆ๐๐ผ๐ฟ๐ฒ ๐ฎ๐ป๐ฑ ๐จ๐๐ฒ ๐๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด๐
Store vectors in a vector database like Milvus and use them to compare passages in real-time or reference stored vectorized text passages.
๐ฅ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐๐๐ด๐บ๐ฒ๐ป๐๐ฒ๐ฑ ๐๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐๐ถ๐ผ๐ป (๐ฅ๐๐)
Use embeddings to enhance AI model accuracy and reliability with facts from external sources.
๐๐ฑ๐๐ฎ๐ป๐๐ฎ๐ด๐ฒ๐ ๐ผ๐๐ฟ ๐ฆ๐น๐ฎ๐๐ฒ ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ผ๐ณ๐ณ๐ฒ๐ฟ ๐ผ๐๐ฒ๐ฟ ๐ผ๐๐ต๐ฒ๐ฟ ๐ฏ๐ฟ๐ฑ-๐ฝ๐ฎ๐ฟ๐๐ ๐ฒ๐บ๐ฏ๐ฒ๐ฑ๐ฑ๐ถ๐ป๐ด ๐บ๐ผ๐ฑ๐ฒ๐น๐:
1. Performance matching or exceeding market leaders in retrieval benchmarks.
2. Exclusively trained on legally approved and commercially viable data for enterprise usage.
3. Scalable, fully-managed, and integrated with the broader watsonx portfolio.
๐๐ฒ๐ ๐ฆ๐๐ฎ๐ฟ๐๐ฒ๐ฑ ๐ป๐ผ๐ ๐๐ถ๐๐ต ๐๐ต๐ถ๐ ๐ฅ๐๐ ๐ง๐๐๐ผ๐ฟ๐ถ๐ฎ๐น!
Here's a Python Notebook leveraging our watsonx Granite Model Series, Chroma, and LangChain to answer questions: https://lnkd.in/gZB-qk-f
#watsonx.ai#GenerativeAI------------------------------
Armand Ruiz
------------------------------