dspy 0.22.1 → 0.24.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 35e148ea7f8b9d9239489008409167bce63fce8bbb51798837573a93cc82bd73
-  data.tar.gz: 69304272af26457e557189b743c59bcddb25f9d05ba485e5fec1e61cee5be4ad
+  metadata.gz: e8fb5750b0bc898e3bfb2b64305e5b7eb186c494aba525fd8b739822385e7129
+  data.tar.gz: 530f9d8163c914845a2b472cdacce848ba187b9e69f9304d8743966b744ddf9f
 SHA512:
-  metadata.gz: 998377fc4c8d444029e83e9b01f5e65efd28df06abc07a8b120258a91ef6894c6a0b75ffa398526c305894fe9b5a22eb389b0e9646a1f26d341af6aea736101b
-  data.tar.gz: 77e0ccd6a18fd3495bd785acfc0d45555f7632b895bb9dbe583e1b42622270f9fb9f9f242cac43f01259971829decb7e8306ad070a2fe9e2a4a9c655bbeb675b
+  metadata.gz: 9f8e5fa70b1be656f174e5370f529086cb6c836030382c04fd1392e79998c43e93b71db7dbc47ec3cf424254cbd42343ac6f1447f800185d6ce499204dec05f2
+  data.tar.gz: 95971087479ca0efa66da1bb6084e94a6cb2120203721c2a949c6fc002d152da9f4587061e8e67c246760dbee5167718f8a6f067024e61106d9fa94c1bd0cd55

data/README.md

@@ -5,16 +5,15 @@
 [![Build Status](https://img.shields.io/github/actions/workflow/status/vicentereig/dspy.rb/ruby.yml?branch=main&label=build)](https://github.com/vicentereig/dspy.rb/actions/workflows/ruby.yml)
 [![Documentation](https://img.shields.io/badge/docs-vicentereig.github.io%2Fdspy.rb-blue)](https://vicentereig.github.io/dspy.rb/)
 
-**Build reliable LLM applications in Ruby using composable, type-safe modules.**
+**Build reliable LLM applications in idiomatic Ruby using composable, type-safe modules.**
 
-DSPy.rb brings structured LLM programming to Ruby developers. Instead of wrestling with prompt strings and parsing 
-responses, you define typed signatures and compose them into pipelines that just work.
+The Ruby framework for programming with large language models. DSPy.rb brings structured LLM programming to Ruby developers. Instead of wrestling with prompt strings and parsing responses, you define typed signatures using idiomatic Ruby to compose and decompose AI Worklows and AI Agents.
 
-Traditional prompting is like writing code with string concatenation: it works until it doesn't. DSPy.rb brings you 
+**Prompts are the just Functions.** Traditional prompting is like writing code with string concatenation: it works until it doesn't. DSPy.rb brings you 
 the programming approach pioneered by [dspy.ai](https://dspy.ai/): instead of crafting fragile prompts, you define modular 
 signatures and let the framework handle the messy details.
 
-DSPy.rb is an idiomatic Ruby port of Stanford's [DSPy framework](https://github.com/stanfordnlp/dspy). While implementing 
+DSPy.rb is an idiomatic Ruby surgical port of Stanford's [DSPy framework](https://github.com/stanfordnlp/dspy). While implementing 
 the core concepts of signatures, predictors, and optimization from the original Python library, DSPy.rb embraces Ruby 
 conventions and adds Ruby-specific innovations like CodeAct agents and enhanced production instrumentation.
 

data/lib/dspy/memory/local_embedding_engine.rb

@@ -53,22 +53,9 @@ module DSPy
       def embed_batch(texts)
         ensure_ready!
         
-        # Preprocess all texts
-        cleaned_texts = texts.map { |text| preprocess_text(text) }
-        
-        # Generate embeddings in batch
-        results = @model.call(cleaned_texts)
-        
-        # Extract and normalize embeddings
-        results.map do |result|
-          # Handle both single embeddings and batch results
-          embedding = case result
-                     when Array
-                       result.flatten  # Flatten in case of nested arrays
-                     else
-                       result.to_a.flatten
-                     end
-          normalize_vector(embedding)
+        # Generate embeddings one by one (informers doesn't support true batch processing)
+        texts.map do |text|
+          embed(text)
         end
       end
 

data/lib/dspy/prediction.rb

@@ -54,7 +54,7 @@ module DSPy
 
     sig { returns(T::Hash[Symbol, T.untyped]) }
     def to_h
-      @_struct.to_h
+      @_struct.serialize
     end
 
     private