gepa 0.29.1 → 1.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +156 -107
- data/lib/gepa/version.rb +1 -1
- metadata +7 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: e16ace9b243a9ce0dc1d315e08bee579c9886ea2679c3532c50c0958b5cf5fbe
|
|
4
|
+
data.tar.gz: 62785ed7f12ab48b72b6f526e37d213ace1a152e5c144113d7073922af69d1b5
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e37ff5121b8e7190245bedc6b71970f6916a07f508fd18fe39dee6a499630c01aca4608b48abb4906e06470ed644d1e14fb83fc2573291579fa464a2e8f6c023
|
|
7
|
+
data.tar.gz: bad1f984c9b846cb3bc81a502c13a8f0500de50f4fa4cf253c5b87de1b507a7c7b0008b8e4371737e2997722b7812ecff11b34851cb654a4b4d0bbf030963320
|
data/README.md
CHANGED
|
@@ -4,27 +4,58 @@
|
|
|
4
4
|
[](https://rubygems.org/gems/dspy)
|
|
5
5
|
[](https://github.com/vicentereig/dspy.rb/actions/workflows/ruby.yml)
|
|
6
6
|
[](https://vicentereig.github.io/dspy.rb/)
|
|
7
|
+
[](https://discord.gg/zWBhrMqn)
|
|
8
|
+
|
|
9
|
+
> [!NOTE]
|
|
10
|
+
> The core Prompt Engineering Framework is production-ready with
|
|
11
|
+
> comprehensive documentation. I am focusing now on educational content on systematic Prompt Optimization and Context Engineering.
|
|
12
|
+
> Your feedback is invaluable. if you encounter issues, please open an [issue](https://github.com/vicentereig/dspy.rb/issues). If you have suggestions, open a [new thread](https://github.com/vicentereig/dspy.rb/discussions).
|
|
13
|
+
>
|
|
14
|
+
> If you want to contribute, feel free to reach out to me to coordinate efforts: hey at vicente.services
|
|
15
|
+
>
|
|
7
16
|
|
|
8
17
|
**Build reliable LLM applications in idiomatic Ruby using composable, type-safe modules.**
|
|
9
18
|
|
|
10
|
-
|
|
19
|
+
DSPy.rb is the Ruby-first surgical port of Stanford's [DSPy paradigm](https://github.com/stanfordnlp/dspy). It delivers structured LLM programming, prompt engineering, and context engineering in the language we love. Instead of wrestling with brittle prompt strings, you define typed signatures in idiomatic Ruby and compose workflows and agents that actually behave.
|
|
20
|
+
|
|
21
|
+
**Prompts are 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/): define modular signatures and let the framework deal with the messy bits.
|
|
11
22
|
|
|
12
|
-
|
|
13
|
-
the programming approach pioneered by [dspy.ai](https://dspy.ai/): instead of crafting fragile prompts, you define modular
|
|
14
|
-
signatures and let the framework handle the messy details.
|
|
23
|
+
While we implement the same signatures, predictors, and optimization algorithms as the original library, DSPy.rb leans hard into Ruby conventions with Sorbet-based typing, ReAct loops, and production-ready integrations like non-blocking OpenTelemetry instrumentation.
|
|
15
24
|
|
|
16
|
-
|
|
17
|
-
the core concepts of signatures, predictors, and optimization from the original Python library, DSPy.rb embraces Ruby
|
|
18
|
-
conventions and adds Ruby-specific innovations like CodeAct agents and enhanced production instrumentation.
|
|
25
|
+
**What you get?** Ruby LLM applications that scale and don't break when you sneeze.
|
|
19
26
|
|
|
20
|
-
|
|
27
|
+
Check the [examples](examples/) and take them for a spin!
|
|
21
28
|
|
|
22
29
|
## Your First DSPy Program
|
|
30
|
+
### Installation
|
|
31
|
+
|
|
32
|
+
Add to your Gemfile:
|
|
23
33
|
|
|
24
34
|
```ruby
|
|
25
|
-
|
|
35
|
+
gem 'dspy'
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
and
|
|
39
|
+
|
|
40
|
+
```bash
|
|
41
|
+
bundle install
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
### Your First Reliable Predictor
|
|
45
|
+
|
|
46
|
+
```ruby
|
|
47
|
+
require 'dspy'
|
|
48
|
+
|
|
49
|
+
# Configure DSPy globally to use your fave LLM (you can override per predictor).
|
|
50
|
+
DSPy.configure do |c|
|
|
51
|
+
c.lm = DSPy::LM.new('openai/gpt-4o-mini',
|
|
52
|
+
api_key: ENV['OPENAI_API_KEY'],
|
|
53
|
+
structured_outputs: true) # Enable OpenAI's native JSON mode
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
# Define a signature for sentiment classification - instead of writing a full prompt!
|
|
26
57
|
class Classify < DSPy::Signature
|
|
27
|
-
description "Classify sentiment of a given sentence."
|
|
58
|
+
description "Classify sentiment of a given sentence." # sets the goal of the underlying prompt
|
|
28
59
|
|
|
29
60
|
class Sentiment < T::Enum
|
|
30
61
|
enums do
|
|
@@ -33,32 +64,59 @@ class Classify < DSPy::Signature
|
|
|
33
64
|
Neutral = new('neutral')
|
|
34
65
|
end
|
|
35
66
|
end
|
|
36
|
-
|
|
67
|
+
|
|
68
|
+
# Structured Inputs: makes sure you are sending only valid prompt inputs to your model
|
|
37
69
|
input do
|
|
38
|
-
const :sentence, String
|
|
70
|
+
const :sentence, String, description: 'The sentence to analyze'
|
|
39
71
|
end
|
|
40
72
|
|
|
73
|
+
# Structured Outputs: your predictor will validate the output of the model too.
|
|
41
74
|
output do
|
|
42
|
-
const :sentiment, Sentiment
|
|
43
|
-
const :confidence, Float
|
|
75
|
+
const :sentiment, Sentiment, description: 'The sentiment of the sentence'
|
|
76
|
+
const :confidence, Float, description: 'A number between 0.0 and 1.0'
|
|
44
77
|
end
|
|
45
78
|
end
|
|
46
79
|
|
|
47
|
-
#
|
|
48
|
-
DSPy.configure do |c|
|
|
49
|
-
c.lm = DSPy::LM.new('openai/gpt-4o-mini',
|
|
50
|
-
api_key: ENV['OPENAI_API_KEY'],
|
|
51
|
-
structured_outputs: true) # Enable OpenAI's native JSON mode
|
|
52
|
-
end
|
|
53
|
-
|
|
54
|
-
# Create the predictor and run inference
|
|
80
|
+
# Wire it to the simplest prompting technique: a prediction loop.
|
|
55
81
|
classify = DSPy::Predict.new(Classify)
|
|
82
|
+
# it may raise an error if you mess the inputs or your LLM messes the outputs.
|
|
56
83
|
result = classify.call(sentence: "This book was super fun to read!")
|
|
57
84
|
|
|
58
85
|
puts result.sentiment # => #<Sentiment::Positive>
|
|
59
86
|
puts result.confidence # => 0.85
|
|
60
87
|
```
|
|
61
88
|
|
|
89
|
+
Save this as `examples/first_predictor.rb` and run it with:
|
|
90
|
+
|
|
91
|
+
```bash
|
|
92
|
+
bundle exec ruby examples/first_predictor.rb
|
|
93
|
+
```
|
|
94
|
+
|
|
95
|
+
### Sibling Gems
|
|
96
|
+
|
|
97
|
+
DSPy.rb ships multiple gems from this monorepo so you can opt into features with heavier dependency trees (e.g., datasets pull in Polars/Arrow, MIPROv2 requires `numo-*` BLAS bindings) only when you need them. Add these alongside `dspy`:
|
|
98
|
+
|
|
99
|
+
| Gem | Description | Status |
|
|
100
|
+
| --- | --- | --- |
|
|
101
|
+
| `dspy-schema` | Exposes `DSPy::TypeSystem::SorbetJsonSchema` for downstream reuse. (Still required by the core `dspy` gem; extraction lets other projects depend on it directly.) | **Stable** (v1.0.0) |
|
|
102
|
+
| `dspy-openai` | Packages the OpenAI/OpenRouter/Ollama adapters plus the official SDK guardrails. Install whenever you call `openai/*`, `openrouter/*`, or `ollama/*`. [Adapter README](https://github.com/vicentereig/dspy.rb/blob/main/lib/dspy/openai/README.md) | **Stable** (v1.0.0) |
|
|
103
|
+
| `dspy-anthropic` | Claude adapters, streaming, and structured-output helpers behind the official `anthropic` SDK. [Adapter README](https://github.com/vicentereig/dspy.rb/blob/main/lib/dspy/anthropic/README.md) | **Stable** (v1.0.0) |
|
|
104
|
+
| `dspy-gemini` | Gemini adapters with multimodal + tool-call support via `gemini-ai`. [Adapter README](https://github.com/vicentereig/dspy.rb/blob/main/lib/dspy/gemini/README.md) | **Stable** (v1.0.0) |
|
|
105
|
+
| `dspy-code_act` | Think-Code-Observe agents that synthesize and execute Ruby safely. (Add the gem or set `DSPY_WITH_CODE_ACT=1` before requiring `dspy/code_act`.) | **Stable** (v1.0.0) |
|
|
106
|
+
| `dspy-datasets` | Dataset helpers plus Parquet/Polars tooling for richer evaluation corpora. (Toggle via `DSPY_WITH_DATASETS`.) | **Stable** (v1.0.0) |
|
|
107
|
+
| `dspy-evals` | High-throughput evaluation harness with metrics, callbacks, and regression fixtures. (Toggle via `DSPY_WITH_EVALS`.) | **Stable** (v1.0.0) |
|
|
108
|
+
| `dspy-miprov2` | Bayesian optimization + Gaussian Process backend for the MIPROv2 teleprompter. (Install or export `DSPY_WITH_MIPROV2=1` before requiring the teleprompter.) | **Stable** (v1.0.0) |
|
|
109
|
+
| `dspy-gepa` | `DSPy::Teleprompt::GEPA`, reflection loops, experiment tracking, telemetry adapters. (Install or set `DSPY_WITH_GEPA=1`.) | **Stable** (v1.0.0) |
|
|
110
|
+
| `gepa` | GEPA optimizer core (Pareto engine, telemetry, reflective proposer). | **Stable** (v1.0.0) |
|
|
111
|
+
| `dspy-o11y` | Core observability APIs: `DSPy::Observability`, async span processor, observation types. (Install or set `DSPY_WITH_O11Y=1`.) | **Stable** (v1.0.0) |
|
|
112
|
+
| `dspy-o11y-langfuse` | Auto-configures DSPy observability to stream spans to Langfuse via OTLP. (Install or set `DSPY_WITH_O11Y_LANGFUSE=1`.) | **Stable** (v1.0.0) |
|
|
113
|
+
| `dspy-deep_search` | Production DeepSearch loop with Exa-backed search/read, token budgeting, and instrumentation (Issue #163). | **Stable** (v1.0.0) |
|
|
114
|
+
| `dspy-deep_research` | Planner/QA orchestration atop DeepSearch plus the memory supervisor used by the CLI example. | **Stable** (v1.0.0) |
|
|
115
|
+
| `sorbet-toon` | Token-Oriented Object Notation (TOON) codec, prompt formatter, and Sorbet mixins for BAML/TOON Enhanced Prompting. [Sorbet::Toon README](https://github.com/vicentereig/dspy.rb/blob/main/lib/sorbet/toon/README.md) | **Alpha** (v0.1.0) |
|
|
116
|
+
|
|
117
|
+
**Provider adapters:** Add `dspy-openai`, `dspy-anthropic`, and/or `dspy-gemini` next to `dspy` in your Gemfile depending on which `DSPy::LM` providers you call. Each gem already depends on the official SDK (`openai`, `anthropic`, `gemini-ai`), and DSPy auto-loads the adapters when the gem is present—no extra `require` needed.
|
|
118
|
+
|
|
119
|
+
Set the matching `DSPY_WITH_*` environment variables (see `Gemfile`) to include or exclude each sibling gem when running Bundler locally (for example `DSPY_WITH_GEPA=1` or `DSPY_WITH_O11Y_LANGFUSE=1`). Refer to `adr/013-dependency-tree.md` for the full dependency map and roadmap.
|
|
62
120
|
### Access to 200+ Models Across 5 Providers
|
|
63
121
|
|
|
64
122
|
DSPy.rb provides unified access to major LLM providers with provider-specific optimizations:
|
|
@@ -99,21 +157,46 @@ end
|
|
|
99
157
|
|
|
100
158
|
## What You Get
|
|
101
159
|
|
|
102
|
-
**
|
|
160
|
+
**Developer Experience:** Official clients, multimodal coverage, and observability baked in.
|
|
161
|
+
<details>
|
|
162
|
+
<summary>Expand for everything included</summary>
|
|
163
|
+
|
|
164
|
+
- LLM provider support using official Ruby clients:
|
|
165
|
+
- [OpenAI Ruby](https://github.com/openai/openai-ruby) with vision model support
|
|
166
|
+
- [Anthropic Ruby SDK](https://github.com/anthropics/anthropic-sdk-ruby) with multimodal capabilities
|
|
167
|
+
- [Google Gemini API](https://ai.google.dev/) with native structured outputs
|
|
168
|
+
- [Ollama](https://ollama.com/) via OpenAI compatibility layer for local models
|
|
169
|
+
- **Multimodal Support** - Complete image analysis with DSPy::Image, type-safe bounding boxes, vision-capable models
|
|
170
|
+
- Runtime type checking with [Sorbet](https://sorbet.org/) including T::Enum and union types
|
|
171
|
+
- Type-safe tool definitions for ReAct agents
|
|
172
|
+
- Comprehensive instrumentation and observability
|
|
173
|
+
</details>
|
|
174
|
+
|
|
175
|
+
**Core Building Blocks:** Predictors, agents, and pipelines wired through type-safe signatures.
|
|
176
|
+
<details>
|
|
177
|
+
<summary>Expand for everything included</summary>
|
|
178
|
+
|
|
103
179
|
- **Signatures** - Define input/output schemas using Sorbet types with T::Enum and union type support
|
|
104
180
|
- **Predict** - LLM completion with structured data extraction and multimodal support
|
|
105
181
|
- **Chain of Thought** - Step-by-step reasoning for complex problems with automatic prompt optimization
|
|
106
182
|
- **ReAct** - Tool-using agents with type-safe tool definitions and error recovery
|
|
107
|
-
- **CodeAct** - Dynamic code execution agents for programming tasks
|
|
108
183
|
- **Module Composition** - Combine multiple LLM calls into production-ready workflows
|
|
184
|
+
</details>
|
|
185
|
+
|
|
186
|
+
**Optimization & Evaluation:** Treat prompt optimization like a real ML workflow.
|
|
187
|
+
<details>
|
|
188
|
+
<summary>Expand for everything included</summary>
|
|
109
189
|
|
|
110
|
-
**Optimization & Evaluation:**
|
|
111
190
|
- **Prompt Objects** - Manipulate prompts as first-class objects instead of strings
|
|
112
191
|
- **Typed Examples** - Type-safe training data with automatic validation
|
|
113
192
|
- **Evaluation Framework** - Advanced metrics beyond simple accuracy with error-resilient pipelines
|
|
114
193
|
- **MIPROv2 Optimization** - Advanced Bayesian optimization with Gaussian Processes, multiple optimization strategies, auto-config presets, and storage persistence
|
|
194
|
+
</details>
|
|
195
|
+
|
|
196
|
+
**Production Features:** Hardened behaviors for teams shipping actual products.
|
|
197
|
+
<details>
|
|
198
|
+
<summary>Expand for everything included</summary>
|
|
115
199
|
|
|
116
|
-
**Production Features:**
|
|
117
200
|
- **Reliable JSON Extraction** - Native structured outputs for OpenAI and Gemini, Anthropic tool-based extraction, and automatic strategy selection with fallback
|
|
118
201
|
- **Type-Safe Configuration** - Strategy enums with automatic provider optimization (Strict/Compatible modes)
|
|
119
202
|
- **Smart Retry Logic** - Progressive fallback with exponential backoff for handling transient failures
|
|
@@ -121,25 +204,46 @@ end
|
|
|
121
204
|
- **Performance Caching** - Schema and capability caching for faster repeated operations
|
|
122
205
|
- **File-based Storage** - Optimization result persistence with versioning
|
|
123
206
|
- **Structured Logging** - JSON and key=value formats with span tracking
|
|
207
|
+
</details>
|
|
124
208
|
|
|
125
|
-
|
|
126
|
-
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
-
|
|
133
|
-
- Type-
|
|
134
|
-
-
|
|
209
|
+
## Recent Achievements
|
|
210
|
+
|
|
211
|
+
DSPy.rb has gone from experimental to production-ready in three fast releases.
|
|
212
|
+
<details>
|
|
213
|
+
<summary>Expand for the full changelog highlights</summary>
|
|
214
|
+
|
|
215
|
+
### Foundation
|
|
216
|
+
- ✅ **JSON Parsing Reliability** - Native OpenAI structured outputs with adaptive retry logic and schema-aware fallbacks
|
|
217
|
+
- ✅ **Type-Safe Strategy Configuration** - Provider-optimized strategy selection and enum-backed optimizer presets
|
|
218
|
+
- ✅ **Core Module System** - Predict, ChainOfThought, ReAct with type safety (add `dspy-code_act` for Think-Code-Observe agents)
|
|
219
|
+
- ✅ **Production Observability** - OpenTelemetry, New Relic, and Langfuse integration
|
|
220
|
+
- ✅ **Advanced Optimization** - MIPROv2 with Bayesian optimization, Gaussian Processes, and multi-mode search
|
|
221
|
+
|
|
222
|
+
### Recent Advances
|
|
223
|
+
- ✅ **MIPROv2 ADE Integrity (v0.29.1)** - Stratified train/val/test splits, honest precision accounting, and enum-driven `--auto` presets with integration coverage
|
|
224
|
+
- ✅ **Instruction Deduplication (v0.29.1)** - Candidate generation now filters repeated programs so optimization logs highlight unique strategies
|
|
225
|
+
- ✅ **GEPA Teleprompter (v0.29.0)** - Genetic-Pareto reflective prompt evolution with merge proposer scheduling, reflective mutation, and ADE demo parity
|
|
226
|
+
- ✅ **Optimizer Utilities Parity (v0.29.0)** - Bootstrap strategies, dataset summaries, and Layer 3 utilities unlock multi-predictor programs on Ruby
|
|
227
|
+
- ✅ **Observability Hardening (v0.29.0)** - OTLP exporter runs on a single-thread executor preventing frozen SSL contexts without blocking spans
|
|
228
|
+
- ✅ **Documentation Refresh (v0.29.x)** - New GEPA guide plus ADE optimization docs covering presets, stratified splits, and error-handling defaults
|
|
229
|
+
</details>
|
|
230
|
+
|
|
231
|
+
**Current Focus Areas:** Closing the loop on production patterns and community adoption ahead of v1.0.
|
|
232
|
+
<details>
|
|
233
|
+
<summary>Expand for the roadmap</summary>
|
|
234
|
+
|
|
235
|
+
### Production Readiness
|
|
236
|
+
- 🚧 **Production Patterns** - Real-world usage validation and performance optimization
|
|
237
|
+
- 🚧 **Ruby Ecosystem Integration** - Rails integration, Sidekiq compatibility, deployment patterns
|
|
135
238
|
|
|
136
|
-
|
|
239
|
+
### Community & Adoption
|
|
240
|
+
- 🚧 **Community Examples** - Real-world applications and case studies
|
|
241
|
+
- 🚧 **Contributor Experience** - Making it easier to contribute and extend
|
|
242
|
+
- 🚧 **Performance Benchmarks** - Comparative analysis vs other frameworks
|
|
243
|
+
</details>
|
|
137
244
|
|
|
138
|
-
|
|
139
|
-
comprehensive documentation, but I'm battle-testing features through the 0.x series before committing
|
|
140
|
-
to a stable v1.0 API.
|
|
245
|
+
**v1.0 Philosophy:** v1.0 lands after battle-testing, not checkbox bingo. The API is already stable; the milestone marks production confidence.
|
|
141
246
|
|
|
142
|
-
Real-world usage feedback is invaluable - if you encounter issues or have suggestions, please open a GitHub issue!
|
|
143
247
|
|
|
144
248
|
## Documentation
|
|
145
249
|
|
|
@@ -156,92 +260,37 @@ For LLMs and AI assistants working with DSPy.rb:
|
|
|
156
260
|
- **[Quick Start Guide](docs/src/getting-started/quick-start.md)** - Your first DSPy programs
|
|
157
261
|
- **[Core Concepts](docs/src/getting-started/core-concepts.md)** - Understanding signatures, predictors, and modules
|
|
158
262
|
|
|
159
|
-
###
|
|
263
|
+
### Prompt Engineering
|
|
160
264
|
- **[Signatures & Types](docs/src/core-concepts/signatures.md)** - Define typed interfaces for LLM operations
|
|
161
265
|
- **[Predictors](docs/src/core-concepts/predictors.md)** - Predict, ChainOfThought, ReAct, and more
|
|
162
266
|
- **[Modules & Pipelines](docs/src/core-concepts/modules.md)** - Compose complex multi-stage workflows
|
|
163
267
|
- **[Multimodal Support](docs/src/core-concepts/multimodal.md)** - Image analysis with vision-capable models
|
|
164
268
|
- **[Examples & Validation](docs/src/core-concepts/examples.md)** - Type-safe training data
|
|
269
|
+
- **[Rich Types](docs/src/advanced/complex-types.md)** - Sorbet type integration with automatic coercion for structs, enums, and arrays
|
|
270
|
+
- **[Composable Pipelines](docs/src/advanced/pipelines.md)** - Manual module composition patterns
|
|
165
271
|
|
|
166
|
-
### Optimization
|
|
272
|
+
### Prompt Optimization
|
|
167
273
|
- **[Evaluation Framework](docs/src/optimization/evaluation.md)** - Advanced metrics beyond simple accuracy
|
|
168
274
|
- **[Prompt Optimization](docs/src/optimization/prompt-optimization.md)** - Manipulate prompts as objects
|
|
169
275
|
- **[MIPROv2 Optimizer](docs/src/optimization/miprov2.md)** - Advanced Bayesian optimization with Gaussian Processes
|
|
170
276
|
- **[GEPA Optimizer](docs/src/optimization/gepa.md)** *(beta)* - Reflective mutation with optional reflection LMs
|
|
171
277
|
|
|
172
|
-
###
|
|
173
|
-
- **[
|
|
174
|
-
- **[
|
|
175
|
-
|
|
176
|
-
### Advanced Usage
|
|
177
|
-
- **[Complex Types](docs/src/advanced/complex-types.md)** - Sorbet type integration with automatic coercion for structs, enums, and arrays
|
|
178
|
-
- **[Manual Pipelines](docs/src/advanced/pipelines.md)** - Manual module composition patterns
|
|
278
|
+
### Context Engineering
|
|
279
|
+
- **[Tools](docs/src/core-concepts/toolsets.md)** - Tool wieldint agents.
|
|
280
|
+
- **[Agentic Memory](docs/src/core-concepts/memory.md)** - Memory Tools & Agentic Loops
|
|
179
281
|
- **[RAG Patterns](docs/src/advanced/rag.md)** - Manual RAG implementation with external services
|
|
180
|
-
- **[Custom Metrics](docs/src/advanced/custom-metrics.md)** - Proc-based evaluation logic
|
|
181
|
-
|
|
182
|
-
## Quick Start
|
|
183
|
-
|
|
184
|
-
### Installation
|
|
185
|
-
|
|
186
|
-
Add to your Gemfile:
|
|
187
282
|
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
Then run:
|
|
193
|
-
|
|
194
|
-
```bash
|
|
195
|
-
bundle install
|
|
196
|
-
```
|
|
197
|
-
|
|
198
|
-
## Recent Achievements
|
|
199
|
-
|
|
200
|
-
DSPy.rb has rapidly evolved from experimental to production-ready:
|
|
201
|
-
|
|
202
|
-
### Foundation
|
|
203
|
-
- ✅ **JSON Parsing Reliability** - Native OpenAI structured outputs, strategy selection, retry logic
|
|
204
|
-
- ✅ **Type-Safe Strategy Configuration** - Provider-optimized automatic strategy selection
|
|
205
|
-
- ✅ **Core Module System** - Predict, ChainOfThought, ReAct, CodeAct with type safety
|
|
206
|
-
- ✅ **Production Observability** - OpenTelemetry, New Relic, and Langfuse integration
|
|
207
|
-
- ✅ **Advanced Optimization** - MIPROv2 with Bayesian optimization, Gaussian Processes, and multiple strategies
|
|
283
|
+
### Production Features
|
|
284
|
+
- **[Observability](docs/src/production/observability.md)** - Zero-config Langfuse integration with a dedicated export worker that never blocks your LLMs
|
|
285
|
+
- **[Storage System](docs/src/production/storage.md)** - Persistence and optimization result storage
|
|
286
|
+
- **[Custom Metrics](docs/src/advanced/custom-metrics.md)** - Proc-based evaluation logic
|
|
208
287
|
|
|
209
|
-
### Recent Advances
|
|
210
|
-
- ✅ **Enhanced Langfuse Integration (v0.25.0)** - Comprehensive OpenTelemetry span reporting with proper input/output, hierarchical nesting, accurate timing, and observation types
|
|
211
|
-
- ✅ **Comprehensive Multimodal Framework** - Complete image analysis with `DSPy::Image`, type-safe bounding boxes, vision model integration
|
|
212
|
-
- ✅ **Advanced Type System** - `T::Enum` integration, union types for agentic workflows, complex type coercion
|
|
213
|
-
- ✅ **Production-Ready Evaluation** - Multi-factor metrics beyond accuracy, error-resilient evaluation pipelines
|
|
214
|
-
- ✅ **Documentation Ecosystem** - `llms.txt` for AI assistants, ADRs, blog articles, comprehensive examples
|
|
215
|
-
- ✅ **API Maturation** - Simplified idiomatic patterns, better error handling, production-proven designs
|
|
216
288
|
|
|
217
|
-
## Roadmap - Production Battle-Testing Toward v1.0
|
|
218
289
|
|
|
219
|
-
DSPy.rb has transitioned from **feature building** to **production validation**. The core framework is
|
|
220
|
-
feature-complete and stable - now I'm focusing on real-world usage patterns, performance optimization,
|
|
221
|
-
and ecosystem integration.
|
|
222
290
|
|
|
223
|
-
**Current Focus Areas:**
|
|
224
291
|
|
|
225
|
-
### Production Readiness
|
|
226
|
-
- 🚧 **Production Patterns** - Real-world usage validation and performance optimization
|
|
227
|
-
- 🚧 **Ruby Ecosystem Integration** - Rails integration, Sidekiq compatibility, deployment patterns
|
|
228
|
-
- 🚧 **Scale Testing** - High-volume usage, memory management, connection pooling
|
|
229
|
-
- 🚧 **Error Recovery** - Robust failure handling patterns for production environments
|
|
230
292
|
|
|
231
|
-
### Ecosystem Expansion
|
|
232
|
-
- 🚧 **Model Context Protocol (MCP)** - Integration with MCP ecosystem
|
|
233
|
-
- 🚧 **Additional Provider Support** - Azure OpenAI, local models beyond Ollama
|
|
234
|
-
- 🚧 **Tool Ecosystem** - Expanded tool integrations for ReAct agents
|
|
235
293
|
|
|
236
|
-
### Community & Adoption
|
|
237
|
-
- 🚧 **Community Examples** - Real-world applications and case studies
|
|
238
|
-
- 🚧 **Contributor Experience** - Making it easier to contribute and extend
|
|
239
|
-
- 🚧 **Performance Benchmarks** - Comparative analysis vs other frameworks
|
|
240
|
-
|
|
241
|
-
**v1.0 Philosophy:**
|
|
242
|
-
v1.0 will be released after extensive production battle-testing, not after checking off features.
|
|
243
|
-
The API is already stable - v1.0 represents confidence in production reliability backed by real-world validation.
|
|
244
294
|
|
|
245
295
|
## License
|
|
246
|
-
|
|
247
296
|
This project is licensed under the MIT License.
|
data/lib/gepa/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,28 +1,28 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: gepa
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 1.0.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Vicente Reig Rincón de Arellano
|
|
8
8
|
bindir: bin
|
|
9
9
|
cert_chain: []
|
|
10
|
-
date:
|
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
11
11
|
dependencies:
|
|
12
12
|
- !ruby/object:Gem::Dependency
|
|
13
13
|
name: dspy
|
|
14
14
|
requirement: !ruby/object:Gem::Requirement
|
|
15
15
|
requirements:
|
|
16
|
-
- -
|
|
16
|
+
- - "<"
|
|
17
17
|
- !ruby/object:Gem::Version
|
|
18
|
-
version: 0.
|
|
18
|
+
version: 1.0.0
|
|
19
19
|
type: :runtime
|
|
20
20
|
prerelease: false
|
|
21
21
|
version_requirements: !ruby/object:Gem::Requirement
|
|
22
22
|
requirements:
|
|
23
|
-
- -
|
|
23
|
+
- - "<"
|
|
24
24
|
- !ruby/object:Gem::Version
|
|
25
|
-
version: 0.
|
|
25
|
+
version: 1.0.0
|
|
26
26
|
description: GEPA delivers optimization strategies, telemetry, and proposer tooling
|
|
27
27
|
for reflective DSPy agents.
|
|
28
28
|
email:
|
|
@@ -72,7 +72,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
72
72
|
- !ruby/object:Gem::Version
|
|
73
73
|
version: '0'
|
|
74
74
|
requirements: []
|
|
75
|
-
rubygems_version: 3.6.
|
|
75
|
+
rubygems_version: 3.6.9
|
|
76
76
|
specification_version: 4
|
|
77
77
|
summary: Gradient-based Exploration and Pareto Agents for DSPy.rb.
|
|
78
78
|
test_files: []
|