rcrewai 0.10.0 → 0.11.0

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.
Files changed (56) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +24 -0
  3. data/README.md +133 -23
  4. data/ROADMAP.md +1 -1
  5. data/docs/api/agent.md +5 -2
  6. data/docs/api/configuration.md +36 -41
  7. data/docs/api/crew.md +34 -48
  8. data/docs/api/index.md +7 -0
  9. data/docs/api/task.md +10 -91
  10. data/docs/api/tools.md +19 -0
  11. data/docs/examples/api-integration.md +4 -4
  12. data/docs/examples/async-execution.md +4 -4
  13. data/docs/examples/code-review-crew.md +1 -1
  14. data/docs/examples/content-marketing-pipeline.md +3 -3
  15. data/docs/examples/custom-tools.md +8 -8
  16. data/docs/examples/customer-support.md +5 -5
  17. data/docs/examples/data-analysis-team.md +4 -4
  18. data/docs/examples/database-operations.md +4 -4
  19. data/docs/examples/ecommerce-operations.md +4 -4
  20. data/docs/examples/financial-analysis.md +3 -3
  21. data/docs/examples/hierarchical-crew.md +3 -2
  22. data/docs/examples/production-ready-crew.md +16 -10
  23. data/docs/examples/research-development.md +5 -5
  24. data/docs/examples/simple-research-crew.md +2 -2
  25. data/docs/examples/social-media.md +4 -4
  26. data/docs/examples/task-automation.md +2 -2
  27. data/docs/examples/tool-composition.md +42 -27
  28. data/docs/examples/web-scraping.md +6 -6
  29. data/docs/index.md +61 -44
  30. data/docs/tutorials/advanced-agents.md +194 -917
  31. data/docs/tutorials/agent-options.md +1 -1
  32. data/docs/tutorials/checkpointing.md +65 -0
  33. data/docs/tutorials/concurrency.md +57 -0
  34. data/docs/tutorials/custom-tools.md +198 -1143
  35. data/docs/tutorials/deployment.md +156 -155
  36. data/docs/tutorials/getting-started.md +69 -81
  37. data/docs/tutorials/index.md +19 -0
  38. data/docs/tutorials/interceptors-and-events.md +84 -0
  39. data/docs/tutorials/live-streaming.md +52 -0
  40. data/docs/tutorials/multiple-crews.md +70 -51
  41. data/docs/tutorials/providers.md +115 -0
  42. data/docs/upgrading-to-0.11.md +55 -0
  43. data/lib/rcrewai/agent.rb +0 -2
  44. data/lib/rcrewai/configuration.rb +64 -29
  45. data/lib/rcrewai/context_window.rb +12 -2
  46. data/lib/rcrewai/llm_clients/anthropic.rb +60 -9
  47. data/lib/rcrewai/llm_clients/base.rb +7 -0
  48. data/lib/rcrewai/llm_clients/bedrock.rb +29 -2
  49. data/lib/rcrewai/llm_clients/google.rb +36 -4
  50. data/lib/rcrewai/llm_clients/ollama.rb +17 -3
  51. data/lib/rcrewai/llm_clients/openai.rb +14 -1
  52. data/lib/rcrewai/llm_clients/openai_responses.rb +21 -2
  53. data/lib/rcrewai/pricing.rb +13 -3
  54. data/lib/rcrewai/tool_runner.rb +5 -1
  55. data/lib/rcrewai/version.rb +1 -1
  56. metadata +7 -1
data/docs/index.md CHANGED
@@ -44,6 +44,16 @@ RCrewAI has expanded well beyond the classic crew model. Recent releases added:
44
44
  See the [CHANGELOG](https://github.com/gkosmo/rcrewAI/blob/main/CHANGELOG.md) and the
45
45
  per-release upgrade guides (e.g. [upgrading to 0.7](https://github.com/gkosmo/rcrewAI/blob/main/docs/upgrading-to-0.7.md)) for details.
46
46
 
47
+ ## What's new (0.8 – 0.10)
48
+
49
+ - **[Providers]({{ site.baseurl }}/tutorials/providers)**: AWS Bedrock, Snowflake Cortex, OpenAI-compatible endpoints and the Responses API
50
+ - **[Checkpointing]({{ site.baseurl }}/tutorials/checkpointing)**: resume a failed run without repeating finished tasks
51
+ - **[Interceptors and events]({{ site.baseurl }}/tutorials/interceptors-and-events)**: hook into LLM calls and rebuild a run into a trace
52
+ - **[Concurrency]({{ site.baseurl }}/tutorials/concurrency)**: parallel tool calls, consensus rounds and embeddings, each with a limit
53
+ - **[Live streaming]({{ site.baseurl }}/tutorials/live-streaming)**: cancellable Anthropic streams with connection reuse
54
+
55
+ Upgrading? See [what to check]({{ site.baseurl }}/upgrading-to-0.11).
56
+
47
57
  ## Quick Start
48
58
 
49
59
  ### Basic Agent Collaboration
@@ -185,51 +195,32 @@ $ gem install rcrewai
185
195
 
186
196
  ## CLI Usage
187
197
 
188
- RCrewAI includes a powerful CLI for managing your AI crews:
189
-
190
198
  ```bash
191
- # Create a new crew with different process types
192
- $ rcrewai new my_research_crew --process sequential
193
- $ rcrewai new enterprise_team --process hierarchical
194
-
195
- # List available crews and agents
199
+ # Create and list crews
200
+ $ rcrewai new my_research_crew
196
201
  $ rcrewai list
197
- $ rcrewai agents list
198
202
 
199
- # Create agents with advanced capabilities
203
+ # Create agents and tasks
200
204
  $ rcrewai agent new researcher \
201
205
  --role "Senior Research Analyst" \
202
- --goal "Find cutting-edge AI information" \
203
- --backstory "Expert researcher with 10 years experience" \
204
- --tools web_search,file_writer \
205
- --verbose \
206
- --human-input
207
-
208
- # Create manager agents for hierarchical crews
209
- $ rcrewai agent new project_manager \
210
- --role "Project Coordinator" \
211
- --goal "Coordinate team execution" \
212
- --manager \
213
- --allow-delegation
214
-
215
- # Create tasks with dependencies and human interaction
206
+ --goal "Find reliable sources"
207
+
216
208
  $ rcrewai task new research \
217
209
  --description "Research latest AI developments" \
218
- --expected-output "Comprehensive AI research report" \
219
210
  --agent researcher \
220
- --async \
221
- --human-input \
222
- --require-confirmation
211
+ --async
223
212
 
224
- # Run crews with different execution modes
213
+ # Run a crew
225
214
  $ rcrewai run --crew my_research_crew
226
- $ rcrewai run --crew enterprise_team --async --max-concurrency 4
227
215
 
228
- # Check crew status and results
229
- $ rcrewai status --crew my_research_crew
230
- $ rcrewai results --crew my_research_crew --task research
216
+ # Inspect saved checkpoints
217
+ $ rcrewai checkpoint list
218
+ $ rcrewai checkpoint info RUN_ID
219
+ $ rcrewai checkpoint delete RUN_ID
231
220
  ```
232
221
 
222
+ `checkpoint` and `version` are fully working. The `new`, `list`, `run`, `agent` and `task` commands are placeholders: they don't save anything, the lists are sample names, and `run` executes an empty crew. For now, define crews in Ruby.
223
+
233
224
  ## Key Capabilities
234
225
 
235
226
  ### 🧠 **Advanced Agent Intelligence**
@@ -287,44 +278,70 @@ Built for enterprise deployment and reliability:
287
278
  RCrewAI works with all major LLM providers through a unified interface:
288
279
 
289
280
  ```ruby
290
- # OpenAI (GPT-4, GPT-3.5, etc.)
281
+ # OpenAI
291
282
  RCrewAI.configure do |config|
292
283
  config.llm_provider = :openai
293
284
  config.openai_api_key = ENV['OPENAI_API_KEY']
294
- config.model = 'gpt-4'
295
- config.temperature = 0.1
285
+ config.openai_model = 'gpt-4o'
296
286
  end
297
287
 
298
- # Anthropic Claude
288
+ # Anthropic
299
289
  RCrewAI.configure do |config|
300
290
  config.llm_provider = :anthropic
301
- config.anthropic_api_key = ENV['ANTHROPIC_API_KEY']
302
- config.model = 'claude-3-sonnet-20240229'
291
+ config.anthropic_api_key = ENV['ANTHROPIC_API_KEY']
292
+ config.anthropic_model = 'claude-opus-5-5'
303
293
  end
304
294
 
305
295
  # Google Gemini
306
296
  RCrewAI.configure do |config|
307
297
  config.llm_provider = :google
308
298
  config.google_api_key = ENV['GOOGLE_API_KEY']
309
- config.model = 'gemini-pro'
299
+ config.google_model = 'gemini-3.8-flash'
310
300
  end
311
301
 
312
302
  # Azure OpenAI
313
303
  RCrewAI.configure do |config|
314
304
  config.llm_provider = :azure
315
305
  config.azure_api_key = ENV['AZURE_OPENAI_API_KEY']
316
- config.azure_endpoint = ENV['AZURE_OPENAI_ENDPOINT']
317
- config.model = 'gpt-4'
306
+ config.base_url = ENV['AZURE_OPENAI_ENDPOINT']
307
+ config.deployment_name = 'your-deployment'
308
+ config.api_version = '2024-10-21'
318
309
  end
319
310
 
320
- # Local Ollama
311
+ # Local Ollama (no API key)
321
312
  RCrewAI.configure do |config|
322
313
  config.llm_provider = :ollama
323
- config.ollama_url = 'http://localhost:11434'
324
- config.model = 'llama2'
314
+ config.base_url = 'http://localhost:11434'
315
+ config.model = 'llama3.1'
316
+ end
317
+
318
+ # Any OpenAI-compatible endpoint: Together, Groq, Fireworks, vLLM, LiteLLM, OpenRouter
319
+ RCrewAI.configure do |config|
320
+ config.llm_provider = :openai_compatible
321
+ config.base_url = 'https://api.groq.com/openai/v1'
322
+ config.api_key = ENV['GROQ_API_KEY']
323
+ config.model = 'your-model'
324
+ end
325
+
326
+ # AWS Bedrock (bearer token; SigV4 signing isn't built in)
327
+ RCrewAI.configure do |config|
328
+ config.llm_provider = :bedrock
329
+ config.aws_region = 'us-east-1'
330
+ config.api_key = ENV['BEDROCK_API_KEY']
331
+ config.model = 'your-bedrock-model-id'
332
+ end
333
+
334
+ # Snowflake Cortex
335
+ RCrewAI.configure do |config|
336
+ config.llm_provider = :snowflake
337
+ config.snowflake_account = 'your-account'
338
+ config.api_key = ENV['SNOWFLAKE_TOKEN']
339
+ config.model = 'your-cortex-model'
325
340
  end
326
341
  ```
327
342
 
343
+ There's also `:openai_responses`, which uses OpenAI's Responses API (no streaming) with your OpenAI model and key settings.
344
+
328
345
  ## Use Cases
329
346
 
330
347
  RCrewAI excels in scenarios requiring: