Skip to content

Releases: crewAIInc/crewAI

0.65.2

27 Sep 23:55
Compare
Choose a tag to compare
  • Adding experimental Flows feature
  • Fixing order of tasks bug
  • Updating templates

0.64.0

27 Sep 01:20
Compare
Choose a tag to compare
  • Ordering tasks properly
  • Fixing summarization logic
  • Fixing stop words logic
  • Increases default max iterations to 20
  • Fix crew's key after input interpolation
  • Fixing Training Feature
  • Adding initial tools API
  • TYPOS
  • Updating Docs

Fixes: #1359 #1355 #1353 #1356 and others

v0.63.6

25 Sep 03:32
Compare
Choose a tag to compare
  • Updating projects templates

v0.63.5

25 Sep 03:03
Compare
Choose a tag to compare
  • Bringing support to o1 family back, and any model that don't support stop words
  • Updating dependencies
  • Updating logs
  • Updating docs

v0.63.2

24 Sep 05:04
Compare
Choose a tag to compare
  • Adding OPENAI_BASE_URL as fallback
  • Adding proper LLM import
  • Updating docs

v0.63.1

24 Sep 01:16
Compare
Choose a tag to compare
  • Small bug fix for support future CrewAI deploy

v0.63.0

24 Sep 00:08
Compare
Choose a tag to compare
  • New LLM class to interact with LLMs (leveraging LiteLLM)
  • Adding support to custom memory interfaces
  • Bringing GPT-4o-mini as the default model
  • Updates Docs
  • Updating dependencies
  • Bug fixes
    • Remove redundant task creation in kickoff_for_each_async

v0.61.0

18 Sep 07:59
Compare
Choose a tag to compare
  • Updating dependencies
  • Printing max rpm message in different color
  • Updating all cassettes for tests
  • Always ending on a user message - to better support certain models like bedrock ones
  • Overall small bug fixes

v0.60.0

16 Sep 18:41
e77442c
Compare
Choose a tag to compare
  • Removing LangChain and Rebuilding Executor
  • Get all of out tests back to green
  • Adds the ability to not use system prompt use_system_prompt on the Agent
  • Adds the ability to not use stop words (to support o1 models) use_stop_words on the Agent
  • Sliding context window gets renamed to respect_context_window, and enable by default
  • Delegation is now disabled by default
  • Inner prompts were slightly changed as well
  • Overall reliability and quality of results
  • New support for:
    • Number of max requests per minute
    • A maximum number of iterations before giving a final answer
    • Proper take advantage of system prompts
    • Token calculation flow
    • New logging of the crew and agent execution

v0.55.2

13 Sep 17:28
322780a
Compare
Choose a tag to compare

What's Changed

  • Adding ability for auto complete
  • Add name and expected_output to TaskOutput
  • New crewai install CLI
  • New crewai deploy CLI
  • Cleaning up of Pipeline feature
  • Updated docs
  • Dev experience improvements like bandit CI pipeline
  • Fix bugs:
    • Ability to use planning_llm
    • Fix YAML based projects
    • Fix Azure support
    • Add support to Python 3.10
    • Moving away from Pydantic v1