andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 16:18:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
273491f61a4d8b742bc71f3fa853741ab479bcfa
crewAI/lib/crewai/tests/cassettes/test_after_crew_modification.yaml
Lorenze Jay d1343b96ed Release/v1.0.0 (#3618) 
* feat: add `apps` & `actions` attributes to Agent (#3504)

* feat: add app attributes to Agent

* feat: add actions attribute to Agent

* chore: resolve linter issues

* refactor: merge the apps and actions parameters into a single one

* fix: remove unnecessary print

* feat: logging error when CrewaiPlatformTools fails

* chore: export CrewaiPlatformTools directly from crewai_tools

* style: resolver linter issues

* test: fix broken tests

* style: solve linter issues

* fix: fix broken test

* feat: monorepo restructure and test/ci updates

- Add crewai workspace member
- Fix vcr cassette paths and restore test dirs
- Resolve ci failures and update linter/pytest rules

* chore: update python version to 3.13 and package metadata

* feat: add crewai-tools workspace and fix tests/dependencies

* feat: add crewai-tools workspace structure

* Squashed 'temp-crewai-tools/' content from commit 9bae5633

git-subtree-dir: temp-crewai-tools
git-subtree-split: 9bae56339096cb70f03873e600192bd2cd207ac9

* feat: configure crewai-tools workspace package with dependencies

* fix: apply ruff auto-formatting to crewai-tools code

* chore: update lockfile

* fix: don't allow tool tests yet

* fix: comment out extra pytest flags for now

* fix: remove conflicting conftest.py from crewai-tools tests

* fix: resolve dependency conflicts and test issues

- Pin vcrpy to 7.0.0 to fix pytest-recording compatibility
- Comment out types-requests to resolve urllib3 conflict
- Update requests requirement in crewai-tools to >=2.32.0

* chore: update CI workflows and docs for monorepo structure

* chore: update CI workflows and docs for monorepo structure

* fix: actions syntax

* chore: ci publish and pin versions

* fix: add permission to action

* chore: bump version to 1.0.0a1 across all packages

- Updated version to 1.0.0a1 in pyproject.toml for crewai and crewai-tools
- Adjusted version in __init__.py files for consistency

* WIP: v1 docs (#3626)

(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)

* docs: parity for all translations

* docs: full name of acronym AMP

* docs: fix lingering unused code

* docs: expand contextual options in docs.json

* docs: add contextual action to request feature on GitHub (#3635)

* chore: apply linting fixes to crewai-tools

* feat: add required env var validation for brightdata

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* fix: handle properly anyOf oneOf allOf schema's props

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: bump version to 1.0.0a2

* Lorenze/native inference sdks (#3619)

* ruff linted

* using native sdks with litellm fallback

* drop exa

* drop print on completion

* Refactor LLM and utility functions for type consistency

- Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`.
- Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`.
- Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety.
- Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances.

* fix agent_tests

* fix litellm tests and usagemetrics fix

* drop print

* Refactor LLM event handling and improve test coverage

- Removed commented-out event emission for LLM call failures in `llm.py`.
- Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses.
- Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity.
- Updated agent and task ID assertions in tests to ensure they are consistently treated as strings.

* fix test_converter

* fixed tests/agents/test_agent.py

* Refactor LLM context length exception handling and improve provider integration

- Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency.
- Updated LLM class to pass the provider parameter correctly during initialization.
- Enhanced error handling in various LLM provider implementations to raise the new exception type.
- Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios.

* Enhance LLM context window handling across providers

- Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs.
- Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits.
- Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models.
- Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility.

* fix test agent again

* fix test agent

* feat: add native LLM providers for Anthropic, Azure, and Gemini

- Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs.
- Added utility functions for tool validation and extraction to support function calling across LLM providers.
- Enhanced context window management and token usage extraction for each provider.
- Created a common utility module for shared functionality among LLM providers.

* chore: update dependencies and improve context management

- Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity.
- Updated the `litellm` dependency specification to allow for greater flexibility in versioning.
- Refactored context length exception handling across various LLM providers to use a consistent error class.
- Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems.

* refactor(tests): update LLM instantiation to include is_litellm flag in test cases

- Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class.
- This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios.
- Adjusted relevant assertions and comments to reflect the updated LLM behavior.

* linter

* linted

* revert constants

* fix(tests): correct type hint in expected model description

- Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions.
- This change ensures that the test accurately reflects the expected output format for model descriptions.

* refactor(llm): enhance LLM instantiation and error handling

- Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string.
- Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM.
- Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration.
- Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios.

* fixed test

* refactor(llm): enhance token usage tracking and add copy methods

- Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities.
- Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters.
- Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration.

* refactor(tests): reorganize imports and enhance error messages in test cases

- Cleaned up import statements in test_crew.py for better organization and readability.
- Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling.
- Adjusted comments for clarity and consistency across test scenarios.
- Ensured that all necessary modules are imported correctly to avoid potential runtime issues.

* feat: add base devtooling

* fix: ensure dep refs are updated for devtools

* fix: allow pre-release

* feat: allow release after tag

* feat: bump versions to 1.0.0a3 

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

* fix: match tag and release title, ignore devtools build for pypi

* fix: allow failed pypi publish

* feat: introduce trigger listing and execution commands for local development (#3643)

* chore: exclude tests from ruff linting

* chore: exclude tests from GitHub Actions linter

* fix: replace print statements with logger in agent and memory handling

* chore: add noqa for intentional print in printer utility

* fix: resolve linting errors across codebase

* feat: update docs with new approach to consume Platform Actions (#3675)

* fix: remove duplicate line and add explicit env var

* feat: bump versions to 1.0.0a4 (#3686)

* Update triggers docs (#3678)

* docs: introduce triggers list & triggers run command

* docs: add KO triggers docs

* docs: ensure CREWAI_PLATFORM_INTEGRATION_TOKEN is mentioned on docs (#3687)

* Lorenze/bedrock llm (#3693)

* feat: add AWS Bedrock support and update dependencies

- Introduced BedrockCompletion class for AWS Bedrock integration in LLM.
- Added boto3 as a new dependency in both pyproject.toml and uv.lock.
- Updated LLM class to support Bedrock provider.
- Created new files for Bedrock provider implementation.

* using converse api

* converse

* linted

* refactor: update BedrockCompletion class to improve parameter handling

- Changed max_tokens from a fixed integer to an optional integer.
- Simplified model ID assignment by removing the inference profile mapping method.
- Cleaned up comments and unnecessary code related to tool specifications and model-specific parameters.

* feat: improve event bus thread safety and async support

Add thread-safe, async-compatible event bus with read–write locking and
handler dependency ordering. Remove blinker dependency and implement
direct dispatch. Improve type safety, error handling, and deterministic
event synchronization.

Refactor tests to auto-wait for async handlers, ensure clean teardown,
and add comprehensive concurrency coverage. Replace thread-local state
in AgentEvaluator with instance-based locking for correct cross-thread
access. Enhance tracing reliability and event finalization.

* feat: enhance OpenAICompletion class with additional client parameters (#3701)

* feat: enhance OpenAICompletion class with additional client parameters

- Added support for default_headers, default_query, and client_params in the OpenAICompletion class.
- Refactored client initialization to use a dedicated method for client parameter retrieval.
- Introduced new test cases to validate the correct usage of OpenAICompletion with various parameters.

* fix: correct test case for unsupported OpenAI model

- Updated the test_openai.py to ensure that the LLM instance is created before calling the method, maintaining proper error handling for unsupported models.
- This change ensures that the test accurately checks for the NotFoundError when an invalid model is specified.

* fix: enhance error handling in OpenAICompletion class

- Added specific exception handling for NotFoundError and APIConnectionError in the OpenAICompletion class to provide clearer error messages and improve logging.
- Updated the test case for unsupported models to ensure it raises a ValueError with the appropriate message when a non-existent model is specified.
- This change improves the robustness of the OpenAI API integration and enhances the clarity of error reporting.

* fix: improve test for unsupported OpenAI model handling

- Refactored the test case in test_openai.py to create the LLM instance after mocking the OpenAI client, ensuring proper error handling for unsupported models.
- This change enhances the clarity of the test by accurately checking for ValueError when a non-existent model is specified, aligning with recent improvements in error handling for the OpenAICompletion class.

* feat: bump versions to 1.0.0b1 (#3706)

* Lorenze/tools drop litellm (#3710)

* completely drop litellm and correctly pass config for qdrant

* feat: add support for additional embedding models in EmbeddingService

- Expanded the list of supported embedding models to include Google Vertex, Hugging Face, Jina, Ollama, OpenAI, Roboflow, Watson X, custom embeddings, Sentence Transformers, Text2Vec, OpenClip, and Instructor.
- This enhancement improves the versatility of the EmbeddingService by allowing integration with a wider range of embedding providers.

* fix: update collection parameter handling in CrewAIRagAdapter

- Changed the condition for setting vectors_config in the CrewAIRagAdapter to check for QdrantConfig instance instead of using hasattr. This improves type safety and ensures proper configuration handling for Qdrant integration.

* moved stagehand as optional dep (#3712)

* feat: bump versions to 1.0.0b2 (#3713)

* feat: enhance AnthropicCompletion class with additional client parame… (#3707)

* feat: enhance AnthropicCompletion class with additional client parameters and tool handling

- Added support for client_params in the AnthropicCompletion class to allow for additional client configuration.
- Refactored client initialization to use a dedicated method for retrieving client parameters.
- Implemented a new method to handle tool use conversation flow, ensuring proper execution and response handling.
- Introduced comprehensive test cases to validate the functionality of the AnthropicCompletion class, including tool use scenarios and parameter handling.

* drop print statements

* test: add fixture to mock ANTHROPIC_API_KEY for tests

- Introduced a pytest fixture to automatically mock the ANTHROPIC_API_KEY environment variable for all tests in the test_anthropic.py module.
- This change ensures that tests can run without requiring a real API key, improving test isolation and reliability.

* refactor: streamline streaming message handling in AnthropicCompletion class

- Removed the 'stream' parameter from the API call as it is set internally by the SDK.
- Simplified the handling of tool use events and response construction by extracting token usage from the final message.
- Enhanced the flow for managing tool use conversation, ensuring proper integration with the streaming API response.

* fix streaming here too

* fix: improve error handling in tool conversion for AnthropicCompletion class

- Enhanced exception handling during tool conversion by catching KeyError and ValueError.
- Added logging for conversion errors to aid in debugging and maintain robustness in tool integration.

* feat: enhance GeminiCompletion class with client parameter support (#3717)

* feat: enhance GeminiCompletion class with client parameter support

- Added support for client_params in the GeminiCompletion class to allow for additional client configuration.
- Refactored client initialization into a dedicated method for improved parameter handling.
- Introduced a new method to retrieve client parameters, ensuring compatibility with the base class.
- Enhanced error handling during client initialization to provide clearer messages for missing configuration.
- Updated documentation to reflect the changes in client parameter usage.

* add optional dependancies

* refactor: update test fixture to mock GOOGLE_API_KEY

- Renamed the fixture from `mock_anthropic_api_key` to `mock_google_api_key` to reflect the change in the environment variable being mocked.
- This update ensures that all tests in the module can run with a mocked GOOGLE_API_KEY, improving test isolation and reliability.

* fix tests

* feat: enhance BedrockCompletion class with advanced features

* feat: enhance BedrockCompletion class with advanced features and error handling

- Added support for guardrail configuration, additional model request fields, and custom response field paths in the BedrockCompletion class.
- Improved error handling for AWS exceptions and added token usage tracking with stop reason logging.
- Enhanced streaming response handling with comprehensive event management, including tool use and content block processing.
- Updated documentation to reflect new features and initialization parameters.
- Introduced a new test suite for BedrockCompletion to validate functionality and ensure robust integration with AWS Bedrock APIs.

* chore: add boto typing

* fix: use typing_extensions.Required for Python 3.10 compatibility

---------

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: azure native tests

* feat: add Azure AI Inference support and related tests

- Introduced the `azure-ai-inference` package with version `1.0.0b9` and its dependencies in `uv.lock` and `pyproject.toml`.
- Added new test files for Azure LLM functionality, including tests for Azure completion and tool handling.
- Implemented comprehensive test cases to validate Azure-specific behavior and integration with the CrewAI framework.
- Enhanced the testing framework to mock Azure credentials and ensure proper isolation during tests.

* feat: enhance AzureCompletion class with Azure OpenAI support

- Added support for the Azure OpenAI endpoint in the AzureCompletion class, allowing for flexible endpoint configurations.
- Implemented endpoint validation and correction to ensure proper URL formats for Azure OpenAI deployments.
- Enhanced error handling to provide clearer messages for common HTTP errors, including authentication and rate limit issues.
- Updated tests to validate the new endpoint handling and error messaging, ensuring robust integration with Azure AI Inference.
- Refactored parameter preparation to conditionally include the model parameter based on the endpoint type.

* refactor: convert project module to metaclass with full typing

* Lorenze/OpenAI base url backwards support (#3723)

* fix: enhance OpenAICompletion class base URL handling

- Updated the base URL assignment in the OpenAICompletion class to prioritize the new `api_base` attribute and fallback to the environment variable `OPENAI_BASE_URL` if both are not set.
- Added `api_base` to the list of parameters in the OpenAICompletion class to ensure proper configuration and flexibility in API endpoint management.

* feat: enhance OpenAICompletion class with api_base support

- Added the `api_base` parameter to the OpenAICompletion class to allow for flexible API endpoint configuration.
- Updated the `_get_client_params` method to prioritize `base_url` over `api_base`, ensuring correct URL handling.
- Introduced comprehensive tests to validate the behavior of `api_base` and `base_url` in various scenarios, including environment variable fallback.
- Enhanced test coverage for client parameter retrieval, ensuring robust integration with the OpenAI API.

* fix: improve OpenAICompletion class configuration handling

- Added a debug print statement to log the client configuration parameters during initialization for better traceability.
- Updated the base URL assignment logic to ensure it defaults to None if no valid base URL is provided, enhancing robustness in API endpoint configuration.
- Refined the retrieval of the `api_base` environment variable to streamline the configuration process.

* drop print

* feat: improvements on import native sdk support (#3725)

* feat: add support for Anthropic provider and enhance logging

- Introduced the `anthropic` package with version `0.69.0` in `pyproject.toml` and `uv.lock`, allowing for integration with the Anthropic API.
- Updated logging in the LLM class to provide clearer error messages when importing native providers, enhancing debugging capabilities.
- Improved error handling in the AnthropicCompletion class to guide users on installation via the updated error message format.
- Refactored import error handling in other provider classes to maintain consistency in error messaging and installation instructions.

* feat: enhance LLM support with Bedrock provider and update dependencies

- Added support for the `bedrock` provider in the LLM class, allowing integration with AWS Bedrock APIs.
- Updated `uv.lock` to replace `boto3` with `bedrock` in the dependencies, reflecting the new provider structure.
- Introduced `SUPPORTED_NATIVE_PROVIDERS` to include `bedrock` and ensure proper error handling when instantiating native providers.
- Enhanced error handling in the LLM class to raise informative errors when native provider instantiation fails.
- Added tests to validate the behavior of the new Bedrock provider and ensure fallback mechanisms work correctly for unsupported providers.

* test: update native provider fallback tests to expect ImportError

* adjust the test with the expected bevaior - raising ImportError

* this is exoecting the litellm format, all gemini native tests are in test_google.py

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

* fix: remove stdout prints, improve test determinism, and update trace handling

Removed `print` statements from the `LLMStreamChunkEvent` handler to prevent
LLM response chunks from being written directly to stdout. The listener now
only tracks chunks internally.

Fixes #3715

Added explicit return statements for trace-related tests.

Updated cassette for `test_failed_evaluation` to reflect new behavior where
an empty trace dict is used instead of returning early.

Ensured deterministic cleanup order in test fixtures by making
`clear_event_bus_handlers` depend on `setup_test_environment`. This guarantees
event bus shutdown and file handle cleanup occur before temporary directory
deletion, resolving intermittent “Directory not empty” errors in CI.

* chore: remove lib/crewai exclusion from pre-commit hooks

* feat: enhance task guardrail functionality and validation

* feat: enhance task guardrail functionality and validation

- Introduced support for multiple guardrails in the Task class, allowing for sequential processing of guardrails.
- Added a new `guardrails` field to the Task model to accept a list of callable guardrails or string descriptions.
- Implemented validation to ensure guardrails are processed correctly, including handling of retries and error messages.
- Enhanced the `_invoke_guardrail_function` method to manage guardrail execution and integrate with existing task output processing.
- Updated tests to cover various scenarios involving multiple guardrails, including success, failure, and retry mechanisms.

This update improves the flexibility and robustness of task execution by allowing for more complex validation scenarios.

* refactor: enhance guardrail type handling in Task model

- Updated the Task class to improve guardrail type definitions, introducing GuardrailType and GuardrailsType for better clarity and type safety.
- Simplified the validation logic for guardrails, ensuring that both single and multiple guardrails are processed correctly.
- Enhanced error messages for guardrail validation to provide clearer feedback when incorrect types are provided.
- This refactor improves the maintainability and robustness of task execution by standardizing guardrail handling.

* feat: implement per-guardrail retry tracking in Task model

- Introduced a new private attribute `_guardrail_retry_counts` to the Task class for tracking retry attempts on a per-guardrail basis.
- Updated the guardrail processing logic to utilize the new retry tracking, allowing for independent retry counts for each guardrail.
- Enhanced error handling to provide clearer feedback when guardrails fail validation after exceeding retry limits.
- Modified existing tests to validate the new retry tracking behavior, ensuring accurate assertions on guardrail retries.

This update improves the robustness and flexibility of task execution by allowing for more granular control over guardrail validation and retry mechanisms.

* chore: 1.0.0b3 bump (#3734)

* chore: full ruff and mypy

improved linting, pre-commit setup, and internal architecture. Configured Ruff to respect .gitignore, added stricter rules, and introduced a lock pre-commit hook with virtualenv activation. Fixed type shadowing in EXASearchTool using a type_ alias to avoid PEP 563 conflicts and resolved circular imports in agent executor and guardrail modules. Removed agent-ops attributes, deprecated watson alias, and dropped crewai-enterprise tools with corresponding test updates. Refactored cache and memoization for thread safety and cleaned up structured output adapters and related logic.

* New MCL DSL (#3738)

* Adding MCP implementation

* New tests for MCP implementation

* fix tests

* update docs

* Revert "New tests for MCP implementation"

This reverts commit 0bbe6dee90.

* linter

* linter

* fix

* verify mcp pacakge exists

* adjust docs to be clear only remote servers are supported

* reverted

* ensure args schema generated properly

* properly close out

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: a2a experimental

experimental a2a support

---------

Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
Co-authored-by: Mike Plachta <mplachta@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2025-10-20 14:10:19 -07:00

450 lines
22 KiB
YAML
Raw Blame History

interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1894'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 17 Nov 2024 07:09:57 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are LLMs Senior Data Researcher\n.
You''re a seasoned researcher with a knack for uncovering the latest developments
in LLMs. Known for your ability to find the most relevant information and present
it in a clear and concise manner.\n\nYour personal goal is: Uncover cutting-edge
developments in LLMs\n\nTo give my best complete final answer to the task use
the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!"}, {"role": "user", "content": "\nCurrent Task: Conduct a thorough research
about LLMs Make sure you find any interesting and relevant information given
the current year is 2024.\n\n\nThis is the expect criteria for your final answer:
A list with 10 bullet points of the most relevant information about LLMs\n\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1235'
content-type:
- application/json
cookie:
- __cf_bm=08pKRcLhS1PDw0mYfL2jz19ac6M.T31GoiMuI5DlX6w-1731827382-1.0.1.1-UfOLu3AaIUuXP1sGzdV6oggJ1q7iMTC46t08FDhYVrKcW5YmD4CbifudOJiSgx8h0JLTwZdgk.aG05S0eAO_PQ;
_cfuvid=74kaPOoAcp8YRSA0XocQ1FFNksu9V0_KiWdQfo7wQuQ-1731827382509-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e3de5de7b6c6217-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 17 Nov 2024 07:10:00 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '6026'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999713'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_553f04a622d026a28dd3c5da55568fcd
status:
code: 200
message: OK
- request:
body: !!binary |
Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
bGVtZXRyeRKOAgoQIn+FuHJydyMnR3y/Qfb8GBII2zXFs4gynEgqDFRhc2sgQ3JlYXRlZDABOShs
9ljYrwgYQQiP+FjYrwgYSi4KCGNyZXdfa2V5EiIKIGYzNDZhOWFkNmQ3MzA2M2UwNjc3YjE3Y2U5
YzUwMTc3SjEKB2NyZXdfaWQSJgokNzY0Y2VjNWEtODc5MS00ZjdjLTlmNDAtYTUzMzMyZjk5N2Mw
Si4KCHRhc2tfa2V5EiIKIGIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3SjEKB3Rhc2tf
aWQSJgokMDBiZmQ2OWQtNzlmYi00YzI3LWEzNGItNjcwZGViZTM1NDVmegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '337'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 17 Nov 2024 07:10:01 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are LLMs Reporting Analyst\n.
You''re a meticulous analyst with a keen eye for detail. You''re known for your
ability to turn complex data into clear and concise reports, making it easy
for others to understand and act on the information you provide.\nYour personal
goal is: Create detailed reports based on LLMs data analysis and research findings\n\nTo
give my best complete final answer to the task use the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
Task: Review the context you got and expand each topic into a full section for
a report. Make sure the report is detailed and contains any and all relevant
information.\n\n\nThis is the expect criteria for your final answer: A fully
fledge reports with the mains topics, each with a full section of information.
Formatted as markdown without ''```''\n\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nThis is the context you''re working
with:\n1. **OpenAI''s GPT-4 Released**: OpenAI released GPT-4, which further
improves contextual understanding and generation capabilities. It offers increased
accuracy, creativity, and coherence in responses compared to its predecessors,
making it an essential tool for businesses, educators, and developers.\n\n2.
**Google''s Gemini Model**: In 2024, Google launched the Gemini model, focusing
on merging language understanding with multimodal capabilities. This model can
process text, audio, and images simultaneously, enhancing its applications in
fields like voice assistants and image captioning.\n\n3. **Anthropic''s Claude**:
Claude, by Anthropic, is designed to prioritize safety and ethical considerations
in LLM usage. It''s built to minimize harmful outputs and biases prevalent in
earlier language models, demonstrating a shift towards responsible AI deployment.\n\n4.
**Meta''s Open Pre-trained Transformer (OPT) 3.0**: Meta has introduced OPT
3.0, boasting efficient training approaches that lower computational costs while
maintaining high performance. The model excels in translation tasks and has
become a popular choice for academic research due to its open-access policy.\n\n5.
**Language Model Distillation Advances**: Recent advances in model distillation
techniques have allowed developers to deploy smaller, more efficient language
models on edge devices without notably compromising performance, expanding the
accessibility and application of LLMs in mobile and IoT devices.\n\n6. **Fine-Tuning
with Limited Data**: Methods for fine-tuning LLMs with limited data have improved,
enabling customization for niche applications without the need for vast datasets.
This development has opened doors to using LLMs in specialized industries, like
legal and medical sectors.\n\n7. **Ethical and Transparent AI Use**: 2024 has
seen a significant emphasis on ethical AI, with organizations establishing standardized
frameworks for LLM transparency and accountability. More companies are adopting
practices like AI model cards to disclose model capabilities, limitations, and
data sources.\n\n8. **The Rise of Prompt Engineering**: As models become more
advanced, prompt engineering has emerged as a crucial technique for optimizing
model outputs. This involves designing specific input prompts that guide LLMs
to yield desired results, thus enhancing usability in content creation and customer
service.\n\n9. **Integration with Augmented Reality**: Language models in 2024
are increasingly being integrated with AR technologies to provide real-time
language translation, virtual assistants in immersive environments, and interactive
educational tools, enriching the user''s experience with contextualized AI assistance.\n\n10.
**Regulatory Developments**: Governments worldwide are progressing towards formalizing
regulations around LLM usage, focusing on data privacy, security, and ethical
concerns. These developments aim to safeguard users while encouraging innovation
in AI technology.\n\nThese points reflect the cutting-edge advancements and
trends in the field of large language models (LLMs) as of 2024, highlighting
their growing influence and the increasing focus on ethical and practical deployment.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4624'
content-type:
- application/json
cookie:
- __cf_bm=08pKRcLhS1PDw0mYfL2jz19ac6M.T31GoiMuI5DlX6w-1731827382-1.0.1.1-UfOLu3AaIUuXP1sGzdV6oggJ1q7iMTC46t08FDhYVrKcW5YmD4CbifudOJiSgx8h0JLTwZdgk.aG05S0eAO_PQ;
_cfuvid=74kaPOoAcp8YRSA0XocQ1FFNksu9V0_KiWdQfo7wQuQ-1731827382509-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e3de605dca06217-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 17 Nov 2024 07:10:10 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '9951'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998873'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_52a4f98f9c08fbaa1724634d237f3245
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink