internal crew

poetry.lock

@@ -836,13 +836,13 @@ cron = ["capturer (>=2.4)"]
 
 [[package]]
 name = "crewai-tools"
-version = "0.2.5"
+version = "0.2.6"
 description = "Set of tools for the crewAI framework"
 optional = false
 python-versions = "<=3.13,>=3.10"
 files = [
-    {file = "crewai_tools-0.2.5-py3-none-any.whl", hash = "sha256:3e36a3f6dc6be5b53308609f7383c3936d39e307987f59fb504931ef1b8ab5d9"},
-    {file = "crewai_tools-0.2.5.tar.gz", hash = "sha256:662d77d14bc1dfcd4d21adf503d5f38a6a88cebe6fcd75141a678070fb0a7e08"},
+    {file = "crewai_tools-0.2.6-py3-none-any.whl", hash = "sha256:b98ce2d40f545ee3c1bef6ba7ce07bfcecc0ebc8faf9db315016515bd709ab90"},
+    {file = "crewai_tools-0.2.6.tar.gz", hash = "sha256:f46d7c89aae927a4059297efc8f9d32d2200db225b9464c7d2a2134b4fc028d5"},
 ]
 
 [package.dependencies]
@@ -935,13 +935,13 @@ test = ["flake8", "isort", "pytest"]
 
 [[package]]
 name = "dataclasses-json"
-version = "0.6.5"
+version = "0.6.6"
 description = "Easily serialize dataclasses to and from JSON."
 optional = false
 python-versions = "<4.0,>=3.7"
 files = [
-    {file = "dataclasses_json-0.6.5-py3-none-any.whl", hash = "sha256:f49c77aa3a85cac5bf5b7f65f4790ca0d2be8ef4d92c75e91ba0103072788a39"},
-    {file = "dataclasses_json-0.6.5.tar.gz", hash = "sha256:1c287594d9fcea72dc42d6d3836cf14848c2dc5ce88f65ed61b36b57f515fe26"},
+    {file = "dataclasses_json-0.6.6-py3-none-any.whl", hash = "sha256:e54c5c87497741ad454070ba0ed411523d46beb5da102e221efb873801b0ba85"},
+    {file = "dataclasses_json-0.6.6.tar.gz", hash = "sha256:0c09827d26fffda27f1be2fed7a7a01a29c5ddcd2eb6393ad5ebf9d77e9deae8"},
 ]
 
 [package.dependencies]
@@ -1393,13 +1393,13 @@ requests = ["requests (>=2.20.0,<3.0.0.dev0)"]
 
 [[package]]
 name = "google-cloud-aiplatform"
-version = "1.50.0"
+version = "1.51.0"
 description = "Vertex AI API client library"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "google-cloud-aiplatform-1.50.0.tar.gz", hash = "sha256:f9f7cc76dbaad3905408fd07d6322caa6c4cd60a0330e4b15de66033c6598cc6"},
-    {file = "google_cloud_aiplatform-1.50.0-py2.py3-none-any.whl", hash = "sha256:6aa8246086252fe01d3438cd6566561147405a09611cf03f082be197c77b8197"},
+    {file = "google-cloud-aiplatform-1.51.0.tar.gz", hash = "sha256:901993b4d14392452699c14cf23d72c01c5488ee36a7e00b23195e64d7d2f5ec"},
+    {file = "google_cloud_aiplatform-1.51.0-py2.py3-none-any.whl", hash = "sha256:f2d3ff231454fe397f02fce1358680dea76ed7c74fc42e6c7e1aa1acb1648df3"},
 ]
 
 [package.dependencies]
@@ -1421,8 +1421,8 @@ cloud-profiler = ["tensorboard-plugin-profile (>=2.4.0,<3.0.0dev)", "tensorflow
 datasets = ["pyarrow (>=10.0.1)", "pyarrow (>=14.0.0)", "pyarrow (>=3.0.0,<8.0dev)"]
 endpoint = ["requests (>=2.28.1)"]
 full = ["cloudpickle (<3.0)", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.109.1)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-cloud-logging (<4.0)", "google-vizier (>=0.1.6)", "httpx (>=0.23.0,<0.25.0)", "immutabledict", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.1.1)", "nest-asyncio (>=1.0.0,<1.6.0)", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pandas (>=1.0.0,<2.2.0)", "pyarrow (>=10.0.1)", "pyarrow (>=14.0.0)", "pyarrow (>=3.0.0,<8.0dev)", "pyarrow (>=6.0.1)", "pydantic (<2)", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<=2.9.3)", "ray[default] (>=2.5,<=2.9.3)", "requests (>=2.28.1)", "starlette (>=0.17.1)", "tensorflow (>=2.3.0,<3.0.0dev)", "tensorflow (>=2.3.0,<3.0.0dev)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)"]
-langchain = ["langchain (>=0.1.13,<0.2)", "langchain-core (<0.2)", "langchain-google-vertexai (<0.2)"]
-langchain-testing = ["absl-py", "cloudpickle (>=2.2.1,<3.0)", "langchain (>=0.1.13,<0.2)", "langchain-core (<0.2)", "langchain-google-vertexai (<0.2)", "pydantic (>=2.6.3,<3)", "pytest-xdist"]
+langchain = ["langchain (>=0.1.16,<0.2)", "langchain-core (<0.2)", "langchain-google-vertexai (<2)"]
+langchain-testing = ["absl-py", "cloudpickle (>=2.2.1,<3.0)", "langchain (>=0.1.16,<0.2)", "langchain-core (<0.2)", "langchain-google-vertexai (<2)", "pydantic (>=2.6.3,<3)", "pytest-xdist"]
 lit = ["explainable-ai-sdk (>=1.0.0)", "lit-nlp (==0.4.0)", "pandas (>=1.0.0)", "tensorflow (>=2.3.0,<3.0.0dev)"]
 metadata = ["numpy (>=1.15.0)", "pandas (>=1.0.0)"]
 pipelines = ["pyyaml (>=5.3.1,<7)"]
@@ -1732,13 +1732,13 @@ test = ["objgraph", "psutil"]
 
 [[package]]
 name = "griffe"
-version = "0.44.0"
+version = "0.45.0"
 description = "Signatures for entire Python programs. Extract the structure, the frame, the skeleton of your project, to generate API documentation or find breaking changes in your API."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "griffe-0.44.0-py3-none-any.whl", hash = "sha256:8a4471c469ba980b87c843f1168850ce39d0c1d0c7be140dca2480f76c8e5446"},
-    {file = "griffe-0.44.0.tar.gz", hash = "sha256:34aee1571042f9bf00529bc715de4516fb6f482b164e90d030300601009e0223"},
+    {file = "griffe-0.45.0-py3-none-any.whl", hash = "sha256:90fe5c90e1b0ca7dd6fee78f9009f4e01b37dbc9ab484a9b2c1578915db1e571"},
+    {file = "griffe-0.45.0.tar.gz", hash = "sha256:85cb2868d026ea51c89bdd589ad3ccc94abc5bd8d5d948e3d4450778a2a05b4a"},
 ]
 
 [package.dependencies]
@@ -2193,13 +2193,13 @@ tests = ["aiohttp", "duckdb", "pandas (>=1.4)", "polars (>=0.19)", "pytest", "py
 
 [[package]]
 name = "langchain"
-version = "0.1.19"
+version = "0.1.20"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain-0.1.19-py3-none-any.whl", hash = "sha256:a1270b70139344a09f91c8a1b117c4300d9920d6d88aaaaf5ba729625ac68801"},
-    {file = "langchain-0.1.19.tar.gz", hash = "sha256:7d2ffb66944a84dcac99901c4fd33f6d92aa7f794d17b5ba9a29c55a7306e32c"},
+    {file = "langchain-0.1.20-py3-none-any.whl", hash = "sha256:09991999fbd6c3421a12db3c7d1f52d55601fc41d9b2a3ef51aab2e0e9c38da9"},
+    {file = "langchain-0.1.20.tar.gz", hash = "sha256:f35c95eed8c8375e02dce95a34f2fd4856a4c98269d6dc34547a23dba5beab7e"},
 ]
 
 [package.dependencies]
@@ -2315,13 +2315,13 @@ extended-testing = ["lxml (>=5.1.0,<6.0.0)"]
 
 [[package]]
 name = "langsmith"
-version = "0.1.56"
+version = "0.1.57"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langsmith-0.1.56-py3-none-any.whl", hash = "sha256:2f930e054ea8eccd8ff99f0f129ae7d2513973b2e706d5483f44ea9951a1dca0"},
-    {file = "langsmith-0.1.56.tar.gz", hash = "sha256:ff645b5bf16e2566740218ed6c048a1f8edbbedb4480a0d305a837ec71303fbf"},
+    {file = "langsmith-0.1.57-py3-none-any.whl", hash = "sha256:dbd83b0944a2fbea4151f0aa053530d93fcf6784a580621bc60633cb890b57dc"},
+    {file = "langsmith-0.1.57.tar.gz", hash = "sha256:4682204de19f0218029c2b8445ce2cc3485c8d0df9796b31e2ce4c9051fce365"},
 ]
 
 [package.dependencies]
@@ -2561,13 +2561,13 @@ pyyaml = ">=5.1"
 
 [[package]]
 name = "mkdocs-material"
-version = "9.5.21"
+version = "9.5.22"
 description = "Documentation that simply works"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "mkdocs_material-9.5.21-py3-none-any.whl", hash = "sha256:210e1f179682cd4be17d5c641b2f4559574b9dea2f589c3f0e7c17c5bd1959bc"},
-    {file = "mkdocs_material-9.5.21.tar.gz", hash = "sha256:049f82770f40559d3c2aa2259c562ea7257dbb4aaa9624323b5ef27b2d95a450"},
+    {file = "mkdocs_material-9.5.22-py3-none-any.whl", hash = "sha256:8c7a377d323567934e6cd46915e64dc209efceaec0dec1cf2202184f5649862c"},
+    {file = "mkdocs_material-9.5.22.tar.gz", hash = "sha256:22a853a456ae8c581c4628159574d6fc7c71b2c7569dc9c3a82cc70432219599"},
 ]
 
 [package.dependencies]
@@ -2870,6 +2870,53 @@ files = [
     {file = "mutagen-1.47.0.tar.gz", hash = "sha256:719fadef0a978c31b4cf3c956261b3c58b6948b32023078a2117b1de09f0fc99"},
 ]
 
+[[package]]
+name = "mypy"
+version = "1.10.0"
+description = "Optional static typing for Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "mypy-1.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:da1cbf08fb3b851ab3b9523a884c232774008267b1f83371ace57f412fe308c2"},
+    {file = "mypy-1.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:12b6bfc1b1a66095ab413160a6e520e1dc076a28f3e22f7fb25ba3b000b4ef99"},
+    {file = "mypy-1.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e36fb078cce9904c7989b9693e41cb9711e0600139ce3970c6ef814b6ebc2b2"},
+    {file = "mypy-1.10.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2b0695d605ddcd3eb2f736cd8b4e388288c21e7de85001e9f85df9187f2b50f9"},
+    {file = "mypy-1.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:cd777b780312ddb135bceb9bc8722a73ec95e042f911cc279e2ec3c667076051"},
+    {file = "mypy-1.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3be66771aa5c97602f382230165b856c231d1277c511c9a8dd058be4784472e1"},
+    {file = "mypy-1.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8b2cbaca148d0754a54d44121b5825ae71868c7592a53b7292eeb0f3fdae95ee"},
+    {file = "mypy-1.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ec404a7cbe9fc0e92cb0e67f55ce0c025014e26d33e54d9e506a0f2d07fe5de"},
+    {file = "mypy-1.10.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e22e1527dc3d4aa94311d246b59e47f6455b8729f4968765ac1eacf9a4760bc7"},
+    {file = "mypy-1.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:a87dbfa85971e8d59c9cc1fcf534efe664d8949e4c0b6b44e8ca548e746a8d53"},
+    {file = "mypy-1.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a781f6ad4bab20eef8b65174a57e5203f4be627b46291f4589879bf4e257b97b"},
+    {file = "mypy-1.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b808e12113505b97d9023b0b5e0c0705a90571c6feefc6f215c1df9381256e30"},
+    {file = "mypy-1.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f55583b12156c399dce2df7d16f8a5095291354f1e839c252ec6c0611e86e2e"},
+    {file = "mypy-1.10.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4cf18f9d0efa1b16478c4c129eabec36148032575391095f73cae2e722fcf9d5"},
+    {file = "mypy-1.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:bc6ac273b23c6b82da3bb25f4136c4fd42665f17f2cd850771cb600bdd2ebeda"},
+    {file = "mypy-1.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9fd50226364cd2737351c79807775136b0abe084433b55b2e29181a4c3c878c0"},
+    {file = "mypy-1.10.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:f90cff89eea89273727d8783fef5d4a934be2fdca11b47def50cf5d311aff727"},
+    {file = "mypy-1.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fcfc70599efde5c67862a07a1aaf50e55bce629ace26bb19dc17cece5dd31ca4"},
+    {file = "mypy-1.10.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:075cbf81f3e134eadaf247de187bd604748171d6b79736fa9b6c9685b4083061"},
+    {file = "mypy-1.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:3f298531bca95ff615b6e9f2fc0333aae27fa48052903a0ac90215021cdcfa4f"},
+    {file = "mypy-1.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fa7ef5244615a2523b56c034becde4e9e3f9b034854c93639adb667ec9ec2976"},
+    {file = "mypy-1.10.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3236a4c8f535a0631f85f5fcdffba71c7feeef76a6002fcba7c1a8e57c8be1ec"},
+    {file = "mypy-1.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4a2b5cdbb5dd35aa08ea9114436e0d79aceb2f38e32c21684dcf8e24e1e92821"},
+    {file = "mypy-1.10.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:92f93b21c0fe73dc00abf91022234c79d793318b8a96faac147cd579c1671746"},
+    {file = "mypy-1.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:28d0e038361b45f099cc086d9dd99c15ff14d0188f44ac883010e172ce86c38a"},
+    {file = "mypy-1.10.0-py3-none-any.whl", hash = "sha256:f8c083976eb530019175aabadb60921e73b4f45736760826aa1689dda8208aee"},
+    {file = "mypy-1.10.0.tar.gz", hash = "sha256:3d087fcbec056c4ee34974da493a826ce316947485cef3901f511848e687c131"},
+]
+
+[package.dependencies]
+mypy-extensions = ">=1.0.0"
+tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
+typing-extensions = ">=4.1.0"
+
+[package.extras]
+dmypy = ["psutil (>=4.0)"]
+install-types = ["pip"]
+mypyc = ["setuptools (>=50)"]
+reports = ["lxml"]
+
 [[package]]
 name = "mypy-extensions"
 version = "1.0.0"
@@ -3000,13 +3047,13 @@ sympy = "*"
 
 [[package]]
 name = "openai"
-version = "1.28.0"
+version = "1.29.0"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.28.0-py3-none-any.whl", hash = "sha256:94b5a99f5121e1747dda1bb8fff31820d5ab4b49056a9cf2e3605f5c90011955"},
-    {file = "openai-1.28.0.tar.gz", hash = "sha256:ac43b8b48aec70de4b76cfc96ae906bf8d5814427475b9dabb662f84f655f0e1"},
+    {file = "openai-1.29.0-py3-none-any.whl", hash = "sha256:c61cd12376c84362d406341f9e2f9a9d6b81c082b133b44484dc0f43954496b1"},
+    {file = "openai-1.29.0.tar.gz", hash = "sha256:d5a769f485610cff8bae14343fa45a8b1d346be3d541fa5b28ccd040dbc8baf8"},
 ]
 
 [package.dependencies]
@@ -3457,13 +3504,13 @@ test = ["coverage", "flake8", "freezegun (==0.3.15)", "mock (>=2.0.0)", "pylint"
 
 [[package]]
 name = "pre-commit"
-version = "3.7.0"
+version = "3.7.1"
 description = "A framework for managing and maintaining multi-language pre-commit hooks."
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "pre_commit-3.7.0-py2.py3-none-any.whl", hash = "sha256:5eae9e10c2b5ac51577c3452ec0a490455c45a0533f7960f993a0d01e59decab"},
-    {file = "pre_commit-3.7.0.tar.gz", hash = "sha256:e209d61b8acdcf742404408531f0c37d49d2c734fd7cff2d6076083d191cb060"},
+    {file = "pre_commit-3.7.1-py2.py3-none-any.whl", hash = "sha256:fae36fd1d7ad7d6a5a1c0b0d5adb2ed1a3bda5a21bf6c3e5372073d7a11cd4c5"},
+    {file = "pre_commit-3.7.1.tar.gz", hash = "sha256:8ca3ad567bc78a4972a3f1a477e94a79d4597e8140a6e0b651c5e33899c3654a"},
 ]
 
 [package.dependencies]
@@ -4124,7 +4171,6 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
@@ -5087,13 +5133,13 @@ tests = ["Werkzeug (==2.0.3)", "aiohttp", "boto3", "httplib2", "httpx", "pytest"
 
 [[package]]
 name = "virtualenv"
-version = "20.26.1"
+version = "20.26.2"
 description = "Virtual Python Environment builder"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "virtualenv-20.26.1-py3-none-any.whl", hash = "sha256:7aa9982a728ae5892558bff6a2839c00b9ed145523ece2274fad6f414690ae75"},
-    {file = "virtualenv-20.26.1.tar.gz", hash = "sha256:604bfdceaeece392802e6ae48e69cec49168b9c5f4a44e483963f9242eb0e78b"},
+    {file = "virtualenv-20.26.2-py3-none-any.whl", hash = "sha256:a624db5e94f01ad993d476b9ee5346fdf7b9de43ccaee0e0197012dc838a0e9b"},
+    {file = "virtualenv-20.26.2.tar.gz", hash = "sha256:82bf0f4eebbb78d36ddaee0283d43fe5736b53880b8a8cdcd37390a07ac3741c"},
 ]
 
 [package.dependencies]
@@ -5593,4 +5639,4 @@ tools = ["crewai-tools"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<=3.13"
-content-hash = "77320f84572c4fcfed132f224ddd6cf865742e1fb6d3c5d14b12f0ac63ec10be"
+content-hash = "40ec094c69ad35760fe38820394f52af8d393e4566e3ac3ee14f013be9a5bb9f"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.30.4"
+version = "0.30.10"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -21,7 +21,7 @@ opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "^0.5.2"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.2.5", optional = true }
+crewai-tools = { version = "^0.2.6", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
 embedchain = "^0.1.98"
@@ -42,7 +42,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.2.5"
+crewai-tools = "^0.2.6"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = {extras = ["tools"], version = "^0.28.8"}
+crewai = {extras = ["tools"], version = "^0.30.9"}
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/crew.py

@@ -1,7 +1,9 @@
+import os
 import json
 import uuid
 from typing import Any, Dict, List, Optional, Union
 
+from langchain_openai import ChatOpenAI
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
     UUID4,
@@ -27,7 +29,6 @@ from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools import AgentTools
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
 
-
 class Crew(BaseModel):
     """
     Represents a group of agents, defining how they should collaborate and the tasks they should perform.
@@ -101,6 +102,15 @@ class Crew(BaseModel):
     config: Optional[Union[Json, Dict[str, Any]]] = Field(default=None)
     id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
     share_crew: Optional[bool] = Field(default=False)
+    autonomous_llm: Optional[Any] = Field(
+        default_factory=lambda: ChatOpenAI(
+            model=os.environ.get("OPENAI_MODEL_NAME", "gpt-4")
+        ),
+        description="Language model that will used for agents dinamycally created.",
+    )
+    autonomous_tools: Optional[List[Any]] = Field(
+        default_factory=list, description="Tools at agents disposal when dinamically generated."
+    )
     step_callback: Optional[Any] = Field(
         default=None,
         description="Callback to be executed after each step for all agents execution.",
@@ -164,8 +174,8 @@ class Crew(BaseModel):
         """Set private attributes."""
         if self.memory:
             self._long_term_memory = LongTermMemory()
-            self._short_term_memory = ShortTermMemory(embedder_config=self.embedder)
-            self._entity_memory = EntityMemory(embedder_config=self.embedder)
+            self._short_term_memory = ShortTermMemory(crew=self, embedder_config=self.embedder)
+            self._entity_memory = EntityMemory(crew=self, embedder_config=self.embedder)
         return self
 
     @model_validator(mode="after")
@@ -266,6 +276,10 @@ class Crew(BaseModel):
             result, manager_metrics = self._run_hierarchical_process()  # type: ignore # Unpacking a string is disallowed
             metrics.append(manager_metrics)  # type: ignore # Cannot determine type of "manager_metrics"
 
+            result, manager_metrics = self._run_hierarchical_process()
+            metrics.append(manager_metrics)
+        elif self.process == Process.autonomous:
+            result = self._run_autonomous_process()
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
@@ -315,6 +329,61 @@ class Crew(BaseModel):
         self._finish_execution(task_output)
         return self._format_output(task_output)
 
+    def _run_autonomous_process(self) -> str:
+        """Executes high level tasks by automatically creating agents and tasks for achieving an initial task"""
+        from crewai.internal.crew.planning_crew.crew import PlanningCrewCrew
+        #task_output = ""
+        # Need to decide how to break the initial task into smaller tasks
+        # Need to decide on what agents to create to fullfill the tasks
+        # Need to decide what process to use, whether sequential or hierarchical
+        # Need to decide on what tools to use for the agents
+
+        import pkgutil
+        import inspect
+        import crewai_tools
+
+        def list_crewai_tools():
+            tool_list = []
+            for importer, modname, ispkg in pkgutil.iter_modules(crewai_tools.__path__):
+                module = importer.find_module(modname).load_module(modname)
+                for name, obj in inspect.getmembers(module, inspect.isclass):
+                    if obj.__module__ == module.__name__:
+                        tool_list.append(name)
+            return tool_list
+
+        # Get the list of tools
+        tools = list_crewai_tools()
+
+        descriptions = []
+        for tool in tools:
+            args = {
+                k: {k2: v2 for k2, v2 in v.items() if k2 in ["description", "type"]}
+                for k, v in tool.args.items()
+            }
+            descriptions.append(
+                "\n".join(
+                    [
+                        f"Tool Name: {tool.name.lower()}",
+                        f"Tool Description: {tool.description}",
+                        f"Tool Arguments: {args}",
+                    ]
+                )
+            )
+        descriptions =  "\n--\n".join(descriptions)
+        print(descriptions)
+
+        crew = PlanningCrewCrew().crew()
+
+        for task in self.tasks:
+            crew.kickoff({
+                "task": task.description,
+                "goal": task.expected_output,
+                "tools_list": descriptions
+            })
+
+
+
+
     def _run_hierarchical_process(self) -> str:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
 
@@ -364,6 +433,7 @@ class Crew(BaseModel):
         for task in self.tasks:
             if not task.callback:
                 task.callback = self.task_callback
+            task.callback = self.task_callback
 
     def _interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
         """Interpolates the inputs in the tasks and agents."""

src/crewai/internal/agents/hierarchical_manager.py

@@ -0,0 +1,15 @@
+from crewai.agent import Agent
+from crewai.tools.agent_tools import AgentTools
+from crewai.utilities import I18N
+
+class HierarchicalManagerAgent:
+	def __init__(self, llm, agents, verbose):
+		i18n = I18N()
+		self.agent = Agent(
+									role=i18n.retrieve("hierarchical_manager_agent", "role"),
+									goal=i18n.retrieve("hierarchical_manager_agent", "goal"),
+									backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
+									tools=AgentTools(agents=agents).tools(),
+									llm=llm,
+									verbose=verbose,
+								)

src/crewai/internal/agents/planning_manager.py

@@ -0,0 +1,12 @@
+from crewai.agent import Agent
+from crewai.utilities import i18n
+
+class PlanningManagerAgent:
+	def __init__(self, llm, verbose):
+		self.agent = Agent(
+									role=i18n.retrieve("planning_manager_agent", "role"),
+									goal=i18n.retrieve("planning_manager_agent", "goal"),
+									backstory=i18n.retrieve("planning_manager_agent", "backstory"),
+									verbose=verbose,
+									llm=llm,
+								)

src/crewai/internal/crew/planning_crew/config/agents.yaml

@@ -0,0 +1,21 @@
+project_manager:
+  role: >
+    High-Level Task Decomposer
+  goal: >
+    Efficiently break down high-level tasks into actionable subtasks.
+  backstory: >
+    As a visionary leader and strategist, you excel at dissecting complex
+    projects into manageable parts. Your expertise lies in identifying key
+    components and stages of a project, ensuring that each piece is addressed
+    with precision and aligned with overarching objectives.
+
+resource_manager:
+  role: >
+    Resource Allocation Specialist
+  goal: >
+    Assign the right resources (agents and tools) to the generated subtasks.
+  backstory: >
+    With a strategic mind and a masterful grasp of logistics, you specialize
+    in allocating the best-suited agents and tools for specific tasks. Your
+    ability to match project needs with available resources ensures optimal
+    efficiency and effectiveness in project execution.

src/crewai/internal/crew/planning_crew/config/tasks.yaml

@@ -0,0 +1,36 @@
+task_decomposition:
+  description: >
+    Analyze the high-level task, "{task}", provided and break it down into
+    distinct, manageable subtasks that are specific and actionable.
+    Consider all aspects of the task and ensure that each subtask is
+    aligned with the final goal. Additionally, outline the roles, goals,
+    and backstories for the agents you plan to recruit for performing
+    each subtask. Make sure to clearly define their responsibilities in
+    the context of this project.
+  expected_output: >
+    A detailed list of subtasks, each with defined objectives and
+    scopes, ensuring they collectively address all components of the
+    original task, "{task}". Each subtask should be assigned to a
+    specific agent you will recruit, complete with their role, goal, and
+    backstory. The main goal is to ensure systematic progression and
+    effective task management.
+
+resource_allocation:
+  description: >
+    Evaluate the list of subtasks generated from the high-level task
+    "{task}" and determine the most appropriate agents and tools needed
+    for each. Assign resources based on the complexity, required skills,
+    and the tools needed to effectively complete each subtask. This
+    evaluation should consider the unique requirements of each subtask
+    and align resources to optimize task completion. Available tools to
+    choose from include:
+    {tools_list}.
+  expected_output: >
+    An allocation plan that lists each subtask along with the assigned
+    agent and the tools they will use, explaining the rationale for each
+    resource assignment to ensure transparency and optimal task
+    alignment. The expected outcome is to have a fully resourced plan
+    that facilitates efficient task execution and achievement of the
+    main goal: "{goal}".
+    Ensure each tool selected is from the provided list of available tools:
+    {tools_list}.

src/crewai/internal/crew/planning_crew/crew.py

@@ -0,0 +1,51 @@
+from .... import Agent, Crew, Process, Task
+from ....project import CrewBase, agent, crew, task
+
+from .crew_config import CrewConfig
+
+@CrewBase
+class PlanningCrewCrew():
+  """PlanningCrew crew"""
+  agents_config = '../internal/crew/planning_crew/config/agents.yaml'
+  tasks_config = '../internal/crew/planning_crew/config/tasks.yaml'
+
+  @agent
+  def project_manager(self) -> Agent:
+    return Agent(
+      config=self.agents_config['project_manager'],
+      allow_delegation=False,
+      verbose=True
+    )
+
+  @agent
+  def resource_manager(self) -> Agent:
+    return Agent(
+      config=self.agents_config['resource_manager'],
+      allow_delegation=False,
+      verbose=True
+    )
+
+  @task
+  def task_decomposition(self) -> Task:
+    return Task(
+      config=self.tasks_config['task_decomposition'],
+      agent=self.project_manager(),
+      output_pydantic=CrewConfig
+    )
+
+  @task
+  def resource_allocation(self) -> Task:
+    return Task(
+      config=self.tasks_config['resource_allocation'],
+      agent=self.resource_manager(),
+      output_pydantic=CrewConfig
+    )
+
+  @crew
+  def crew(self) -> Crew:
+    """Creates the PlanningCrew crew"""
+    return Crew(
+      agents=[self.project_manager(), self.resource_manager()],
+      tasks=[self.task_decomposition(), self.resource_allocation()],
+      process=Process.sequential
+    )

src/crewai/internal/crew/planning_crew/crew_config.py

@@ -0,0 +1,17 @@
+from typing import List
+from pydantic import BaseModel, Field
+
+
+class AgentConfig(BaseModel):
+	role: str = Field(..., description="The role of the agent")
+	goal: str = Field(..., description="The goal of the agent")
+	backstory: str = Field(..., description="The backstory of the agent")
+	tools: List[str] = Field(..., description="The tools used by the agent")
+
+class TaskConfig(BaseModel):
+	description: str = Field(..., description="The description of the task")
+	expected_output: str = Field(..., description="The expected output of the task")
+	agent: AgentConfig = Field(..., description="The agent responsible for the task")
+
+class CrewConfig(BaseModel):
+	tasks: List[TaskConfig] = Field(..., description="The tasks to be performed by the crew")

src/crewai/memory/entity/entity_memory.py

@@ -10,9 +10,9 @@ class EntityMemory(Memory):
     Inherits from the Memory class.
     """
 
-    def __init__(self, embedder_config=None):
+    def __init__(self, crew=None, embedder_config=None):
         storage = RAGStorage(
-            type="entities", allow_reset=False, embedder_config=embedder_config
+            type="entities", allow_reset=False, embedder_config=embedder_config, crew=crew
         )
         super().__init__(storage)
 

src/crewai/memory/short_term/short_term_memory.py

@@ -12,8 +12,8 @@ class ShortTermMemory(Memory):
     MemoryItem instances.
     """
 
-    def __init__(self, embedder_config=None):
-        storage = RAGStorage(type="short_term", embedder_config=embedder_config)
+    def __init__(self, crew=None, embedder_config=None):
+        storage = RAGStorage(type="short_term", embedder_config=embedder_config, crew=crew)
         super().__init__(storage)
 
     def save(self, item: ShortTermMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"

src/crewai/memory/storage/rag_storage.py

@@ -37,13 +37,18 @@ class RAGStorage(Storage):
     search efficiency.
     """
 
-    def __init__(self, type, allow_reset=True, embedder_config=None):
+    def __init__(self, type, allow_reset=True, embedder_config=None, crew=None):
         super().__init__()
         if (
             not os.getenv("OPENAI_API_KEY")
             and not os.getenv("OPENAI_BASE_URL") == "https://api.openai.com/v1"
         ):
             os.environ["OPENAI_API_KEY"] = "fake"
+
+        agents = crew.agents if crew else []
+        agents = [agent.role for agent in agents]
+        agents = "_".join(agents)
+
         config = {
             "app": {
                 "config": {"name": type, "collect_metrics": False, "log_level": "ERROR"}
@@ -58,7 +63,7 @@ class RAGStorage(Storage):
                 "provider": "chroma",
                 "config": {
                     "collection_name": type,
-                    "dir": f"{db_storage_path()}/{type}",
+                    "dir": f"{db_storage_path()}/{type}/{agents}",
                     "allow_reset": allow_reset,
                 },
             },

src/crewai/process.py

@@ -6,6 +6,7 @@ class Process(str, Enum):
     Class representing the different processes that can be used to tackle tasks
     """
 
+    autonomous = "autonomous"
     sequential = "sequential"
     hierarchical = "hierarchical"
     # TODO: consensual = 'consensual'

src/crewai/project/crew_base.py

@@ -1,18 +1,21 @@
 import inspect
-import os
-from pathlib import Path
-
 import yaml
+import os
+
+from pathlib import Path
+from pydantic import ConfigDict
+
 from dotenv import load_dotenv
-
-from crewai.utilities.parser import YamlParser
-
 load_dotenv()
 
 
 def CrewBase(cls):
     class WrappedClass(cls):
-        is_crew_class = True
+        model_config = ConfigDict(arbitrary_types_allowed=True)
+        is_crew_class: bool = True
+
+        class Config:
+            arbitrary_types_allowed = True
 
         base_directory = None
         for frame_info in inspect.stack():
@@ -42,7 +45,7 @@ def CrewBase(cls):
         @staticmethod
         def load_yaml(config_path: str):
             with open(config_path, "r") as file:
-                parsedContent = YamlParser.parse(file)  # type: ignore # Argument 1 to "parse" has incompatible type "TextIOWrapper"; expected "YamlParser"
-                return yaml.safe_load(parsedContent)
+                # parsedContent = YamlParser.parse(file)  # type: ignore # Argument 1 to "parse" has incompatible type "TextIOWrapper"; expected "YamlParser"
+                return yaml.safe_load(file)
 
     return WrappedClass

src/crewai/tools/agent_tools.py

@@ -35,12 +35,18 @@ class AgentTools(BaseModel):
 
     def delegate_work(self, task: str, context: str, coworker: Union[str, None] = None, **kwargs):
         """Useful to delegate a specific task to a co-worker passing all necessary context and names."""
-        coworker = coworker or kwargs.get("co_worker")
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("co-worker")
+        is_list = coworker.startswith("[") and coworker.endswith("]")
+        if is_list:
+            coworker = coworker[1:-1].split(",")[0]
         return self._execute(coworker, task, context)
 
     def ask_question(self, question: str, context: str, coworker: Union[str, None] = None, **kwargs):
         """Useful to ask a question, opinion or take from a co-worker passing all necessary context and names."""
-        coworker = coworker or kwargs.get("co_worker")
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("co-worker")
+        is_list = coworker.startswith("[") and coworker.endswith("]")
+        if is_list:
+            coworker = coworker[1:-1].split(",")[0]
         return self._execute(coworker, question, context)
 
     def _execute(self, agent, task, context):

src/crewai/translations/en.json

@@ -4,6 +4,11 @@
     "goal": "Manage the team to complete the task in the best way possible.",
     "backstory": "You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don't perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members."
   },
+  "planning_manager_agent": {
+    "role": "Crew Creator",
+    "goal": "Do the best most granular break down of a final goal into tasks and agents to complete them.",
+    "backstory": "You are a very seasoned manager very capable of breaking goals into smaller tasks and recruiting the right people to complete them.\n You are also great at set expectation for the team you recruit and provide them with the best tools for their work."
+  },
   "slices": {
     "observation": "\nObservation",
     "task": "\nCurrent Task: {input}\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:",

tests/agent_tools/agent_tools_test.py

@@ -68,6 +68,33 @@ def test_ask_question_with_wrong_co_worker_variable():
         == "No, I don't hate AI agents. In fact, I find them quite fascinating. They are powerful tools that can greatly assist in various tasks, including my research. As a technology researcher, AI and AI agents are subjects of interest to me due to their potential in advancing our understanding and capabilities in various fields. My supposed love for them stems from this professional interest and the potential they hold."
     )
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_delegate_work_withwith_coworker_as_array():
+    result = tools.delegate_work(
+        co_worker="[researcher]",
+        task="share your take on AI Agents",
+        context="I heard you hate them",
+    )
+
+    assert (
+        result
+        == "AI Agents are software entities which operate in an environment to achieve a particular goal. They can perceive their environment, reason about it, and take actions to fulfill their objectives. This includes everything from chatbots to self-driving cars. They are designed to act autonomously to a certain extent and are capable of learning from their experiences to improve their performance over time.\n\nDespite some people's fears or dislikes, AI Agents are not inherently good or bad. They are tools, and like any tool, their value depends on how they are used. For instance, AI Agents can be used to automate repetitive tasks, provide customer support, or analyze vast amounts of data far more quickly and accurately than a human could. They can also be used in ways that invade privacy or replace jobs, which is often where the apprehension comes from.\n\nThe key is to create regulations and ethical guidelines for the use of AI Agents, and to continue researching and developing them in a way that maximizes their benefits and minimizes their potential harm. From a research perspective, there's a lot of potential in AI Agents, and it's a fascinating field to be a part of."
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_ask_question_with_coworker_as_array():
+    result = tools.ask_question(
+        co_worker="[researcher]",
+        question="do you hate AI Agents?",
+        context="I heard you LOVE them",
+    )
+
+    assert (
+        result
+        == "I don't hate or love AI agents. My passion lies in understanding them, researching about their capabilities, implications, and potential for development. As a researcher, my feelings toward AI are more of fascination and interest rather than personal love or hate."
+    )
+
 
 def test_delegate_work_to_wrong_agent():
     result = tools.ask_question(

tests/agent_tools/cassettes/test_ask_question_with_coworker_as_array.yaml

@@ -0,0 +1,427 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are researcher. You''re
+      an expert researcher, specialized in technology\nYour personal goal is: make
+      the best research and analysis on content about AI and AI agentsTo 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: my best complete final answer to
+      the task.\nYour 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!\nCurrent Task: do you hate AI Agents?\n\nThis is the expect criteria for
+      your final answer: Your best answer to your co-worker asking you this, accounting
+      for the context shared. \n you MUST return the actual complete content as the
+      final answer, not a summary.\n\nThis is the context you''re working with:\nI
+      heard you LOVE them\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:\n"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '1103'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=r7d0l_hEOM639ffTY.owt.2ZeXQN7IgsM0JmFM6FEiE-1715576040584-0.0.1.1-604800000;
+        __cf_bm=bHXznnX6IEnPWC4UFqVw22jiTLBlLvClKsTW4F99UPc-1715613132-1.0.1.1-5k2TYkm6.lsjrA1MkQ4uD2GxUGKPmwNVeYL_sKTpAPJ_trVvN3.uNZS4HljKfVPlku1XDNCYfU4y43hlt3e.RQ
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.25.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.25.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"As"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        researcher"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        specialized"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        technology"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        specifically"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        my"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        personal"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        feelings"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        towards"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        them"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        not"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        based"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        on"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        emotion"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        but"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        on"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        professional"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        interest"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        intellectual"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        curiosity"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        \n\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        don"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''t"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        hate"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        love"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        My"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        passion"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        lies"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        understanding"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        them"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        researching"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        about"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        their"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        capabilities"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        implications"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        potential"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        for"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        development"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        As"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        researcher"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        my"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        feelings"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        toward"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        more"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        fascination"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        interest"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        rather"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        than"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        personal"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        love"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        or"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        hate"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ORdkG4FJphn6RbqXUgZlUbRtXBIO","object":"chat.completion.chunk","created":1715613148,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 883396429922624c-GRU
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 13 May 2024 15:12:29 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '514'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299745'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 50ms
+      x-request-id:
+      - req_5a62449ef9052c3a350f1b47f268bbcc
+    status:
+      code: 200
+      message: OK
+version: 1

tests/crew_test.py

@@ -960,36 +960,4 @@ def test_manager_agent_in_agents_raises_exception():
             process=Process.hierarchical,
             manager_agent=manager,
             tasks=[task],
-        )
-
-
-def test_manager_agent_with_tools_raises_exception():
-    from crewai_tools import tool
-
-    @tool
-    def testing_tool(first_number: int, second_number: int) -> int:
-        """Useful for when you need to multiply two numbers together."""
-        return first_number * second_number
-
-    task = Task(
-        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
-        expected_output="5 bullet points with a paragraph for each idea.",
-    )
-
-    manager = Agent(
-        role="Manager",
-        goal="Manage the crew and ensure the tasks are completed efficiently.",
-        backstory="You're an experienced manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
-        allow_delegation=False,
-        tools=[testing_tool],
-    )
-
-    crew = Crew(
-        agents=[researcher, writer],
-        process=Process.hierarchical,
-        manager_agent=manager,
-        tasks=[task],
-    )
-
-    with pytest.raises(Exception):
-        crew.kickoff()
+        )

tests/memory/short_term_memory_test.py

@@ -1,13 +1,32 @@
 import pytest
 
+from crewai.agent import Agent
+from crewai.crew import Crew
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
+from crewai.task import Task
 
 
 @pytest.fixture
 def short_term_memory():
     """Fixture to create a ShortTermMemory instance"""
-    return ShortTermMemory()
+    agent = Agent(
+        role="Researcher",
+        goal="Search relevant data and provide results",
+        backstory="You are a researcher at a leading tech think tank.",
+        tools=[],
+        verbose=True,
+    )
+
+    task = Task(
+        description="Perform a search on specific topics.",
+        expected_output="A list of relevant URLs based on the search query.",
+        agent=agent,
+    )
+    return ShortTermMemory(crew=Crew(
+        agents=[agent],
+        tasks=[task]
+    ))
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])