diff --git a/Doczy.AI_Automation/requirements.txt b/Doczy.AI_Automation/requirements.txt index 80c5789..afa8de5 100644 --- a/Doczy.AI_Automation/requirements.txt +++ b/Doczy.AI_Automation/requirements.txt @@ -1,8 +1,9 @@ -selenium~=4.23.1 -pytest~=8.3.1 -pandas~=2.2.2 -loguru~=0.7.2 -PyYAML~=6.0.1 -boto3~=1.34.148 -pysnowflake~=0.1.3 -botocore~=1.34.148 \ No newline at end of file +boto3==1.35.37 +botocore==1.35.37 +loguru==0.7.2 +pandas==2.2.3 +pytest==8.3.3 +PyYAML==5.4.1 +PyYAML==6.0.2 +selenium==4.25.0 +snowflake==0.13.0 diff --git a/airflow/requirements.txt b/airflow/requirements.txt new file mode 100644 index 0000000..997dc6d --- /dev/null +++ b/airflow/requirements.txt @@ -0,0 +1,3 @@ +apache-airflow==2.10.2 +boto3==1.35.37 +pandas==2.2.3 diff --git a/fieldExtraction/.gitignore b/fieldExtraction/.gitignore index d2bbe27..a1b7db3 100644 --- a/fieldExtraction/.gitignore +++ b/fieldExtraction/.gitignore @@ -65,7 +65,6 @@ texts/ *.json myenv/ *.env -*.txt subset/ output/ docs/ \ No newline at end of file diff --git a/fieldExtraction/requirements.txt b/fieldExtraction/requirements.txt new file mode 100644 index 0000000..d3898f3 --- /dev/null +++ b/fieldExtraction/requirements.txt @@ -0,0 +1,5 @@ +anthropic==0.36.0 +boto3==1.35.37 +botocore==1.35.37 +pandas==2.2.3 +Requests==2.32.3 diff --git a/requirements.txt b/requirements.txt index f229360..663bd1f 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1 +1 @@ -requests +requests \ No newline at end of file diff --git a/streamlit-server/requirements.txt b/streamlit-server/requirements.txt index 2f5239f..1c6e342 100644 --- a/streamlit-server/requirements.txt +++ b/streamlit-server/requirements.txt @@ -1,213 +1,213 @@ -aiohttp==3.9.5 -aiosignal==1.3.1 -altair==5.3.0 -anthropic==0.25.7 -anyio==4.3.0 -asn1crypto==1.5.1 -async-timeout==4.0.3 -atpublic==4.1.0 -attrs==21.2.0 -Automat==20.2.0 -awscli==1.32.99 -Babel==2.8.0 -backoff==2.2.1 -bcrypt==3.2.0 -beautifulsoup4==4.12.3 -blinker==1.4 -boto3==1.34.99 -botocore==1.34.99 -cachetools==5.3.3 -certifi==2020.6.20 -cffi==1.16.0 -chardet==4.0.0 -charset-normalizer==3.3.2 -chroma-hnswlib==0.7.2 -chromadb==0.4.6 -click==8.0.3 -cloud-init==23.4.4 -cloudpickle==2.2.1 -colorama==0.4.4 -coloredlogs==15.0.1 -command-not-found==0.3 -configobj==5.0.6 -constantly==15.1.0 -contourpy==1.2.1 -cryptography==42.0.7 -cycler==0.12.1 -dataclasses-json==0.5.14 -dbus-python==1.2.18 -distro==1.7.0 -distro-info==1.1+ubuntu0.2 -docutils==0.16 -docx2txt==0.8 -ec2-hibinit-agent==1.0.0 -emoji==2.11.1 -entrypoints==0.4 -et-xmlfile==1.1.0 -exceptiongroup==1.2.1 -Faker==25.0.1 -fastapi==0.99.1 -favicon==0.7.0 -filelock==3.14.0 -filetype==1.2.0 -flatbuffers==24.3.25 -fonttools==4.51.0 -frozenlist==1.4.1 -fsspec==2024.3.1 -gitdb==4.0.11 -GitPython==3.1.43 -greenlet==3.0.3 -h11==0.14.0 -hibagent==1.0.1 -htbuilder==0.6.2 -httpcore==1.0.5 -httplib2==0.20.2 -httptools==0.6.1 -httpx==0.27.0 -huggingface-hub==0.23.0 -humanfriendly==10.0 -hyperlink==21.0.0 -idna==3.3 -importlib-metadata==4.6.4 -importlib_resources==6.4.0 -incremental==21.3.0 -jeepney==0.7.1 -Jinja2==3.0.3 -jmespath==1.0.1 -joblib==1.4.2 -jsonpatch==1.33 -jsonpointer==2.0 -jsonschema==3.2.0 -keyring==23.5.0 -kiwisolver==1.4.5 -langchain==0.1.17 -langchain-community==0.0.37 -langchain-core==0.1.52 -langchain-text-splitters==0.0.1 -langdetect==1.0.9 -langsmith==0.1.54 -launchpadlib==1.10.16 -lazr.restfulclient==0.14.4 -lazr.uri==1.0.6 -lxml==5.2.1 -Markdown==3.6 -markdown-it-py==3.0.0 -markdownlit==0.0.7 -MarkupSafe==2.0.1 -marshmallow==3.21.2 -matplotlib==3.8.4 -mdurl==0.1.2 -monotonic==1.6 -more-itertools==8.10.0 -mpmath==1.3.0 -msal==1.27.0 -multidict==6.0.5 -mypy-extensions==1.0.0 -netifaces==0.11.0 -nltk==3.8.1 -numexpr==2.10.0 -numpy==1.26.4 -oauthlib==3.2.0 -onnxruntime==1.17.3 -openapi-schema-pydantic==1.2.4 -openpyxl==3.1.2 -orjson==3.10.3 -overrides==7.7.0 -packaging==23.2 -pandas==2.2.2 -pdfminer.six==20221105 -pexpect==4.8.0 -pillow==10.3.0 -platformdirs==4.2.1 -posthog==3.5.0 -prometheus_client==0.20.0 -protobuf==4.25.3 -ptyprocess==0.7.0 -pulsar-client==3.5.0 -pyarrow==16.0.0 -pyasn1==0.4.8 -pyasn1-modules==0.2.1 -pycparser==2.22 -pydantic==1.10.15 -pydeck==0.9.0 -Pygments==2.18.0 -PyGObject==3.42.1 -PyHamcrest==2.0.2 -PyJWT==2.3.0 -pymdown-extensions==10.8.1 -pyOpenSSL==24.1.0 -pyparsing==2.4.7 -PyPika==0.48.9 -pyrsistent==0.18.1 -pyserial==3.5 -python-apt==2.4.0+ubuntu3 -python-dateutil==2.9.0.post0 -python-debian==0.1.43+ubuntu1.1 -python-dotenv==1.0.1 -python-iso639==2024.4.27 -python-magic==0.4.24 -pytz==2022.1 -PyYAML==5.4.1 -rapidfuzz==3.9.0 -regex==2024.4.28 -requests==2.31.0 -rich==13.7.1 -rsa==4.7.2 -s3transfer==0.10.1 -SecretStorage==3.3.1 -service-identity==18.1.0 -six==1.16.0 -smmap==5.0.1 -sniffio==1.3.1 -snowflake-connector-python==3.10.0 -snowflake-snowpark-python==1.15.0 -snowflake._legacy==0.8.0 -snowflake.core==0.8.0 -sortedcontainers==2.4.0 -sos==4.5.6 -soupsieve==2.5 -SQLAlchemy==2.0.30 -ssh-import-id==5.11 -st-annotated-text==4.0.1 -starlette==0.27.0 -streamlit==1.34.0 -streamlit-camera-input-live==0.2.0 -streamlit-card==1.0.0 -streamlit-embedcode==0.1.2 -streamlit-extras==0.4.2 -streamlit-faker==0.0.3 -streamlit-image-coordinates==0.1.6 -streamlit-keyup==0.2.4 -streamlit-toggle-switch==1.0.2 -streamlit-vertical-slider==2.5.5 -streamlit_pdf_viewer -sympy==1.12 -systemd-python==234 -tabulate==0.9.0 -tenacity==8.2.3 -tokenizers==0.19.1 -toml==0.10.2 -tomlkit==0.12.4 -toolz==0.12.1 -tornado==6.4 -tqdm==4.66.4 -Twisted==22.1.0 -typing-inspect==0.9.0 -typing_extensions==4.11.0 -tzdata==2024.1 -ubuntu-advantage-tools==8001 -ufw==0.36.1 -unattended-upgrades==0.1 -unstructured==0.11.2 -urllib3==1.26.6 -uvicorn==0.29.0 -uvloop==0.19.0 -validators==0.28.1 -wadllib==1.3.6 -watchdog==4.0.0 -watchfiles==0.21.0 -websockets==12.0 -wrapt==1.16.0 -yarl==1.9.4 -zipp==1.0.0 -zope.interface==5.4.0 +aiohttp==3.9.5 +aiosignal==1.3.1 +altair==5.3.0 +anthropic==0.25.7 +anyio==4.3.0 +asn1crypto==1.5.1 +async-timeout==4.0.3 +atpublic==4.1.0 +attrs==21.2.0 +Automat==20.2.0 +awscli==1.32.99 +Babel==2.8.0 +backoff==2.2.1 +bcrypt==3.2.0 +beautifulsoup4==4.12.3 +blinker==1.4 +boto3==1.34.99 +botocore==1.34.99 +cachetools==5.3.3 +certifi==2020.6.20 +cffi==1.16.0 +chardet==4.0.0 +charset-normalizer==3.3.2 +chroma-hnswlib==0.7.2 +chromadb==0.4.6 +click==8.0.3 +cloud-init==23.4.4 +cloudpickle==2.2.1 +colorama==0.4.4 +coloredlogs==15.0.1 +command-not-found==0.3 +configobj==5.0.6 +constantly==15.1.0 +contourpy==1.2.1 +cryptography==42.0.7 +cycler==0.12.1 +dataclasses-json==0.5.14 +dbus-python==1.2.18 +distro==1.7.0 +distro-info==1.1+ubuntu0.2 +docutils==0.16 +docx2txt==0.8 +ec2-hibinit-agent==1.0.0 +emoji==2.11.1 +entrypoints==0.4 +et-xmlfile==1.1.0 +exceptiongroup==1.2.1 +Faker==25.0.1 +fastapi==0.99.1 +favicon==0.7.0 +filelock==3.14.0 +filetype==1.2.0 +flatbuffers==24.3.25 +fonttools==4.51.0 +frozenlist==1.4.1 +fsspec==2024.3.1 +gitdb==4.0.11 +GitPython==3.1.43 +greenlet==3.0.3 +h11==0.14.0 +hibagent==1.0.1 +htbuilder==0.6.2 +httpcore==1.0.5 +httplib2==0.20.2 +httptools==0.6.1 +httpx==0.27.0 +huggingface-hub==0.23.0 +humanfriendly==10.0 +hyperlink==21.0.0 +idna==3.3 +importlib-metadata==4.6.4 +importlib_resources==6.4.0 +incremental==21.3.0 +jeepney==0.7.1 +Jinja2==3.0.3 +jmespath==1.0.1 +joblib==1.4.2 +jsonpatch==1.33 +jsonpointer==2.0 +jsonschema==3.2.0 +keyring==23.5.0 +kiwisolver==1.4.5 +langchain==0.1.17 +langchain-community==0.0.37 +langchain-core==0.1.52 +langchain-text-splitters==0.0.1 +langdetect==1.0.9 +langsmith==0.1.54 +launchpadlib==1.10.16 +lazr.restfulclient==0.14.4 +lazr.uri==1.0.6 +lxml==5.2.1 +Markdown==3.6 +markdown-it-py==3.0.0 +markdownlit==0.0.7 +MarkupSafe==2.0.1 +marshmallow==3.21.2 +matplotlib==3.8.4 +mdurl==0.1.2 +monotonic==1.6 +more-itertools==8.10.0 +mpmath==1.3.0 +msal==1.27.0 +multidict==6.0.5 +mypy-extensions==1.0.0 +netifaces==0.11.0 +nltk==3.8.1 +numexpr==2.10.0 +numpy==1.26.4 +oauthlib==3.2.0 +onnxruntime==1.17.3 +openapi-schema-pydantic==1.2.4 +openpyxl==3.1.2 +orjson==3.10.3 +overrides==7.7.0 +packaging==23.2 +pandas==2.2.2 +pdfminer.six==20221105 +pexpect==4.8.0 +pillow==10.3.0 +platformdirs==4.2.1 +posthog==3.5.0 +prometheus_client==0.20.0 +protobuf==4.25.3 +ptyprocess==0.7.0 +pulsar-client==3.5.0 +pyarrow==16.0.0 +pyasn1==0.4.8 +pyasn1-modules==0.2.1 +pycparser==2.22 +pydantic==1.10.15 +pydeck==0.9.0 +Pygments==2.18.0 +PyGObject==3.42.1 +PyHamcrest==2.0.2 +PyJWT==2.3.0 +pymdown-extensions==10.8.1 +pyOpenSSL==24.1.0 +pyparsing==2.4.7 +PyPika==0.48.9 +pyrsistent==0.18.1 +pyserial==3.5 +python-apt==2.4.0+ubuntu3 +python-dateutil==2.9.0.post0 +python-debian==0.1.43+ubuntu1.1 +python-dotenv==1.0.1 +python-iso639==2024.4.27 +python-magic==0.4.24 +pytz==2022.1 +PyYAML==5.4.1 +rapidfuzz==3.9.0 +regex==2024.4.28 +requests==2.31.0 +rich==13.7.1 +rsa==4.7.2 +s3transfer==0.10.1 +SecretStorage==3.3.1 +service-identity==18.1.0 +six==1.16.0 +smmap==5.0.1 +sniffio==1.3.1 +snowflake-connector-python==3.10.0 +snowflake-snowpark-python==1.15.0 +snowflake._legacy==0.8.0 +snowflake.core==0.8.0 +sortedcontainers==2.4.0 +sos==4.5.6 +soupsieve==2.5 +SQLAlchemy==2.0.30 +ssh-import-id==5.11 +st-annotated-text==4.0.1 +starlette==0.27.0 +streamlit==1.34.0 +streamlit-camera-input-live==0.2.0 +streamlit-card==1.0.0 +streamlit-embedcode==0.1.2 +streamlit-extras==0.4.2 +streamlit-faker==0.0.3 +streamlit-image-coordinates==0.1.6 +streamlit-keyup==0.2.4 +streamlit-toggle-switch==1.0.2 +streamlit-vertical-slider==2.5.5 +streamlit_pdf_viewer +sympy==1.12 +systemd-python==234 +tabulate==0.9.0 +tenacity==8.2.3 +tokenizers==0.19.1 +toml==0.10.2 +tomlkit==0.12.4 +toolz==0.12.1 +tornado==6.4 +tqdm==4.66.4 +Twisted==22.1.0 +typing-inspect==0.9.0 +typing_extensions==4.11.0 +tzdata==2024.1 +ubuntu-advantage-tools==8001 +ufw==0.36.1 +unattended-upgrades==0.1 +unstructured==0.11.2 +urllib3==1.26.6 +uvicorn==0.29.0 +uvloop==0.19.0 +validators==0.28.1 +wadllib==1.3.6 +watchdog==4.0.0 +watchfiles==0.21.0 +websockets==12.0 +wrapt==1.16.0 +yarl==1.9.4 +zipp==1.0.0 +zope.interface==5.4.0 diff --git a/streamlit/requirements.txt b/streamlit/requirements.txt index 94f93cf..2987bbd 100644 --- a/streamlit/requirements.txt +++ b/streamlit/requirements.txt @@ -1,39 +1,18 @@ -# Natural Language Processing -langchain==0.0.267 -chromadb==0.4.6 -pdfminer.six==20221105 -InstructorEmbedding -sentence-transformers==2.2.2 -faiss-cpu -huggingface_hub -transformers -autoawq -protobuf==3.20.2; sys_platform != 'darwin' -protobuf==3.20.2; sys_platform == 'darwin' and platform_machine != 'arm64' -protobuf==3.20.3; sys_platform == 'darwin' and platform_machine == 'arm64' -auto-gptq==0.2.2 -docx2txt -unstructured -unstructured[pdf] - -# Utilities -urllib3==1.26.6 -accelerate -bitsandbytes ; sys_platform != 'win32' -bitsandbytes-windows ; sys_platform == 'win32' -click -flask -requests - -# Streamlit related -streamlit -Streamlit-extras - -# Excel File Manipulation -openpyxl -numpy>=1.22.2 - -# AWS related -boto3 -awscli - +anthropic==0.36.0 +boto3==1.35.37 +botocore==1.35.37 +chromadb==0.5.12 +click==8.1.7 +click==8.0.3 +langchain==0.3.3 +langchain_community==0.3.2 +msal==1.31.0 +numpy==2.1.2 +pandas==2.2.3 +pydantic==2.9.2 +python_dateutil==2.9.0.post0 +Requests==2.32.3 +snowflake==0.13.0 +streamlit_extras==0.4.7 +streamlit_pdf_viewer==0.0.18 +torch==2.4.1 diff --git a/streamlit_multipage/requirements.txt b/streamlit_multipage/requirements.txt index 2b11d15..12fb6ee 100644 --- a/streamlit_multipage/requirements.txt +++ b/streamlit_multipage/requirements.txt @@ -1,4 +1,4 @@ -pandas==2.2.2 -streamlit==1.35.0 +pandas==2.2.3 +streamlit==1.39.0 streamlit_extras==0.4.7 -streamlit_pdf_viewer==0.0.17 +streamlit_pdf_viewer==0.0.18 diff --git a/textract-pipeline/src/lambda-layer/pypdf2-layer-new/requirements.txt b/textract-pipeline/src/lambda-layer/pypdf2-layer-new/requirements.txt index d682eda..ef768ef 100644 --- a/textract-pipeline/src/lambda-layer/pypdf2-layer-new/requirements.txt +++ b/textract-pipeline/src/lambda-layer/pypdf2-layer-new/requirements.txt @@ -1,2 +1,2 @@ -PyPDF2 +PyPDF2 pycryptodome \ No newline at end of file diff --git a/textract-pipeline/src/lambda/batch-creation/requirements.txt b/textract-pipeline/src/lambda/batch-creation/requirements.txt new file mode 100644 index 0000000..2d828d8 --- /dev/null +++ b/textract-pipeline/src/lambda/batch-creation/requirements.txt @@ -0,0 +1 @@ +boto3==1.35.37 diff --git a/textract-pipeline/src/lambda/call-bedrock/requirements.txt b/textract-pipeline/src/lambda/call-bedrock/requirements.txt new file mode 100644 index 0000000..d5497cc --- /dev/null +++ b/textract-pipeline/src/lambda/call-bedrock/requirements.txt @@ -0,0 +1,2 @@ +boto3==1.35.37 +botocore==1.35.37 diff --git a/textract-pipeline/src/lambda/database-interface-get/requirements.txt b/textract-pipeline/src/lambda/database-interface-get/requirements.txt new file mode 100644 index 0000000..8c5123d --- /dev/null +++ b/textract-pipeline/src/lambda/database-interface-get/requirements.txt @@ -0,0 +1,2 @@ +boto3==1.35.37 +snowflake==0.13.0 diff --git a/textract-pipeline/src/lambda/database-interface/requirements.txt b/textract-pipeline/src/lambda/database-interface/requirements.txt new file mode 100644 index 0000000..8c5123d --- /dev/null +++ b/textract-pipeline/src/lambda/database-interface/requirements.txt @@ -0,0 +1,2 @@ +boto3==1.35.37 +snowflake==0.13.0 diff --git a/textract-pipeline/src/lambda/docx-to-pdf/requirements.txt b/textract-pipeline/src/lambda/docx-to-pdf/requirements.txt new file mode 100644 index 0000000..a1d7e95 --- /dev/null +++ b/textract-pipeline/src/lambda/docx-to-pdf/requirements.txt @@ -0,0 +1,3 @@ +boto3==1.35.37 +botocore==1.35.37 +brotli==1.1.0 diff --git a/textract-pipeline/src/lambda/insert-record/requirements.txt b/textract-pipeline/src/lambda/insert-record/requirements.txt new file mode 100644 index 0000000..2d828d8 --- /dev/null +++ b/textract-pipeline/src/lambda/insert-record/requirements.txt @@ -0,0 +1 @@ +boto3==1.35.37 diff --git a/textract-pipeline/src/lambda/pdf-validation/requirements.txt b/textract-pipeline/src/lambda/pdf-validation/requirements.txt new file mode 100644 index 0000000..090aa84 --- /dev/null +++ b/textract-pipeline/src/lambda/pdf-validation/requirements.txt @@ -0,0 +1,3 @@ +boto3==1.35.37 +botocore==1.35.37 +PyPDF2==3.0.1 \ No newline at end of file diff --git a/textract-pipeline/src/lambda/prompt-orchestrator/requirements.txt b/textract-pipeline/src/lambda/prompt-orchestrator/requirements.txt new file mode 100644 index 0000000..ed81246 --- /dev/null +++ b/textract-pipeline/src/lambda/prompt-orchestrator/requirements.txt @@ -0,0 +1,7 @@ +anthropic==0.36.0 +boto3==1.35.37 +botocore==1.35.37 +numpy==2.1.2 +pandas==2.2.3 +Requests==2.32.3 +snowflake==0.13.0 diff --git a/textract-pipeline/src/lambda/prompt-processor/requirements.txt b/textract-pipeline/src/lambda/prompt-processor/requirements.txt new file mode 100644 index 0000000..2d828d8 --- /dev/null +++ b/textract-pipeline/src/lambda/prompt-processor/requirements.txt @@ -0,0 +1 @@ +boto3==1.35.37 diff --git a/textract-pipeline/src/lambda/s3-folder-details/requirements.txt b/textract-pipeline/src/lambda/s3-folder-details/requirements.txt new file mode 100644 index 0000000..2d828d8 --- /dev/null +++ b/textract-pipeline/src/lambda/s3-folder-details/requirements.txt @@ -0,0 +1 @@ +boto3==1.35.37 diff --git a/textract-pipeline/src/lambda/text-creation/requirements.txt b/textract-pipeline/src/lambda/text-creation/requirements.txt new file mode 100644 index 0000000..ae1f099 --- /dev/null +++ b/textract-pipeline/src/lambda/text-creation/requirements.txt @@ -0,0 +1,3 @@ +boto3==1.35.37 +pandas==2.2.3 +PyPDF2==3.0.1 diff --git a/textract-pipeline/src/lambda/textract-receiver/requirements.txt b/textract-pipeline/src/lambda/textract-receiver/requirements.txt new file mode 100644 index 0000000..d5497cc --- /dev/null +++ b/textract-pipeline/src/lambda/textract-receiver/requirements.txt @@ -0,0 +1,2 @@ +boto3==1.35.37 +botocore==1.35.37 diff --git a/textract-pipeline/src/lambda/textract-sender/requirements.txt b/textract-pipeline/src/lambda/textract-sender/requirements.txt new file mode 100644 index 0000000..d5497cc --- /dev/null +++ b/textract-pipeline/src/lambda/textract-sender/requirements.txt @@ -0,0 +1,2 @@ +boto3==1.35.37 +botocore==1.35.37 diff --git a/textract-pipeline/src/lambda/tiff-to-pdf/requirements.txt b/textract-pipeline/src/lambda/tiff-to-pdf/requirements.txt new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/textract-pipeline/src/lambda/tiff-to-pdf/requirements.txt @@ -0,0 +1 @@ + diff --git a/textract-pipeline/src/lambda/trigger-pipeline/requirements.txt b/textract-pipeline/src/lambda/trigger-pipeline/requirements.txt new file mode 100644 index 0000000..d5497cc --- /dev/null +++ b/textract-pipeline/src/lambda/trigger-pipeline/requirements.txt @@ -0,0 +1,2 @@ +boto3==1.35.37 +botocore==1.35.37