diff --git a/.github/update-requirements.yml b/.github/update-requirements.yml new file mode 100644 index 00000000..31d0abe6 --- /dev/null +++ b/.github/update-requirements.yml @@ -0,0 +1,26 @@ +name: Update requirements +on: + push: + paths: + - 'pyproject.toml' + - '.github/workflows/update-requirements.yml' + +jobs: + update: + name: Update requirements + runs-on: ubuntu-latest + steps: + - name: Install the latest version of rye + uses: eifinger/setup-rye@v3 + - name: Build app + run: rye run update-requirements + commit: + name: Commit changes + run: | + git config --global user.name 'github-actions' + git config --global user.email 'github-actions[bot]@users.noreply.github.com' + git add . + git commit -m "ci: update requirements.txt [skip ci]" + git push + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} diff --git a/CHANGELOG.md b/CHANGELOG.md index 01fb0c3a..e8b2ceb3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,20 @@ +## [1.10.0-beta.6](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.10.0-beta.5...v1.10.0-beta.6) (2024-07-22) + + +### Features + +* add new toml ([fcb3220](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/fcb3220868e7ef1127a7a47f40d0379be282e6eb)) + + +### chore + +* **pyproject:** upgrade dependencies ([0425124](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/0425124c570f765b98fcf67ba6649f4f9fe76b15)) + + +### Docs + +* **gpt-4o-mini:** added new gpt, fixed chromium lazy loading, ([99dc849](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/99dc8497d85289759286a973e4aecc3f924d3ada)) + ## [1.10.0-beta.5](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.10.0-beta.4...v1.10.0-beta.5) (2024-07-20) diff --git a/manual deployment/autorequirements.py b/manual deployment/autorequirements.py new file mode 100644 index 00000000..2bb7e1e8 --- /dev/null +++ b/manual deployment/autorequirements.py @@ -0,0 +1,30 @@ +import toml + +# Load the TOML file +data = toml.load('pyproject.toml') + +# Get the dependencies +dependencies = data['project']['dependencies'] + +# Write the dependencies to a requirements.txt file +with open('requirements.txt', 'w') as f: + for dependency in dependencies: + f.write(dependency + '\n') + +# Get the dev dependencies +dev_dependencies = data['tool']['rye']['dev-dependencies'] + +# Expand the optional dependencies +optional_dependencies = data['project']['optional-dependencies'] +expanded_dev_dependencies = [] +for dependency in dev_dependencies: + if dependency.startswith('-e file:.'): + optional_dependency_name = dependency.split('.')[1][1:-1] + expanded_dev_dependencies.extend(optional_dependencies[optional_dependency_name]) + else: + expanded_dev_dependencies.append(dependency) + +# Write the expanded dev dependencies to a requirements-dev.txt file +with open('requirements-dev.txt', 'w') as f: + for dependency in expanded_dev_dependencies: + f.write(dependency + '\n') \ No newline at end of file diff --git a/pyproject.toml b/pyproject.toml index 827a7d64..39c7209d 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -2,7 +2,7 @@ name = "scrapegraphai" -version = "1.10.0b5" +version = "1.10.0b6" @@ -13,30 +13,30 @@ authors = [ { name = "Lorenzo Padoan", email = "lorenzo.padoan977@gmail.com" } ] dependencies = [ - "langchain", - "langchain-google-genai", + "langchain>=0.2.10", + "langchain-google-genai>=1.0.7", "langchain-google-vertexai", - "langchain-openai", - "langchain-groq==0.1.3", - "langchain-aws==0.1.3", - "langchain-anthropic==0.1.11", + "langchain-openai>=0.1.17", + "langchain-groq>=0.1.3", + "langchain-aws>=0.1.3", + "langchain-anthropic>=0.1.11", "langchain-nvidia-ai-endpoints==0.1.6", - "html2text==2024.2.26", - "faiss-cpu==1.8.0", - "beautifulsoup4==4.12.3", - "pandas==2.2.2", - "python-dotenv==1.0.1", - "tiktoken==0.7", - "tqdm==4.66.4", - "graphviz==0.20.3", - "minify-html==0.15.0", - "free-proxy==1.1.1", - "playwright==1.43.0", - "google==3.0.0", - "undetected-playwright==0.3.0", - "semchunk==1.0.1", - "html2text==2024.2.26", - "langchain-fireworks==0.1.3" + "html2text>=2024.2.26", + "faiss-cpu>=1.8.0", + "beautifulsoup4>=4.12.3", + "pandas>=2.2.2", + "python-dotenv>=1.0.1", + "tiktoken>=0.7", + "tqdm>=4.66.4", + "graphviz>=0.20.3", + "minify-html>=0.15.0", + "free-proxy>=1.1.1", + "playwright>=1.43.0", + "google>=3.0.0", + "undetected-playwright>=0.3.0", + "semchunk>=1.0.1", + "html2text>=2024.2.26", + "langchain-fireworks>=0.1.3", ] license = "MIT" @@ -91,4 +91,5 @@ dev-dependencies = [ [tool.rye.scripts] pylint-local = "pylint scrapegraphai/**/*.py" -pylint-ci = "pylint --disable=C0114,C0115,C0116 --exit-zero scrapegraphai/**/*.py" \ No newline at end of file +pylint-ci = "pylint --disable=C0114,C0115,C0116 --exit-zero scrapegraphai/**/*.py" +update-requirements = "python 'manual deployment/autorequirements.py'" diff --git a/requirements-dev.lock b/requirements-dev.lock index b22a5576..3e8ddc74 100644 --- a/requirements-dev.lock +++ b/requirements-dev.lock @@ -8,11 +8,10 @@ # with-sources: false -e file:. -aiofiles==23.2.1 +aiofiles==24.1.0 # via burr aiohttp==3.9.5 # via langchain - # via langchain-community # via langchain-fireworks # via langchain-nvidia-ai-endpoints aiosignal==1.3.1 @@ -25,14 +24,14 @@ annotated-types==0.7.0 # via pydantic anthropic==0.31.2 # via langchain-anthropic -anyio==4.3.0 +anyio==4.4.0 # via anthropic # via groq # via httpx # via openai # via starlette # via watchfiles -astroid==3.2.2 +astroid==3.2.4 # via pylint async-timeout==4.0.3 # via aiohttp @@ -49,17 +48,17 @@ beautifulsoup4==4.12.3 # via scrapegraphai blinker==1.8.2 # via streamlit -boto3==1.34.145 +boto3==1.34.146 # via langchain-aws -botocore==1.34.145 +botocore==1.34.146 # via boto3 # via s3transfer burr==0.22.1 # via scrapegraphai -cachetools==5.3.3 +cachetools==5.4.0 # via google-auth # via streamlit -certifi==2024.2.2 +certifi==2024.7.4 # via httpcore # via httpx # via requests @@ -74,12 +73,10 @@ contourpy==1.2.1 # via matplotlib cycler==0.12.1 # via matplotlib -dataclasses-json==0.6.7 - # via langchain - # via langchain-community defusedxml==0.7.1 # via langchain-anthropic dill==0.3.8 + # via multiprocess # via pylint distro==1.9.0 # via anthropic @@ -91,32 +88,31 @@ docstring-parser==0.16 # via google-cloud-aiplatform docutils==0.19 # via sphinx -email-validator==2.1.1 +email-validator==2.2.0 # via fastapi -exceptiongroup==1.2.1 +exceptiongroup==1.2.2 # via anyio # via pytest -faiss-cpu==1.8.0 +faiss-cpu==1.8.0.post1 # via scrapegraphai -fastapi==0.111.0 +fastapi==0.111.1 # via burr - # via fastapi-pagination fastapi-cli==0.0.4 # via fastapi -fastapi-pagination==0.12.24 +fastapi-pagination==0.12.26 # via burr -filelock==3.14.0 +filelock==3.15.4 # via huggingface-hub fireworks-ai==0.14.0 # via langchain-fireworks -fonttools==4.52.1 +fonttools==4.53.1 # via matplotlib free-proxy==1.1.1 # via scrapegraphai frozenlist==1.4.1 # via aiohttp # via aiosignal -fsspec==2024.5.0 +fsspec==2024.6.1 # via huggingface-hub furo==2024.5.6 # via scrapegraphai @@ -126,9 +122,9 @@ gitpython==3.1.43 # via streamlit google==3.0.0 # via scrapegraphai -google-ai-generativelanguage==0.6.4 +google-ai-generativelanguage==0.6.6 # via google-generativeai -google-api-core==2.19.0 +google-api-core==2.19.1 # via google-ai-generativelanguage # via google-api-python-client # via google-cloud-aiplatform @@ -137,9 +133,9 @@ google-api-core==2.19.0 # via google-cloud-resource-manager # via google-cloud-storage # via google-generativeai -google-api-python-client==2.130.0 +google-api-python-client==2.137.0 # via google-generativeai -google-auth==2.29.0 +google-auth==2.32.0 # via google-ai-generativelanguage # via google-api-core # via google-api-python-client @@ -152,27 +148,27 @@ google-auth==2.29.0 # via google-generativeai google-auth-httplib2==0.2.0 # via google-api-python-client -google-cloud-aiplatform==1.58.0 +google-cloud-aiplatform==1.59.0 # via langchain-google-vertexai google-cloud-bigquery==3.25.0 # via google-cloud-aiplatform google-cloud-core==2.4.1 # via google-cloud-bigquery # via google-cloud-storage -google-cloud-resource-manager==1.12.3 +google-cloud-resource-manager==1.12.4 # via google-cloud-aiplatform -google-cloud-storage==2.17.0 +google-cloud-storage==2.18.0 # via google-cloud-aiplatform # via langchain-google-vertexai google-crc32c==1.5.0 # via google-cloud-storage # via google-resumable-media -google-generativeai==0.5.4 +google-generativeai==0.7.2 # via langchain-google-genai google-resumable-media==2.7.1 # via google-cloud-bigquery # via google-cloud-storage -googleapis-common-protos==1.63.0 +googleapis-common-protos==1.63.2 # via google-api-core # via grpc-google-iam-v1 # via grpcio-status @@ -181,11 +177,12 @@ graphviz==0.20.3 # via scrapegraphai greenlet==3.0.3 # via playwright -groq==0.8.0 + # via sqlalchemy +groq==0.9.0 # via langchain-groq grpc-google-iam-v1==0.13.1 # via google-cloud-resource-manager -grpcio==1.64.0 +grpcio==1.65.1 # via google-api-core # via googleapis-common-protos # via grpc-google-iam-v1 @@ -212,7 +209,7 @@ httpx==0.27.0 # via openai httpx-sse==0.4.0 # via fireworks-ai -huggingface-hub==0.23.1 +huggingface-hub==0.24.0 # via tokenizers idna==3.7 # via anyio @@ -236,34 +233,31 @@ jinja2==3.1.4 # via fastapi # via pydeck # via sphinx -jiter==0.4.0 +jiter==0.5.0 # via anthropic jmespath==1.0.1 # via boto3 # via botocore jsonpatch==1.33 # via langchain-core -jsonpointer==2.4 +jsonpointer==3.0.0 # via jsonpatch -jsonschema==4.22.0 +jsonschema==4.23.0 # via altair jsonschema-specifications==2023.12.1 # via jsonschema kiwisolver==1.4.5 # via matplotlib -langchain==0.1.20 +langchain==0.2.10 # via scrapegraphai -langchain-anthropic==0.1.11 +langchain-anthropic==0.1.20 # via scrapegraphai -langchain-aws==0.1.3 +langchain-aws==0.1.12 # via scrapegraphai -langchain-community==0.0.38 - # via langchain -langchain-core==0.1.52 +langchain-core==0.2.22 # via langchain # via langchain-anthropic # via langchain-aws - # via langchain-community # via langchain-fireworks # via langchain-google-genai # via langchain-google-vertexai @@ -271,23 +265,22 @@ langchain-core==0.1.52 # via langchain-nvidia-ai-endpoints # via langchain-openai # via langchain-text-splitters -langchain-fireworks==0.1.3 +langchain-fireworks==0.1.5 # via scrapegraphai -langchain-google-genai==1.0.4 +langchain-google-genai==1.0.8 # via scrapegraphai -langchain-google-vertexai==1.0.4 +langchain-google-vertexai==1.0.7 # via scrapegraphai -langchain-groq==0.1.3 +langchain-groq==0.1.6 # via scrapegraphai langchain-nvidia-ai-endpoints==0.1.6 # via scrapegraphai -langchain-openai==0.1.7 +langchain-openai==0.1.17 # via scrapegraphai -langchain-text-splitters==0.0.2 +langchain-text-splitters==0.2.2 # via langchain langsmith==0.1.93 # via langchain - # via langchain-community # via langchain-core loguru==0.7.2 # via burr @@ -297,9 +290,7 @@ markdown-it-py==3.0.0 # via rich markupsafe==2.1.5 # via jinja2 -marshmallow==3.21.3 - # via dataclasses-json -matplotlib==3.9.0 +matplotlib==3.9.1 # via burr mccabe==0.7.0 # via pylint @@ -307,9 +298,13 @@ mdurl==0.1.2 # via markdown-it-py minify-html==0.15.0 # via scrapegraphai +mpire==2.10.2 + # via semchunk multidict==6.0.5 # via aiohttp # via yarl +multiprocess==0.70.16 + # via mpire mypy-extensions==1.0.0 # via typing-inspect numpy==1.26.4 @@ -318,7 +313,6 @@ numpy==1.26.4 # via faiss-cpu # via langchain # via langchain-aws - # via langchain-community # via matplotlib # via pandas # via pyarrow @@ -330,16 +324,15 @@ openai==1.37.0 # via burr # via langchain-fireworks # via langchain-openai -orjson==3.10.3 - # via fastapi +orjson==3.10.6 # via langsmith -packaging==23.2 +packaging==24.1 # via altair + # via faiss-cpu # via google-cloud-aiplatform # via google-cloud-bigquery # via huggingface-hub # via langchain-core - # via marshmallow # via matplotlib # via pytest # via sphinx @@ -349,19 +342,19 @@ pandas==2.2.2 # via scrapegraphai # via sf-hamilton # via streamlit -pillow==10.3.0 +pillow==10.4.0 # via fireworks-ai # via langchain-nvidia-ai-endpoints # via matplotlib # via streamlit platformdirs==4.2.2 # via pylint -playwright==1.43.0 +playwright==1.45.0 # via scrapegraphai # via undetected-playwright pluggy==1.5.0 # via pytest -proto-plus==1.23.0 +proto-plus==1.24.0 # via google-ai-generativelanguage # via google-api-core # via google-cloud-aiplatform @@ -377,14 +370,14 @@ protobuf==4.25.3 # via grpcio-status # via proto-plus # via streamlit -pyarrow==16.1.0 +pyarrow==17.0.0 # via streamlit pyasn1==0.6.0 # via pyasn1-modules # via rsa pyasn1-modules==0.4.0 # via google-auth -pydantic==2.7.1 +pydantic==2.8.2 # via anthropic # via burr # via fastapi @@ -397,7 +390,7 @@ pydantic==2.7.1 # via langchain-core # via langsmith # via openai -pydantic-core==2.18.2 +pydantic-core==2.20.1 # via pydantic pydeck==0.9.1 # via streamlit @@ -405,9 +398,10 @@ pyee==11.1.0 # via playwright pygments==2.18.0 # via furo + # via mpire # via rich # via sphinx -pylint==3.2.5 +pylint==3.2.6 pyparsing==3.1.2 # via httplib2 # via matplotlib @@ -429,7 +423,6 @@ pytz==2024.1 pyyaml==6.0.1 # via huggingface-hub # via langchain - # via langchain-community # via langchain-core # via uvicorn referencing==0.35.1 @@ -437,7 +430,7 @@ referencing==0.35.1 # via jsonschema-specifications regex==2024.5.15 # via tiktoken -requests==2.32.2 +requests==2.32.3 # via burr # via free-proxy # via google-api-core @@ -445,7 +438,6 @@ requests==2.32.2 # via google-cloud-storage # via huggingface-hub # via langchain - # via langchain-community # via langchain-fireworks # via langsmith # via sphinx @@ -454,18 +446,18 @@ requests==2.32.2 rich==13.7.1 # via streamlit # via typer -rpds-py==0.18.1 +rpds-py==0.19.0 # via jsonschema # via referencing rsa==4.9 # via google-auth -s3transfer==0.10.1 +s3transfer==0.10.2 # via boto3 -semchunk==1.0.1 +semchunk==2.2.0 # via scrapegraphai -sf-hamilton==1.63.0 +sf-hamilton==1.72.1 # via burr -shapely==2.0.4 +shapely==2.0.5 # via google-cloud-aiplatform shellingham==1.5.4 # via typer @@ -493,24 +485,22 @@ sphinxcontrib-applehelp==1.0.8 # via sphinx sphinxcontrib-devhelp==1.0.6 # via sphinx -sphinxcontrib-htmlhelp==2.0.5 +sphinxcontrib-htmlhelp==2.0.6 # via sphinx sphinxcontrib-jsmath==1.0.1 # via sphinx -sphinxcontrib-qthelp==1.0.7 +sphinxcontrib-qthelp==1.0.8 # via sphinx sphinxcontrib-serializinghtml==1.1.10 # via sphinx -sqlalchemy==2.0.30 +sqlalchemy==2.0.31 # via langchain - # via langchain-community starlette==0.37.2 # via fastapi -streamlit==1.35.0 +streamlit==1.36.0 # via burr -tenacity==8.3.0 +tenacity==8.5.0 # via langchain - # via langchain-community # via langchain-core # via streamlit tiktoken==0.7.0 @@ -523,21 +513,22 @@ toml==0.10.2 tomli==2.0.1 # via pylint # via pytest -tomlkit==0.12.5 +tomlkit==0.13.0 # via pylint toolz==0.12.1 # via altair -tornado==6.4 +tornado==6.4.1 # via streamlit tqdm==4.66.4 # via google-generativeai # via huggingface-hub + # via mpire # via openai # via scrapegraphai # via semchunk typer==0.12.3 # via fastapi-cli -typing-extensions==4.12.0 +typing-extensions==4.12.2 # via altair # via anthropic # via anyio @@ -560,25 +551,22 @@ typing-extensions==4.12.0 # via typing-inspect # via uvicorn typing-inspect==0.9.0 - # via dataclasses-json # via sf-hamilton tzdata==2024.1 # via pandas -ujson==5.10.0 - # via fastapi undetected-playwright==0.3.0 # via scrapegraphai uritemplate==4.1.1 # via google-api-python-client -urllib3==1.26.18 +urllib3==1.26.19 # via botocore # via requests -uvicorn==0.29.0 +uvicorn==0.30.3 # via burr # via fastapi uvloop==0.19.0 # via uvicorn -watchfiles==0.21.0 +watchfiles==0.22.0 # via uvicorn websockets==12.0 # via uvicorn diff --git a/requirements-dev.txt b/requirements-dev.txt index d33296d5..e04399e9 100644 --- a/requirements-dev.txt +++ b/requirements-dev.txt @@ -1,4 +1,6 @@ -sphinx==7.1.2 -furo==2024.5.6 pytest==8.0.0 -burr[start]==0.22.1 \ No newline at end of file +pytest-mock==3.14.0 +burr[start]==0.22.1 +sphinx==6.0 +furo==2024.5.6 +pylint>=3.2.5 diff --git a/requirements.lock b/requirements.lock index 0d4c33e1..d99559de 100644 --- a/requirements.lock +++ b/requirements.lock @@ -10,7 +10,6 @@ -e file:. aiohttp==3.9.5 # via langchain - # via langchain-community # via langchain-fireworks # via langchain-nvidia-ai-endpoints aiosignal==1.3.1 @@ -19,7 +18,7 @@ annotated-types==0.7.0 # via pydantic anthropic==0.31.2 # via langchain-anthropic -anyio==4.3.0 +anyio==4.4.0 # via anthropic # via groq # via httpx @@ -32,35 +31,34 @@ attrs==23.2.0 beautifulsoup4==4.12.3 # via google # via scrapegraphai -boto3==1.34.145 +boto3==1.34.146 # via langchain-aws -botocore==1.34.145 +botocore==1.34.146 # via boto3 # via s3transfer -cachetools==5.3.3 +cachetools==5.4.0 # via google-auth -certifi==2024.2.2 +certifi==2024.7.4 # via httpcore # via httpx # via requests charset-normalizer==3.3.2 # via requests -dataclasses-json==0.6.7 - # via langchain - # via langchain-community defusedxml==0.7.1 # via langchain-anthropic +dill==0.3.8 + # via multiprocess distro==1.9.0 # via anthropic # via groq # via openai docstring-parser==0.16 # via google-cloud-aiplatform -exceptiongroup==1.2.1 +exceptiongroup==1.2.2 # via anyio -faiss-cpu==1.8.0 +faiss-cpu==1.8.0.post1 # via scrapegraphai -filelock==3.14.0 +filelock==3.15.4 # via huggingface-hub fireworks-ai==0.14.0 # via langchain-fireworks @@ -69,13 +67,13 @@ free-proxy==1.1.1 frozenlist==1.4.1 # via aiohttp # via aiosignal -fsspec==2024.5.0 +fsspec==2024.6.1 # via huggingface-hub google==3.0.0 # via scrapegraphai -google-ai-generativelanguage==0.6.4 +google-ai-generativelanguage==0.6.6 # via google-generativeai -google-api-core==2.19.0 +google-api-core==2.19.1 # via google-ai-generativelanguage # via google-api-python-client # via google-cloud-aiplatform @@ -84,9 +82,9 @@ google-api-core==2.19.0 # via google-cloud-resource-manager # via google-cloud-storage # via google-generativeai -google-api-python-client==2.130.0 +google-api-python-client==2.137.0 # via google-generativeai -google-auth==2.29.0 +google-auth==2.32.0 # via google-ai-generativelanguage # via google-api-core # via google-api-python-client @@ -99,27 +97,27 @@ google-auth==2.29.0 # via google-generativeai google-auth-httplib2==0.2.0 # via google-api-python-client -google-cloud-aiplatform==1.58.0 +google-cloud-aiplatform==1.59.0 # via langchain-google-vertexai google-cloud-bigquery==3.25.0 # via google-cloud-aiplatform google-cloud-core==2.4.1 # via google-cloud-bigquery # via google-cloud-storage -google-cloud-resource-manager==1.12.3 +google-cloud-resource-manager==1.12.4 # via google-cloud-aiplatform -google-cloud-storage==2.17.0 +google-cloud-storage==2.18.0 # via google-cloud-aiplatform # via langchain-google-vertexai google-crc32c==1.5.0 # via google-cloud-storage # via google-resumable-media -google-generativeai==0.5.4 +google-generativeai==0.7.2 # via langchain-google-genai google-resumable-media==2.7.1 # via google-cloud-bigquery # via google-cloud-storage -googleapis-common-protos==1.63.0 +googleapis-common-protos==1.63.2 # via google-api-core # via grpc-google-iam-v1 # via grpcio-status @@ -127,11 +125,12 @@ graphviz==0.20.3 # via scrapegraphai greenlet==3.0.3 # via playwright -groq==0.8.0 + # via sqlalchemy +groq==0.9.0 # via langchain-groq grpc-google-iam-v1==0.13.1 # via google-cloud-resource-manager -grpcio==1.64.0 +grpcio==1.65.1 # via google-api-core # via googleapis-common-protos # via grpc-google-iam-v1 @@ -154,35 +153,32 @@ httpx==0.27.0 # via openai httpx-sse==0.4.0 # via fireworks-ai -huggingface-hub==0.23.1 +huggingface-hub==0.24.0 # via tokenizers idna==3.7 # via anyio # via httpx # via requests # via yarl -jiter==0.4.0 +jiter==0.5.0 # via anthropic jmespath==1.0.1 # via boto3 # via botocore jsonpatch==1.33 # via langchain-core -jsonpointer==2.4 +jsonpointer==3.0.0 # via jsonpatch -langchain==0.1.20 +langchain==0.2.10 # via scrapegraphai -langchain-anthropic==0.1.11 +langchain-anthropic==0.1.20 # via scrapegraphai -langchain-aws==0.1.3 +langchain-aws==0.1.12 # via scrapegraphai -langchain-community==0.0.38 - # via langchain -langchain-core==0.1.52 +langchain-core==0.2.22 # via langchain # via langchain-anthropic # via langchain-aws - # via langchain-community # via langchain-fireworks # via langchain-google-genai # via langchain-google-vertexai @@ -190,62 +186,60 @@ langchain-core==0.1.52 # via langchain-nvidia-ai-endpoints # via langchain-openai # via langchain-text-splitters -langchain-fireworks==0.1.3 +langchain-fireworks==0.1.5 # via scrapegraphai -langchain-google-genai==1.0.4 +langchain-google-genai==1.0.8 # via scrapegraphai -langchain-google-vertexai==1.0.4 +langchain-google-vertexai==1.0.7 # via scrapegraphai -langchain-groq==0.1.3 +langchain-groq==0.1.6 # via scrapegraphai langchain-nvidia-ai-endpoints==0.1.6 # via scrapegraphai -langchain-openai==0.1.7 +langchain-openai==0.1.17 # via scrapegraphai -langchain-text-splitters==0.0.2 +langchain-text-splitters==0.2.2 # via langchain langsmith==0.1.93 # via langchain - # via langchain-community # via langchain-core lxml==5.2.2 # via free-proxy -marshmallow==3.21.3 - # via dataclasses-json minify-html==0.15.0 # via scrapegraphai +mpire==2.10.2 + # via semchunk multidict==6.0.5 # via aiohttp # via yarl -mypy-extensions==1.0.0 - # via typing-inspect +multiprocess==0.70.16 + # via mpire numpy==1.26.4 # via faiss-cpu # via langchain # via langchain-aws - # via langchain-community # via pandas # via shapely openai==1.37.0 # via langchain-fireworks # via langchain-openai -orjson==3.10.3 +orjson==3.10.6 # via langsmith -packaging==23.2 +packaging==24.1 + # via faiss-cpu # via google-cloud-aiplatform # via google-cloud-bigquery # via huggingface-hub # via langchain-core - # via marshmallow pandas==2.2.2 # via scrapegraphai -pillow==10.3.0 +pillow==10.4.0 # via fireworks-ai # via langchain-nvidia-ai-endpoints -playwright==1.43.0 +playwright==1.45.0 # via scrapegraphai # via undetected-playwright -proto-plus==1.23.0 +proto-plus==1.24.0 # via google-ai-generativelanguage # via google-api-core # via google-cloud-aiplatform @@ -265,7 +259,7 @@ pyasn1==0.6.0 # via rsa pyasn1-modules==0.4.0 # via google-auth -pydantic==2.7.1 +pydantic==2.8.2 # via anthropic # via fireworks-ai # via google-cloud-aiplatform @@ -275,10 +269,12 @@ pydantic==2.7.1 # via langchain-core # via langsmith # via openai -pydantic-core==2.18.2 +pydantic-core==2.20.1 # via pydantic pyee==11.1.0 # via playwright +pygments==2.18.0 + # via mpire pyparsing==3.1.2 # via httplib2 python-dateutil==2.9.0.post0 @@ -292,28 +288,26 @@ pytz==2024.1 pyyaml==6.0.1 # via huggingface-hub # via langchain - # via langchain-community # via langchain-core regex==2024.5.15 # via tiktoken -requests==2.32.2 +requests==2.32.3 # via free-proxy # via google-api-core # via google-cloud-bigquery # via google-cloud-storage # via huggingface-hub # via langchain - # via langchain-community # via langchain-fireworks # via langsmith # via tiktoken rsa==4.9 # via google-auth -s3transfer==0.10.1 +s3transfer==0.10.2 # via boto3 -semchunk==1.0.1 +semchunk==2.2.0 # via scrapegraphai -shapely==2.0.4 +shapely==2.0.5 # via google-cloud-aiplatform six==1.16.0 # via python-dateutil @@ -325,12 +319,10 @@ sniffio==1.3.1 # via openai soupsieve==2.5 # via beautifulsoup4 -sqlalchemy==2.0.30 +sqlalchemy==2.0.31 # via langchain - # via langchain-community -tenacity==8.3.0 +tenacity==8.5.0 # via langchain - # via langchain-community # via langchain-core tiktoken==0.7.0 # via langchain-openai @@ -340,10 +332,11 @@ tokenizers==0.19.1 tqdm==4.66.4 # via google-generativeai # via huggingface-hub + # via mpire # via openai # via scrapegraphai # via semchunk -typing-extensions==4.12.0 +typing-extensions==4.12.2 # via anthropic # via anyio # via google-generativeai @@ -354,16 +347,13 @@ typing-extensions==4.12.0 # via pydantic-core # via pyee # via sqlalchemy - # via typing-inspect -typing-inspect==0.9.0 - # via dataclasses-json tzdata==2024.1 # via pandas undetected-playwright==0.3.0 # via scrapegraphai uritemplate==4.1.1 # via google-api-python-client -urllib3==1.26.18 +urllib3==1.26.19 # via botocore # via requests yarl==1.9.4 diff --git a/requirements.txt b/requirements.txt index 502e9df5..4a3d525c 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,25 +1,23 @@ -beautifulsoup4==4.12.3 -burr==0.24.0 -free_proxy==1.1.1 -google==3.0.0 -graphviz==0.20.3 -html2text==2024.2.26 -langchain==0.2.10 -langchain_anthropic==0.1.20 -langchain_aws==0.1.11 -langchain_community==0.2.9 -langchain_core==0.2.22 -langchain_fireworks==0.1.5 -langchain_google_genai==1.0.7 -langchain_google_vertexai==1.0.6 -langchain_groq==0.1.6 -langchain_openai==0.1.17 -minify_html==0.15.0 -pandas==2.2.2 -playwright==1.43.0 -pydantic==2.8.2 -Requests==2.32.3 -semchunk==2.2.0 -tiktoken==0.7.0 -tqdm==4.66.4 -undetected_playwright==0.3.0 +langchain>=0.2.10 +langchain-google-genai>=1.0.7 +langchain-google-vertexai +langchain-openai>=0.1.17 +langchain-groq>=0.1.3 +langchain-aws>=0.1.3 +langchain-anthropic>=0.1.11 +html2text>=2024.2.26 +faiss-cpu>=1.8.0 +beautifulsoup4>=4.12.3 +pandas>=2.2.2 +python-dotenv>=1.0.1 +tiktoken>=0.7 +tqdm>=4.66.4 +graphviz>=0.20.3 +minify-html>=0.15.0 +free-proxy>=1.1.1 +playwright>=1.43.0 +google>=3.0.0 +undetected-playwright>=0.3.0 +semchunk>=1.0.1 +html2text>=2024.2.26 +langchain-fireworks>=0.1.3