Fix: Clean up requirements.txt to resolve build conflicts

.github/workflows/secret-tester.yml

@@ -1,20 +1,34 @@
-name: "Titkok Tesztelése"
+name: "Weboldal Indexelő Futtatása"
+
 on:
   workflow_dispatch:
+
 jobs:
-  test-secrets-job:
+  build-and-index:
     runs-on: ubuntu-latest
     steps:
       - name: "Repository letöltése"
         uses: actions/checkout@v4
-      - name: "Python beállítása"
+
+      - name: "Python 3.10 beállítása és gyorsítótár használata"
         uses: actions/setup-python@v5
         with:
           python-version: '3.10'
-      - name: "Titkok ellenőrzése a Python szkripttel"
-        run: python test_secrets.py
+          cache: 'pip'
+
+      - name: "Build tools telepítése (a C alapú csomagokhoz)"
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential python3-dev
+
+      - name: "Függőségek telepítése"
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      
+      - name: "Indexer script futtatása"
+        run: python web_indexer_universal_v7.py
         env:
-          ES_API_KEY_FROM_WORKFLOW: ${{ secrets.ES_API_KEY }}
-          ES_CLOUD_ID_FROM_WORKFLOW: ${{ secrets.ES_CLOUD_ID }}
-          PAT_FROM_WORKFLOW: ${{ secrets.PAT }}
-          TOGETHER_API_KEY_FROM_WORKFLOW: ${{ secrets.TOGETHER_API_KEY }}
+          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
+          ES_API_KEY: ${{ secrets.ES_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}

requirements.txt

@@ -1,249 +1,9 @@
-absl-py
-aiohappyeyeballs
-aiohttp
-aiolimiter
-aiosignal
-albucore
-albumentations
-altair
-annotated-types
-anyio
-astor
-astunparse
-attrs
-banks
-beautifulsoup4
-blinker
-blis
-boto3
-botocore
-cachelib
-cachetools
-catalogue
-certifi
-cffi
-charset-normalizer
-click
-cloudpathlib
-colorama
-confection
-contourpy
-cryptography
-cycler
-cymem
-Cython
-dataclasses-json
-decorator
-deep-translator
-Deprecated
-dirtyjson
-docopt
-easyocr
-elastic-transport
 elasticsearch
-et_xmlfile
-eval_type_backport
-filelock
-filetype
-fire
-Flask
-Flask-Cors
-Flask-Session
-flatbuffers
-fonttools
-frozenlist
-fsspec
-gast
-gitdb
-GitPython
-google-ai-generativelanguage
-google-api-core
-google-api-python-client
-google-auth
-google-auth-httplib2
-google-cloud-core
-google-cloud-speech
-google-cloud-storage
-google-crc32c
-google-generativeai
-google-pasta
-google-resumable-media
-googleapis-common-protos
-greenlet
-griffe
-grpcio
-grpcio-status
-h11
-h5py
-httpcore
-httplib2
-httpx
-httpx-sse
-huggingface-hub
-ibm-cloud-sdk-core
-ibm-cos-sdk
-ibm-cos-sdk-core
-ibm-cos-sdk-s3transfer
-ibm-generative-ai
-ibm-watson
-idna
-imageio
-itsdangerous
-Jinja2
-jmespath
-joblib
-jsonschema
-jsonschema-specifications
-keras
-keybert
-kiwisolver
-langcodes
-language_data
-lazy_loader
-Levenshtein
-libclang
-llama-index-core
-llama-index-embeddings-huggingface
-lmdb
-lxml
-marisa-trie
-Markdown
-markdown-it-py
-MarkupSafe
-marshmallow
-matplotlib
-mdurl
-ml_dtypes
-mosestokenizer
-mpmath
-msgspec
-multidict
-murmurhash
-mypy-extensions
-namex
-narwhals
-nest-asyncio
-networkx
-ninja
-nltk
-numpy
-opencv-contrib-python
-opencv-python
-opencv-python-headless
-openfile
-openpyxl
-opt-einsum
-optree
-outcome
-packaging
-paddleocr
-paddlepaddle
-pandas
-pdf2image
-pdfminer.six
-pdfplumber
-pillow
-platformdirs
-preshed
-propcache
-proto-plus
-protobuf
-pyarrow
-pyasn1
-pyasn1_modules
-pyclipper
-pycparser
-pydantic
-pydantic_core
-pydeck
-pydub
-Pygments
-PyJWT
-PyMuPDF
-pyparsing
-pypdfium2
-PySocks
-pyspellchecker
-pytesseract
-python-bidi
-python-dateutil
-python-docx
-python-dotenv
-python-Levenshtein
-pytz
-PyYAML
-RapidFuzz
-redis
-referencing
-regex
 requests
-rich
-rpds-py
-rsa
-s3transfer
-sacremoses
-safetensors
-scikit-image
-scikit-learn
-scipy
-selenium
-sentence-transformers
-sentencepiece
-setuptools
-shapely
-shellingham
-simsimd
-six
-smart-open
-smmap
-sniffio
-sortedcontainers
-soupsieve
-spacy
-spacy-legacy
-spacy-loggers
-SQLAlchemy
-srsly
-streamlit
-stringzilla
-sympy
-tabulate
-tenacity
-tensorboard
-tensorboard-data-server
-tensorflow
-termcolor
-tf_keras
-thinc
-threadpoolctl
-tifffile
-tika
-tiktoken
-together
-tokenizers
-toml
-toolwrapper
+beautifulsoup4
 torch
-torchaudio
-torchvision
-tornado
-tqdm
-transformers
-trio
-trio-websocket
-typer
-typing-inspect
-typing_extensions
-tzdata
-uctools
-uritemplate
-urllib3
-wasabi
-watchdog
-weasel
-websocket-client
-Werkzeug
-wheel
-wrapt
-wsproto
-yarl
+together
+python-dotenv
+tiktoken
+nltk
+sentence-transformers

requirementsS.txt

@@ -0,0 +1,249 @@
+absl-py
+aiohappyeyeballs
+aiohttp
+aiolimiter
+aiosignal
+albucore
+albumentations
+altair
+annotated-types
+anyio
+astor
+astunparse
+attrs
+banks
+beautifulsoup4
+blinker
+blis
+boto3
+botocore
+cachelib
+cachetools
+catalogue
+certifi
+cffi
+charset-normalizer
+click
+cloudpathlib
+colorama
+confection
+contourpy
+cryptography
+cycler
+cymem
+Cython
+dataclasses-json
+decorator
+deep-translator
+Deprecated
+dirtyjson
+docopt
+easyocr
+elastic-transport
+elasticsearch
+et_xmlfile
+eval_type_backport
+filelock
+filetype
+fire
+Flask
+Flask-Cors
+Flask-Session
+flatbuffers
+fonttools
+frozenlist
+fsspec
+gast
+gitdb
+GitPython
+google-ai-generativelanguage
+google-api-core
+google-api-python-client
+google-auth
+google-auth-httplib2
+google-cloud-core
+google-cloud-speech
+google-cloud-storage
+google-crc32c
+google-generativeai
+google-pasta
+google-resumable-media
+googleapis-common-protos
+greenlet
+griffe
+grpcio
+grpcio-status
+h11
+h5py
+httpcore
+httplib2
+httpx
+httpx-sse
+huggingface-hub
+ibm-cloud-sdk-core
+ibm-cos-sdk
+ibm-cos-sdk-core
+ibm-cos-sdk-s3transfer
+ibm-generative-ai
+ibm-watson
+idna
+imageio
+itsdangerous
+Jinja2
+jmespath
+joblib
+jsonschema
+jsonschema-specifications
+keras
+keybert
+kiwisolver
+langcodes
+language_data
+lazy_loader
+Levenshtein
+libclang
+llama-index-core
+llama-index-embeddings-huggingface
+lmdb
+lxml
+marisa-trie
+Markdown
+markdown-it-py
+MarkupSafe
+marshmallow
+matplotlib
+mdurl
+ml_dtypes
+mosestokenizer
+mpmath
+msgspec
+multidict
+murmurhash
+mypy-extensions
+namex
+narwhals
+nest-asyncio
+networkx
+ninja
+nltk
+numpy
+opencv-contrib-python
+opencv-python
+opencv-python-headless
+openfile
+openpyxl
+opt-einsum
+optree
+outcome
+packaging
+paddleocr
+paddlepaddle
+pandas
+pdf2image
+pdfminer.six
+pdfplumber
+pillow
+platformdirs
+preshed
+propcache
+proto-plus
+protobuf
+pyarrow
+pyasn1
+pyasn1_modules
+pyclipper
+pycparser
+pydantic
+pydantic_core
+pydeck
+pydub
+Pygments
+PyJWT
+PyMuPDF
+pyparsing
+pypdfium2
+PySocks
+pyspellchecker
+pytesseract
+python-bidi
+python-dateutil
+python-docx
+python-dotenv
+python-Levenshtein
+pytz
+PyYAML
+RapidFuzz
+redis
+referencing
+regex
+requests
+rich
+rpds-py
+rsa
+s3transfer
+sacremoses
+safetensors
+scikit-image
+scikit-learn
+scipy
+selenium
+sentence-transformers
+sentencepiece
+setuptools
+shapely
+shellingham
+simsimd
+six
+smart-open
+smmap
+sniffio
+sortedcontainers
+soupsieve
+spacy
+spacy-legacy
+spacy-loggers
+SQLAlchemy
+srsly
+streamlit
+stringzilla
+sympy
+tabulate
+tenacity
+tensorboard
+tensorboard-data-server
+tensorflow
+termcolor
+tf_keras
+thinc
+threadpoolctl
+tifffile
+tika
+tiktoken
+together
+tokenizers
+toml
+toolwrapper
+torch
+torchaudio
+torchvision
+tornado
+tqdm
+transformers
+trio
+trio-websocket
+typer
+typing-inspect
+typing_extensions
+tzdata
+uctools
+uritemplate
+urllib3
+wasabi
+watchdog
+weasel
+websocket-client
+Werkzeug
+wheel
+wrapt
+wsproto
+yarl