Merge pull request #107 from neo4j-labs/STAGING

Staging to MAIN

Author: kartikpersistent

.gitignore

@@ -159,4 +159,7 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 .vscode/launch.json
-temp.pdf
+temp.pdf
+google-cloud-sdk
+google-cloud-cli-469.0.0-linux-x86_64.tar.gz
+/data/llm-experiments-387609-c73d512ca3b1.json

README.md

@@ -114,7 +114,7 @@ KNN_MIN_SCORE = ""\
 https://github.com/neo4j-labs/llm-graph-builder/assets/121786590/b725a503-6ade-46d2-9e70-61d57443c311
 
 ## Links
- The Public [ Google cloud Run URL](https://frontend-dcavk67s4a-uc.a.run.app).
+ The Public [ Google cloud Run URL](https://staging-frontend-dcavk67s4a-uc.a.run.app/).
  [Workspace URL](https://workspace-preview.neo4j.io/workspace)
 
 

backend/example.env

@@ -3,8 +3,13 @@ DIFFBOT_API_KEY = ""
 NEO4J_URI = ""
 NEO4J_USERNAME = ""
 NEO4J_PASSWORD = ""
+NEO4J_DATABASE = ""
 AWS_ACCESS_KEY_ID =  ""
 AWS_SECRET_ACCESS_KEY = ""
 EMBEDDING_MODEL = ""
 IS_EMBEDDING = "TRUE"
-KNN_MIN_SCORE = ""
+KNN_MIN_SCORE = ""
+LANGCHAIN_API_KEY = ""
+LANGCHAIN_PROJECT = ""
+LANGCHAIN_TRACING_V2 = ""
+LANGCHAIN_ENDPOINT = ""

backend/requirements.txt

@@ -1,184 +1,164 @@
-aiohttp==3.9.1
+aiohttp==3.9.3
 aiosignal==1.3.1
 annotated-types==0.6.0
 antlr4-python3-runtime==4.9.3
-anyio==4.2.0
-asttokens==2.0.5
+anyio==4.3.0
 async-timeout==4.0.3
+asyncio==3.4.3
 attrs==23.2.0
-backcall==0.2.0
 backoff==2.2.1
-beautifulsoup4==4.12.2
-boto3==1.34.41
-botocore==1.34.41
-certifi==2023.11.17
+beautifulsoup4==4.12.3
+boto3
+botocore
+cachetools==5.3.3
+certifi==2024.2.2
 cffi==1.16.0
 chardet==5.2.0
 charset-normalizer==3.3.2
 click==8.1.7
-colorama==0.4.6
 coloredlogs==15.0.1
-comm==0.1.2
 contourpy==1.2.0
 cryptography==42.0.2
 cycler==0.12.1
-dataclasses-json==0.6.3
+dataclasses-json==0.6.4
 dataclasses-json-speakeasy==0.5.11
-debugpy==1.6.7
-decorator==5.1.1
 Deprecated==1.2.14
 distro==1.9.0
+docstring_parser==0.16
 effdet==0.4.1
 emoji==2.10.1
-exceptiongroup==1.0.4
-executing==0.8.3
-fastapi==0.109.0
+exceptiongroup==1.2.0
+fastapi==0.110.0
 fastapi-health==0.4.0
 filelock==3.13.1
 filetype==1.2.0
 flatbuffers==23.5.26
-fonttools==4.48.1
+fonttools==4.49.0
 frozenlist==1.4.1
 fsspec==2024.2.0
+google-api-core==2.18.0
+google-auth==2.29.0
+google-cloud-aiplatform==1.45.0
+google-cloud-bigquery==3.19.0
+google-cloud-core==2.4.1
+google-cloud-resource-manager==1.12.3
+google-cloud-storage==2.16.0
+google-crc32c==1.5.0
+google-resumable-media==2.7.0
+googleapis-common-protos==1.63.0
 greenlet==3.0.3
+grpc-google-iam-v1==0.13.0
+grpcio==1.62.1
+google-ai-generativelanguage
+grpcio-status==1.62.1
 h11==0.14.0
-httpcore==1.0.2
-httpx==0.26.0
+httpcore==1.0.4
+httpx==0.27.0
 huggingface-hub==0.20.3
 humanfriendly==10.0
 idna==3.6
-importlib-metadata==7.0.1
+importlib-resources==6.1.1
+install==1.3.5
 iopath==0.1.10
-ipykernel==6.25.0
-ipython==8.15.0
-jedi==0.18.1
 Jinja2==3.1.3
 jmespath==1.0.1
 joblib==1.3.2
 jsonpatch==1.33
 jsonpath-python==1.0.6
 jsonpointer==2.4
-jupyter_client==8.6.0
-jupyter_core==5.5.0
 kiwisolver==1.4.5
-langchain==0.1.1
-langchain-community==0.0.20
-langchain-core==0.1.23
-langchain-experimental==0.0.49
-langchain-openai==0.0.2.post1
+langchain
+langchain-google-genai
+langchain-community
+langchain-core
+langchain-experimental
+langchain-google-vertexai
+langchain-openai
+langchain-text-splitters==0.0.1
 langdetect==1.0.9
-langsmith==0.0.87
+langsmith==0.1.31
 layoutparser==0.3.4
 lxml==5.1.0
 MarkupSafe==2.1.5
 marshmallow==3.20.2
-matplotlib==3.8.2
-matplotlib-inline==0.1.6
+matplotlib==3.7.2
 mpmath==1.3.0
-multidict==6.0.4
+multidict==6.0.5
 mypy-extensions==1.0.0
-neo4j==5.16.0
-nest-asyncio==1.5.6
+neo4j==5.18.0
 networkx==3.2.1
 nltk==3.8.1
-numpy==1.26.3
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.19.3
-nvidia-nvjitlink-cu12==12.3.101
-nvidia-nvtx-cu12==12.1.105
+numpy==1.26.4
 omegaconf==2.3.0
 onnx==1.15.0
 onnxruntime==1.15.1
-openai==1.7.1
-opencv-python==4.9.0.80
-opencv-python-headless==4.9.0.80
+openai==1.14.2
+opencv-python==4.8.0.76
+orjson==3.9.15
 packaging==23.2
 pandas==2.2.0
-parso==0.8.3
 pdf2image==1.17.0
 pdfminer.six==20221105
 pdfplumber==0.10.4
-pexpect==4.9.0
-pickleshare==0.7.5
-pikepdf==8.12.0
+pikepdf==8.11.0
 pillow==10.2.0
 pillow_heif==0.15.0
-platformdirs==3.10.0
 portalocker==2.8.2
-prompt-toolkit==3.0.43
-protobuf==4.25.2
-psutil==5.9.0
-ptyprocess==0.7.0
-pure-eval==0.2.2
+proto-plus==1.23.0
+protobuf==4.23.4
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
 pycocotools==2.0.7
 pycparser==2.21
-pydantic==2.5.3
-pydantic_core==2.14.6
-Pygments==2.15.1
-pyparsing==3.1.1
-pypdf==3.17.4
+pydantic==2.6.4
+pydantic_core==2.16.3
+pyparsing==3.0.9
+pypdf==4.0.1
 pypdfium2==4.27.0
 pytesseract==0.3.10
-python-certifi-win32==1.6.1
 python-dateutil==2.8.2
-python-dotenv==1.0.0
+python-dotenv==1.0.1
 python-iso639==2024.2.7
 python-magic==0.4.27
-python-multipart==0.0.6
-pytz==2023.3.post1
+python-multipart==0.0.9
+pytube==15.0.0
+pytz==2024.1
 PyYAML==6.0.1
-pyzmq==25.1.0
 rapidfuzz==3.6.1
 regex==2023.12.25
-requests==2.31.0
-s3transfer==0.10.0
-safetensors==0.4.2
-scipy==1.12.0
-setuptools-scm==8.0.4
+requests
+rsa==4.9
+s3transfer==0.10.1
+safetensors==0.3.2
+scipy==1.10.1
+shapely==2.0.3
 six==1.16.0
-sniffio==1.3.0
+sniffio==1.3.1
 soupsieve==2.5
-SQLAlchemy==2.0.25
-stack-data==0.2.0
-starlette==0.35.1
+SQLAlchemy==2.0.28
+starlette==0.36.3
 sympy==1.12
 tabulate==0.9.0
 tenacity==8.2.3
-tiktoken==0.5.2
+tiktoken==0.6.0
 timm==0.9.12
 tokenizers==0.15.2
-tomli==2.0.1
-torch==2.2.0
-torchvision==0.17.0
-tornado==6.3.3
-tqdm==4.66.1
-traitlets==5.7.1
-transformers==4.37.2
+tqdm==4.66.2
+transformers==4.37.1
 triton==2.2.0
+types-protobuf
+types-requests
 typing-inspect==0.9.0
 typing_extensions==4.9.0
 tzdata==2024.1
-unstructured==0.12.4
-unstructured-client==0.18.0
-unstructured-inference==0.7.23
-unstructured.pytesseract==0.3.12
-urllib3==2.0.7
-uvicorn==0.26.0
-wcwidth==0.2.5
+unstructured
+unstructured-client
+unstructured-inference
+unstructured.pytesseract
+urllib3
+uvicorn==0.29.0
 wikipedia==1.4.0
 wrapt==1.16.0
 yarl==1.9.4
+youtube-transcript-api==0.6.2
 zipp==3.17.0
-poppler-utils
-pytesseract
-pdf2image
-youtube-transcript-api
-pytube