initial

.envrc

@@ -0,0 +1 @@
+source .venv/bin/activate

.gitignore

@@ -0,0 +1,164 @@
+data/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

pyproject.toml

@@ -0,0 +1,22 @@
+[project]
+name = "planning-ai"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10,<3.11"
+dependencies = [
+    "langchain-core>=0.2.38",
+    "langchain-community>=0.2.16",
+    "langchain-unstructured>=0.1.2",
+    "transformers>=4.44.2",
+    "torch>=2.4.1",
+    "accelerate>=0.34.0",
+    "pillow>=10.4.0",
+    "flash-attn>=2.6.3",
+]
+
+[tool.uv]
+dev-dependencies = [
+    "ipdb>=0.13.13",
+    "ipython>=8.27.0",
+]

src/planning_ai/__init__.py

@@ -0,0 +1,2 @@
+def hello() -> str:
+    return "Hello from planning-ai!"

src/planning_ai/loaders.py

@@ -0,0 +1,4 @@
+from langchain_unstructured import UnstructuredLoader
+
+loader = UnstructuredLoader("./data/raw/pdfs/57693-94 Response Form.pdf")
+loader.load()

src/planning_ai/phi.py

@@ -0,0 +1,53 @@
+import requests
+from PIL import Image
+from transformers import AutoModelForCausalLM, AutoProcessor
+
+model_id = "microsoft/Phi-3.5-vision-instruct"
+
+# Note: set _attn_implementation='eager' if you don't have flash_attn installed
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="cuda",
+    trust_remote_code=True,
+    torch_dtype="auto",
+    _attn_implementation="flash_attention_2",
+)
+
+# for best performance, use num_crops=4 for multi-frame, num_crops=16 for single-frame.
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True, num_crops=4)
+
+images = []
+placeholder = ""
+
+# Note: if OOM, you might consider reduce number of frames in this example.
+path = "./data/raw/2024-09-05_10-46.png"
+images.append(Image.open(requests.get(path, stream=True).raw))
+placeholder += f"<|image_1|>\n"
+
+messages = [
+    {"role": "user", "content": placeholder + "Summarize the deck of slides."},
+]
+
+prompt = processor.tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+
+inputs = processor(prompt, images, return_tensors="pt").to("cuda:0")
+
+generation_args = {
+    "max_new_tokens": 1000,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+generate_ids = model.generate(
+    **inputs, eos_token_id=processor.tokenizer.eos_token_id, **generation_args
+)
+
+# remove input tokens
+generate_ids = generate_ids[:, inputs["input_ids"].shape[1] :]
+response = processor.batch_decode(
+    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)[0]
+
+print(response)