Feature/SOF-7804 Update: rename exabyte -> mat3ra #266
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
📝 WalkthroughWalkthroughUpdated examples, scripts, and utilities to import endpoint clients from Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
other/materialsproject/api_interoperability_showcase.ipynb (1)
97-100: Replaceexabyte-api-clientwithmat3ra-api-clientin the JupyterLite install cell.The notebook installs
exabyte-api-clientin the emscripten block but imports frommat3ra.api_client. Sincemat3ra-api-examplesis installed withdeps=False, themat3ra.api_clientmodule won't be available, causing an import failure in JupyterLite.Fix
- await micropip.install("exabyte-api-client") + await micropip.install("mat3ra-api-client")
🤖 Fix all issues with AI agents
In
`@examples/reproducing_publications/band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb`:
- Line 394: The notebook mixes root-level and submodule imports for API endpoint
classes (e.g., BankWorkflowEndpoints, WorkflowEndpoints, ProjectEndpoints);
standardize them by replacing any imports from mat3ra.api_client that reference
endpoint classes with explicit imports from their endpoints submodules (e.g.,
mat3ra.api_client.endpoints.*) so all endpoint classes (BankWorkflowEndpoints,
WorkflowEndpoints, ProjectEndpoints, MaterialEndpoints, JobEndpoints,
PropertiesEndpoints, etc.) are imported via their endpoints.* modules for
consistency and compatibility.
In
`@examples/reproducing_publications/band_structure_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb`:
- Line 647: Import uses a top-level re-export; replace it with the canonical
submodule path to match the rest of the notebook. Change the import statement
that currently reads "from mat3ra.api_client import ProjectEndpoints" to "from
mat3ra.api_client.endpoints.projects import ProjectEndpoints" so the
ProjectEndpoints symbol is imported from mat3ra.api_client.endpoints.projects
and remains consistent with other cells.
In `@examples/workflow/qe_scf_calculation.ipynb`:
- Around line 148-150: The imports for WorkflowEndpoints, MaterialEndpoints, and
JobEndpoints are using the wrong module path; replace the current
mat3ra.api_client.endpoints imports with the correct
exabyte_api_client.endpoints imports so that WorkflowEndpoints,
MaterialEndpoints, and JobEndpoints are imported from
exabyte_api_client.endpoints instead of mat3ra.api_client.endpoints.
🧹 Nitpick comments (3)
utils/material.py (1)
14-29: Consider updating docstring references to the new package name.The docstring at line 20 still references "Exabyte API Client". For consistency with the namespace migration, consider updating to "Mat3ra API Client". Similarly, line 162 references "Exabyte platform".
utils/api.py (1)
14-27: Consider updating docstring references.Multiple docstrings in this file still reference "Exabyte API Client" (lines 20, 48, 64). For consistency with the namespace migration, consider updating these to "Mat3ra API Client".
pyproject.toml (1)
11-11: Confirm the VCS dependency strategy format3ra-api-client.
Pinned git URLs can be fine, but they require VCS-capable installers and can complicate reproducible builds. If a tagged release exists, consider pinning to a versioned release instead; otherwise, please confirm the commit is stable and intended for long-term use.
| "outputs": [], | ||
| "source": [ | ||
| "from exabyte_api_client import BankWorkflowEndpoints, WorkflowEndpoints\n", | ||
| "from mat3ra.api_client import BankWorkflowEndpoints, WorkflowEndpoints\n", |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, let's check the notebook file to see the actual imports at those lines
cd examples/reproducing_publications && wc -l band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynbRepository: Exabyte-io/api-examples
Length of output: 190
🏁 Script executed:
# Let's find the mat3ra package structure
find . -type d -name "mat3ra" | head -5Repository: Exabyte-io/api-examples
Length of output: 49
🏁 Script executed:
# Search for the mat3ra.api_client package __init__.py to check for re-exports
find . -path "*/mat3ra/api_client/__init__.py" 2>/dev/nullRepository: Exabyte-io/api-examples
Length of output: 49
🏁 Script executed:
# Let's also check what import patterns are used in the notebook
rg "from mat3ra" examples/reproducing_publications/band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb -o | head -20Repository: Exabyte-io/api-examples
Length of output: 234
🏁 Script executed:
# List files to understand the repo structure
git ls-files | grep -E "(mat3ra|\.ipynb)" | head -30Repository: Exabyte-io/api-examples
Length of output: 1746
🏁 Script executed:
# Find the notebook file
fd "band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb"Repository: Exabyte-io/api-examples
Length of output: 167
🏁 Script executed:
# Check if mat3ra is a local package or external dependency
find . -type f -name "__init__.py" | grep mat3raRepository: Exabyte-io/api-examples
Length of output: 49
🏁 Script executed:
# Look for imports in setup.py or requirements to understand mat3ra
fd -e txt -e cfg -e toml -e lock | xargs grep -l "mat3ra" 2>/dev/null | head -5Repository: Exabyte-io/api-examples
Length of output: 81
🏁 Script executed:
# Check pyproject.toml for mat3ra dependency
cat pyproject.toml | grep -A 5 -B 5 "mat3ra"Repository: Exabyte-io/api-examples
Length of output: 991
🏁 Script executed:
# Read the notebook file and extract cells around lines 394 and 641
# Notebooks are JSON, so we need to parse them carefully
python <<'EOF'
import json
import sys
# Read the notebook
with open('examples/reproducing_publications/band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb', 'r') as f:
nb = json.load(f)
# Count lines to find which cells correspond to lines 394 and 641
# Jupyter notebooks list cells, we need to find imports
line_count = 0
for i, cell in enumerate(nb['cells']):
if cell['cell_type'] == 'code':
source = ''.join(cell.get('source', []))
cell_lines = len(source.split('\n'))
# Check if this cell contains imports from mat3ra
if 'from mat3ra' in source or 'import mat3ra' in source:
print(f"\n=== Cell {i} (lines {line_count}-{line_count + cell_lines}) ===")
print(source)
line_count += cell_lines
EOFRepository: Exabyte-io/api-examples
Length of output: 4982
🏁 Script executed:
# Now let's check if mat3ra-api-client is available and what it re-exports
# First, let's see if there's any local version or if we can inspect the dependency
python <<'EOF'
# Try to get more info about the mat3ra-api-client package from pyproject.toml
import re
with open('pyproject.toml', 'r') as f:
content = f.read()
# Find the mat3ra-api-client dependency line
match = re.search(r'mat3ra-api-client.*', content)
if match:
print("Found dependency:")
print(match.group())
EOFRepository: Exabyte-io/api-examples
Length of output: 196
🌐 Web query:
mat3ra-api-client BankWorkflowEndpoints WorkflowEndpoints re-export root package __init__.py
💡 Result:
You can re-export those endpoint classes from the package root by importing them into the package init.py and declaring all. Example (put in mat3ra_api_client/init.py):
from .bank_workflow import BankWorkflowEndpoints
from .workflow import WorkflowEndpoints
all = ["BankWorkflowEndpoints", "WorkflowEndpoints"]
Notes:
- Use explicit imports (not wildcard) so tools and linters know the public API. [1][2]
- If you need to preserve backwards-compatibility when renaming, import using "as" and keep the old name in all. [3]
Sources:
[1] Correct way to re-export modules from init.py (StackOverflow).
[2] Best practices for re-exporting via all (pythontutorials.net).
[3] Discussion about explicit re-exports in init.py (mypy / GitHub issue).
🌐 Web query:
site:github.com Exabyte-io api-client endpoints BankWorkflowEndpoints
💡 Result:
I couldn't find any GitHub file or symbol named "BankWorkflowEndpoints" in the Exabyte-io (Exabyte-io / Mat3ra) repositories. I searched Exabyte's GitHub org and their API client/docs but found no match for that exact identifier. Sources: Exabyte GitHub org and Mat3ra/Exabyte API client docs. [1][2]
Would you like me to:
- search the Exabyte repo contents for related names (e.g., "bank workflow", "BankWorkflow", "endpoints")? or
- search other organizations/repos for "BankWorkflowEndpoints"?
Sources:
[1] Exabyte-io — GitHub organization page (repo list).
[2] Mat3ra (Exabyte) REST API / API client documentation.
🏁 Script executed:
# Let's check the actual line numbers in the notebook more carefully
python <<'EOF'
import json
with open('examples/reproducing_publications/band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb', 'r') as f:
nb = json.load(f)
# Count actual line numbers across all content
line_count = 0
for i, cell in enumerate(nb['cells']):
if cell['cell_type'] == 'code':
source = ''.join(cell.get('source', []))
lines = source.split('\n')
for j, line in enumerate(lines):
line_count += 1
if 'BankWorkflowEndpoints' in line or 'WorkflowEndpoints' in line or 'ProjectEndpoints' in line:
print(f"Line {line_count} (Cell {i}): {line.strip()}")
EOFRepository: Exabyte-io/api-examples
Length of output: 615
🏁 Script executed:
# Let's check the imported package's actual structure
# The package is at a specific commit, let's see if we can inspect what endpoints are available
python <<'EOF'
import json
# Parse the notebook to see all imports of mat3ra.api_client
with open('examples/reproducing_publications/band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb', 'r') as f:
nb = json.load(f)
root_imports = {}
endpoint_imports = {}
for cell in nb['cells']:
if cell['cell_type'] == 'code':
source = ''.join(cell.get('source', []))
# Find all from mat3ra imports
for line in source.split('\n'):
line = line.strip()
if line.startswith('from mat3ra.api_client import'):
# Root level import
imported = line.replace('from mat3ra.api_client import ', '').strip()
root_imports[imported] = root_imports.get(imported, 0) + 1
elif 'from mat3ra.api_client.endpoints' in line:
# Endpoints import
endpoint_imports[line] = endpoint_imports.get(line, 0) + 1
print("=== Root-level imports (from mat3ra.api_client) ===")
for imp, count in sorted(root_imports.items()):
print(f"{imp}: {count} time(s)")
print("\n=== Endpoints imports (from mat3ra.api_client.endpoints.*) ===")
for imp, count in sorted(endpoint_imports.items()):
print(f"{imp}: {count} time(s)")
EOFRepository: Exabyte-io/api-examples
Length of output: 569
Inconsistent import patterns for API endpoints—standardize to endpoints.* imports.
The notebook mixes root-level and endpoint-specific imports:
- Line 129 (Cell 27):
from mat3ra.api_client import BankWorkflowEndpoints, WorkflowEndpoints - Line 196 (Cell 47):
from mat3ra.api_client import ProjectEndpoints - Line 176 (Cell 43):
from mat3ra.api_client.endpoints.projects import ProjectEndpoints✓
The majority of other endpoint classes (MaterialEndpoints, JobEndpoints, PropertiesEndpoints) use the endpoints.* path. ProjectEndpoints itself is imported both ways, creating inconsistency. To ensure compatibility and consistency, standardize all endpoint imports to use the explicit endpoints.* submodules:
♻️ Suggested fix
-from mat3ra.api_client import BankWorkflowEndpoints, WorkflowEndpoints
+from mat3ra.api_client.endpoints.bank_workflows import BankWorkflowEndpoints
+from mat3ra.api_client.endpoints.workflows import WorkflowEndpoints-from mat3ra.api_client import ProjectEndpoints
+from mat3ra.api_client.endpoints.projects import ProjectEndpoints📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "from mat3ra.api_client import BankWorkflowEndpoints, WorkflowEndpoints\n", | |
| "from mat3ra.api_client.endpoints.bank_workflows import BankWorkflowEndpoints\n", | |
| "from mat3ra.api_client.endpoints.workflows import WorkflowEndpoints\n", |
🤖 Prompt for AI Agents
In
`@examples/reproducing_publications/band_gaps_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb`
at line 394, The notebook mixes root-level and submodule imports for API
endpoint classes (e.g., BankWorkflowEndpoints, WorkflowEndpoints,
ProjectEndpoints); standardize them by replacing any imports from
mat3ra.api_client that reference endpoint classes with explicit imports from
their endpoints submodules (e.g., mat3ra.api_client.endpoints.*) so all endpoint
classes (BankWorkflowEndpoints, WorkflowEndpoints, ProjectEndpoints,
MaterialEndpoints, JobEndpoints, PropertiesEndpoints, etc.) are imported via
their endpoints.* modules for consistency and compatibility.
| "outputs": [], | ||
| "source": [ | ||
| "from exabyte_api_client import ProjectEndpoints\n", | ||
| "from mat3ra.api_client import ProjectEndpoints\n", |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# First, check if the notebook file exists and read it
if [ -f "examples/reproducing_publications/band_structure_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb" ]; then
echo "=== File exists ==="
# Extract line 647 context from notebook
python3 << 'EOF'
import json
import sys
with open("examples/reproducing_publications/band_structure_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb", 'r') as f:
notebook = json.load(f)
# Search for the import statement in cells
for i, cell in enumerate(notebook.get('cells', [])):
if cell.get('cell_type') == 'code':
source = ''.join(cell.get('source', []))
if 'ProjectEndpoints' in source:
print(f"\n=== Cell {i} ===")
print(source)
print("---")
if 'from mat3ra.api_client' in source:
print(f"\n=== Cell {i} (mat3ra import) ===")
print(source)
print("---")
EOF
else
echo "File not found"
fiRepository: Exabyte-io/api-examples
Length of output: 4543
🏁 Script executed:
#!/bin/bash
# Search for mat3ra package in the codebase to understand structure
echo "=== Looking for mat3ra package files ==="
find . -type f -path "*/mat3ra/*__init__.py" 2>/dev/null | head -20
find . -type f -name "*endpoints*" -o -name "*ProjectEndpoints*" 2>/dev/null | head -20Repository: Exabyte-io/api-examples
Length of output: 107
🏁 Script executed:
#!/bin/bash
# Search for ProjectEndpoints references and imports in codebase
echo "=== Searching for ProjectEndpoints usage ==="
rg "ProjectEndpoints" -A 2 -B 2 --max-count 30Repository: Exabyte-io/api-examples
Length of output: 13000
Align ProjectEndpoints import with the submodule path used elsewhere in the file.
This cell uses from mat3ra.api_client import ProjectEndpoints while Cell 43 in the same notebook imports from mat3ra.api_client.endpoints.projects. The full submodule path is also the standard across the entire codebase, providing clearer intent and avoiding reliance on potentially inconsistent top-level re-exports.
♻️ Suggested change
-from mat3ra.api_client import ProjectEndpoints
+from mat3ra.api_client.endpoints.projects import ProjectEndpoints📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "from mat3ra.api_client import ProjectEndpoints\n", | |
| "from mat3ra.api_client.endpoints.projects import ProjectEndpoints\n", |
🤖 Prompt for AI Agents
In
`@examples/reproducing_publications/band_structure_for_interface_bilayer_twisted_molybdenum_disulfide.ipynb`
at line 647, Import uses a top-level re-export; replace it with the canonical
submodule path to match the rest of the notebook. Change the import statement
that currently reads "from mat3ra.api_client import ProjectEndpoints" to "from
mat3ra.api_client.endpoints.projects import ProjectEndpoints" so the
ProjectEndpoints symbol is imported from mat3ra.api_client.endpoints.projects
and remains consistent with other cells.
| "from mat3ra.api_client.endpoints.workflows import WorkflowEndpoints\n", | ||
| "from mat3ra.api_client.endpoints.materials import MaterialEndpoints\n", | ||
| "from mat3ra.api_client.endpoints.jobs import JobEndpoints" |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# Find dependency/requirements files to identify pinned mat3ra-api-client version
find . -type f \( -name "requirements*.txt" -o -name "setup.py" -o -name "pyproject.toml" -o -name "setup.cfg" -o -name "Pipfile" \) | head -20Repository: Exabyte-io/api-examples
Length of output: 190
🌐 Web query:
mat3ra-api-client WorkflowEndpoints MaterialEndpoints JobEndpoints endpoints documentation
💡 Result:
You can find the Mat3ra (Exabyte) REST API endpoints and the Python API-client docs/examples here:
- API Endpoints overview & list (endpoints documentation). [1]
- API client (Python) page describing the exabyte/mat3ra API client. [2]
- Example notebook showing use of JobEndpoints, MaterialEndpoints, WorkflowEndpoints (imports and example usage). [3]
- Material endpoint example (listing materials by formula). [4]
Quick usage (from the examples): import and initialize the endpoint classes from the Python client:
from exabyte_api_client.endpoints.jobs import JobEndpoints
from exabyte_api_client.endpoints.materials import MaterialEndpoints
from exabyte_api_client.endpoints.workflows import WorkflowEndpoints
job_endpoints = JobEndpoints(*ENDPOINT_ARGS)
material_endpoints = MaterialEndpoints(*ENDPOINT_ARGS)
workflow_endpoints = WorkflowEndpoints(*ENDPOINT_ARGS)
References:
[1] Mat3ra — Endpoints (REST API).
[2] Mat3ra — API client (Python).
[3] Mat3ra — Create and submit job (API examples, shows Job/Material/Workflow endpoints).
[4] Mat3ra — Get materials by formula (API examples).
Fix incorrect endpoint import paths.
The imports use mat3ra.api_client.endpoints but the official mat3ra-api-client package exports these endpoints from exabyte_api_client.endpoints. Update lines 148-150 to:
from exabyte_api_client.endpoints.workflows import WorkflowEndpoints
from exabyte_api_client.endpoints.materials import MaterialEndpoints
from exabyte_api_client.endpoints.jobs import JobEndpoints🤖 Prompt for AI Agents
In `@examples/workflow/qe_scf_calculation.ipynb` around lines 148 - 150, The
imports for WorkflowEndpoints, MaterialEndpoints, and JobEndpoints are using the
wrong module path; replace the current mat3ra.api_client.endpoints imports with
the correct exabyte_api_client.endpoints imports so that WorkflowEndpoints,
MaterialEndpoints, and JobEndpoints are imported from
exabyte_api_client.endpoints instead of mat3ra.api_client.endpoints.
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@other/jarvis/run_job_using_material_from_jarvis_db.ipynb`:
- Around line 254-258: The notebook's imports (e.g.,
mat3ra.api_client.endpoints.jobs.JobEndpoints, .projects.ProjectEndpoints,
.materials.MaterialEndpoints, .bank_workflows.BankWorkflowEndpoints,
.properties.PropertiesEndpoints) will fail because mat3ra-api-client isn't
installed; update the setup cell to pip-install mat3ra-api-client explicitly and
pin it to the version used in pyproject.toml (match the version string there) so
those imports resolve in isolated environments like Colab. Ensure the pip
install runs before the cells that import
JobEndpoints/ProjectEndpoints/MaterialEndpoints/BankWorkflowEndpoints/PropertiesEndpoints.
In `@other/materials_designer/workflows/band_gap.ipynb`:
- Around line 65-66: The comment above the ORGANIZATION_NAME constant contains a
grammatical typo ("you personal" should be "your personal"); update the comment
string that starts "# Set organization name..." to read "your personal account"
so it correctly says "otherwise your personal account is used", keeping the
surrounding context and the ORGANIZATION_NAME = None line unchanged.
🧹 Nitpick comments (1)
other/materials_designer/workflows/band_gap.ipynb (1)
156-164: Add error handling for organization lookup.If
ORGANIZATION_NAMEis set to a non-existent organization,client.get_account(name=ORGANIZATION_NAME)may returnNone, leading to anAttributeErrorwhen accessingselected_account.id. Adding validation improves the user experience in the notebook.💡 Suggested improvement
"selected_account = client.my_account\n", "\n", "if ORGANIZATION_NAME:\n", " selected_account = client.get_account(name=ORGANIZATION_NAME)\n", + " if selected_account is None:\n", + " raise ValueError(f\"Organization '{ORGANIZATION_NAME}' not found. Check available accounts above.\")\n", "\n", "ACCOUNT_ID = selected_account.id\n", "print(f\"✅ Selected account ID: {ACCOUNT_ID}, name: {selected_account.name}\")"
| "from mat3ra.api_client.endpoints.jobs import JobEndpoints\n", | ||
| "from mat3ra.api_client.endpoints.projects import ProjectEndpoints\n", | ||
| "from mat3ra.api_client.endpoints.materials import MaterialEndpoints\n", | ||
| "from mat3ra.api_client.endpoints.bank_workflows import BankWorkflowEndpoints\n", | ||
| "from mat3ra.api_client.endpoints.properties import PropertiesEndpoints\n", |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
# First, let's find the notebook and examine its content
find . -name "run_job_using_material_from_jarvis_db.ipynb" -type fRepository: Exabyte-io/api-examples
Length of output: 125
🏁 Script executed:
# Also search for dependency files and express-py info
find . -name "setup.py" -o -name "pyproject.toml" -o -name "requirements.txt" | head -20Repository: Exabyte-io/api-examples
Length of output: 83
🏁 Script executed:
# Read the notebook file to check imports and dependencies
cat ./other/jarvis/run_job_using_material_from_jarvis_db.ipynb | head -200Repository: Exabyte-io/api-examples
Length of output: 6211
🏁 Script executed:
# Read the pyproject.toml to see express-py and its dependencies
cat ./pyproject.tomlRepository: Exabyte-io/api-examples
Length of output: 2441
🏁 Script executed:
# Let me read more of the notebook to find lines around 254-258
# First, let's check the file size
wc -l ./other/jarvis/run_job_using_material_from_jarvis_db.ipynbRepository: Exabyte-io/api-examples
Length of output: 129
🏁 Script executed:
# Use python to parse the notebook JSON and extract cell contents to find the imports
python3 << 'EOF'
import json
with open('./other/jarvis/run_job_using_material_from_jarvis_db.ipynb', 'r') as f:
nb = json.load(f)
# Flatten all cell sources to find the lines mentioned
line_num = 0
for cell_idx, cell in enumerate(nb['cells']):
if cell['cell_type'] == 'code':
source = ''.join(cell['source']) if isinstance(cell['source'], list) else cell['source']
source_lines = source.split('\n')
for line in source_lines:
line_num += 1
# Look for imports from mat3ra.api_client
if 'mat3ra.api_client.endpoints' in line:
print(f"Found at notebook line {line_num}: {line}")
EOFRepository: Exabyte-io/api-examples
Length of output: 541
🏁 Script executed:
# Now let's check what express-py depends on
web_search "express-py package PyPI dependencies mat3ra-api-client"Repository: Exabyte-io/api-examples
Length of output: 117
🌐 Web query:
express-py PyPI package dependencies
💡 Result:
express-py (latest: 2025.10.16.post0) depends on: pymatgen, ase, jarvis-tools, mat3ra-esse, numpy, munch. [1]
It also declares Python >= 3.10. [2]
Sources: [1] https://www.piwheels.org/project/express-py/ [2] https://pypi.org/project/express-py/
🏁 Script executed:
# Let me check all pip install commands in the notebook
python3 << 'EOF'
import json
with open('./other/jarvis/run_job_using_material_from_jarvis_db.ipynb', 'r') as f:
nb = json.load(f)
# Find all pip install commands
for cell_idx, cell in enumerate(nb['cells']):
if cell['cell_type'] == 'code':
source = ''.join(cell['source']) if isinstance(cell['source'], list) else cell['source']
if 'pip install' in source or '!pip' in source:
print(f"Cell {cell_idx}:")
print(source)
print("---")
EOFRepository: Exabyte-io/api-examples
Length of output: 119
🏁 Script executed:
# Now let's verify the mat3ra-api-client is a direct dependency in pyproject.toml
grep -A 2 -B 2 "mat3ra-api-client" ./pyproject.tomlRepository: Exabyte-io/api-examples
Length of output: 257
Add explicit mat3ra-api-client installation to the notebook.
The notebook installs only express-py, which does not declare mat3ra-api-client as a dependency. However, lines 254–258 import from mat3ra.api_client.endpoints, which will fail in isolation (e.g., in Google Colab). Add an explicit pip install for mat3ra-api-client to the notebook's setup cell, pinned to the version specified in the project's pyproject.toml.
🤖 Prompt for AI Agents
In `@other/jarvis/run_job_using_material_from_jarvis_db.ipynb` around lines 254 -
258, The notebook's imports (e.g.,
mat3ra.api_client.endpoints.jobs.JobEndpoints, .projects.ProjectEndpoints,
.materials.MaterialEndpoints, .bank_workflows.BankWorkflowEndpoints,
.properties.PropertiesEndpoints) will fail because mat3ra-api-client isn't
installed; update the setup cell to pip-install mat3ra-api-client explicitly and
pin it to the version used in pyproject.toml (match the version string there) so
those imports resolve in isolated environments like Colab. Ensure the pip
install runs before the cells that import
JobEndpoints/ProjectEndpoints/MaterialEndpoints/BankWorkflowEndpoints/PropertiesEndpoints.
Summary by CodeRabbit
Chores
New Features
✏️ Tip: You can customize this high-level summary in your review settings.