From 57ae93b3cd0c6061a5192dfaa5dee35eb48b0520 Mon Sep 17 00:00:00 2001
From: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Date: Tue, 17 Dec 2024 18:53:28 +0100
Subject: [PATCH 1/9] Update get_cognify_router.py

---
 .../v1/cognify/routers/get_cognify_router.py  | 22 ++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/cognee/api/v1/cognify/routers/get_cognify_router.py b/cognee/api/v1/cognify/routers/get_cognify_router.py
index a56dbd7a5..1a53a7338 100644
--- a/cognee/api/v1/cognify/routers/get_cognify_router.py
+++ b/cognee/api/v1/cognify/routers/get_cognify_router.py
@@ -1,6 +1,6 @@
 from fastapi import APIRouter
-from typing import List, Optional
-from pydantic import BaseModel
+from typing import List, Optional, Any
+from pydantic import BaseModel, create_model
 from cognee.modules.users.models import User
 from fastapi.responses import JSONResponse
 from cognee.modules.users.methods import get_authenticated_user
@@ -9,7 +9,14 @@ from fastapi import Depends
 
 class CognifyPayloadDTO(BaseModel):
     datasets: List[str]
-    graph_model: Optional[BaseModel] = None
+    graph_model: Optional[Any] = None
+
+
+def json_to_pydantic_model(name: str, json_schema: dict) -> BaseModel:
+    """
+    Create a Pydantic model on the fly from JSON.
+    """
+    return create_model(name, **{k: (type(v), ...) for k, v in json_schema.items()})
 
 def get_cognify_router() -> APIRouter:
     router = APIRouter()
@@ -18,6 +25,15 @@ def get_cognify_router() -> APIRouter:
     async def cognify(payload: CognifyPayloadDTO, user: User = Depends(get_authenticated_user)):
         """ This endpoint is responsible for the cognitive processing of the content."""
         from cognee.api.v1.cognify.cognify_v2 import cognify as cognee_cognify
+        try:
+            # Dynamic conversion of `graph_model` to Pydantic
+            if payload.graph_model:
+                graph_model_schema = payload.graph_model
+                GraphModelDynamic = json_to_pydantic_model("GraphModelDynamic", graph_model_schema)
+                graph_model_instance = GraphModelDynamic(**graph_model_schema)
+                print(graph_model_instance)
+        else:
+            graph_model_instance = None
         try:
             await cognee_cognify(payload.datasets, user, payload.graph_model)
         except Exception as error:

From a42ab3e215f898c83ded7f546a96d7dce1127713 Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 10:58:48 +0100
Subject: [PATCH 2/9] fix: Resolve syntax issue with cognify router

Resolve syntax issue with cognify router

Fix
---
 cognee/api/v1/cognify/routers/get_cognify_router.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/cognee/api/v1/cognify/routers/get_cognify_router.py b/cognee/api/v1/cognify/routers/get_cognify_router.py
index 1a53a7338..739bd1657 100644
--- a/cognee/api/v1/cognify/routers/get_cognify_router.py
+++ b/cognee/api/v1/cognify/routers/get_cognify_router.py
@@ -6,6 +6,8 @@ from fastapi.responses import JSONResponse
 from cognee.modules.users.methods import get_authenticated_user
 from fastapi import Depends
 
+from cognee.shared.data_models import KnowledgeGraph
+
 
 class CognifyPayloadDTO(BaseModel):
     datasets: List[str]
@@ -32,10 +34,10 @@ def get_cognify_router() -> APIRouter:
                 GraphModelDynamic = json_to_pydantic_model("GraphModelDynamic", graph_model_schema)
                 graph_model_instance = GraphModelDynamic(**graph_model_schema)
                 print(graph_model_instance)
-        else:
-            graph_model_instance = None
-        try:
-            await cognee_cognify(payload.datasets, user, payload.graph_model)
+            else:
+                graph_model_instance = KnowledgeGraph
+
+            await cognee_cognify(payload.datasets, user, graph_model_instance)
         except Exception as error:
             return JSONResponse(
                 status_code=409,

From 7be7265c93fc32ba2b0e0ceab6d78e4072b82d7f Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 13:19:02 +0100
Subject: [PATCH 3/9] feat: Add ruff pre-commit hook for linting and formatting

Added formatting and linting on pre-commit hook

Feature COG-650
---
 .pre-commit-config.yaml | 20 ++++++++++
 poetry.lock             | 87 ++++++++++++++++++++++++++++++++++++++++-
 pyproject.toml          |  1 +
 3 files changed, 107 insertions(+), 1 deletion(-)
 create mode 100644 .pre-commit-config.yaml

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 000000000..c862cb36f
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,20 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.8.3
+  hooks:
+    # Run the linter.
+    - id: ruff
+      types_or: [ python, pyi ]
+    # Run the formatter.
+    - id: ruff-format
+      types_or: [ python, pyi ]
\ No newline at end of file
diff --git a/poetry.lock b/poetry.lock
index d2c0a8533..3aee967b2 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -726,6 +726,17 @@ files = [
 [package.dependencies]
 pycparser = "*"
 
+[[package]]
+name = "cfgv"
+version = "3.4.0"
+description = "Validate configuration and produce human readable error messages."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c48f9"},
+    {file = "cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5dead8e0f673fb16db7949d2cfb3f7da4582893288f0ded8fe560"},
+]
+
 [[package]]
 name = "chardet"
 version = "5.2.0"
@@ -1379,6 +1390,17 @@ files = [
     {file = "dirtyjson-1.0.8.tar.gz", hash = "sha256:90ca4a18f3ff30ce849d100dcf4a003953c79d3a2348ef056f1d9c22231a25fd"},
 ]
 
+[[package]]
+name = "distlib"
+version = "0.3.9"
+description = "Distribution utilities"
+optional = false
+python-versions = "*"
+files = [
+    {file = "distlib-0.3.9-py2.py3-none-any.whl", hash = "sha256:47f8c22fd27c27e25a65601af709b38e4f0a45ea4fc2e710f65755fa8caaaf87"},
+    {file = "distlib-0.3.9.tar.gz", hash = "sha256:a60f20dea646b8a33f3e7772f74dc0b2d0772d2837ee1342a00645c81edf9403"},
+]
+
 [[package]]
 name = "distro"
 version = "1.9.0"
@@ -2527,6 +2549,20 @@ files = [
     {file = "hyperframe-6.0.1.tar.gz", hash = "sha256:ae510046231dc8e9ecb1a6586f63d2347bf4c8905914aa84ba585ae85f28a914"},
 ]
 
+[[package]]
+name = "identify"
+version = "2.6.3"
+description = "File identification library for Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "identify-2.6.3-py2.py3-none-any.whl", hash = "sha256:9edba65473324c2ea9684b1f944fe3191db3345e50b6d04571d10ed164f8d7bd"},
+    {file = "identify-2.6.3.tar.gz", hash = "sha256:62f5dae9b5fef52c84cc188514e9ea4f3f636b1d8799ab5ebc475471f9e47a02"},
+]
+
+[package.extras]
+license = ["ukkonen"]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -4535,6 +4571,17 @@ plot = ["matplotlib"]
 tgrep = ["pyparsing"]
 twitter = ["twython"]
 
+[[package]]
+name = "nodeenv"
+version = "1.9.1"
+description = "Node.js virtual environment builder"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+    {file = "nodeenv-1.9.1-py2.py3-none-any.whl", hash = "sha256:ba11c9782d29c27c70ffbdda2d7415098754709be8a7056d79a737cd901155c9"},
+    {file = "nodeenv-1.9.1.tar.gz", hash = "sha256:6ec12890a2dab7946721edbfbcd91f3319c6ccc9aec47be7c7e6b7011ee6645f"},
+]
+
 [[package]]
 name = "notebook"
 version = "7.3.1"
@@ -5348,6 +5395,24 @@ dev = ["black", "flake8", "flake8-print", "isort", "pre-commit"]
 sentry = ["django", "sentry-sdk"]
 test = ["coverage", "django", "flake8", "freezegun (==0.3.15)", "mock (>=2.0.0)", "pylint", "pytest", "pytest-timeout"]
 
+[[package]]
+name = "pre-commit"
+version = "4.0.1"
+description = "A framework for managing and maintaining multi-language pre-commit hooks."
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "pre_commit-4.0.1-py2.py3-none-any.whl", hash = "sha256:efde913840816312445dc98787724647c65473daefe420785f885e8ed9a06878"},
+    {file = "pre_commit-4.0.1.tar.gz", hash = "sha256:80905ac375958c0444c65e9cebebd948b3cdb518f335a091a670a89d652139d2"},
+]
+
+[package.dependencies]
+cfgv = ">=2.0.0"
+identify = ">=1.0.0"
+nodeenv = ">=0.11.1"
+pyyaml = ">=5.1"
+virtualenv = ">=20.10.0"
+
 [[package]]
 name = "prometheus-client"
 version = "0.21.1"
@@ -8375,6 +8440,26 @@ files = [
 [package.extras]
 crypto-eth-addresses = ["eth-hash[pycryptodome] (>=0.7.0)"]
 
+[[package]]
+name = "virtualenv"
+version = "20.28.0"
+description = "Virtual Python Environment builder"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "virtualenv-20.28.0-py3-none-any.whl", hash = "sha256:23eae1b4516ecd610481eda647f3a7c09aea295055337331bb4e6892ecce47b0"},
+    {file = "virtualenv-20.28.0.tar.gz", hash = "sha256:2c9c3262bb8e7b87ea801d715fae4495e6032450c71d2309be9550e7364049aa"},
+]
+
+[package.dependencies]
+distlib = ">=0.3.7,<1"
+filelock = ">=3.12.2,<4"
+platformdirs = ">=3.9.1,<5"
+
+[package.extras]
+docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.2,!=7.3)", "sphinx-argparse (>=0.4)", "sphinxcontrib-towncrier (>=0.2.1a0)", "towncrier (>=23.6)"]
+test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=23.1)", "pytest (>=7.4)", "pytest-env (>=0.8.2)", "pytest-freezer (>=0.4.8)", "pytest-mock (>=3.11.1)", "pytest-randomly (>=3.12)", "pytest-timeout (>=2.1)", "setuptools (>=68)", "time-machine (>=2.10)"]
+
 [[package]]
 name = "watchdog"
 version = "6.0.0"
@@ -8877,4 +8962,4 @@ weaviate = ["weaviate-client"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9.0,<3.12"
-content-hash = "af91e3dcf6a8927ed938fe3f78172a5f1e0c0f9c8fbcbc76767b0e0d84645c9e"
+content-hash = "7b339ad192fdc1bf97bbc0797b9657f0245b00627f811009a545e4a3380368bb"
diff --git a/pyproject.toml b/pyproject.toml
index 79f5a6855..cbee3e056 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -74,6 +74,7 @@ deepeval = {version = "^2.0.1", optional = true}
 transformers = "^4.46.3"
 pymilvus = {version = "^2.5.0", optional = true}
 unstructured = { extras = ["csv", "doc", "docx", "epub", "md", "odt", "org", "ppt", "pptx", "rst", "rtf", "tsv", "xlsx"], version = "^0.16.10", optional = true }
+pre-commit = "^4.0.1"
 
 
 

From 875dd1055e375d65dee1d22b9e8cd90ce677f3d9 Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 13:31:19 +0100
Subject: [PATCH 4/9] chore: Update ruff lint options in pyproject file

Update ruff lint options in pyproject file

Chore
---
 .pre-commit-config.yaml | 2 +-
 pyproject.toml          | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index c862cb36f..42f12ea51 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -17,4 +17,4 @@ repos:
       types_or: [ python, pyi ]
     # Run the formatter.
     - id: ruff-format
-      types_or: [ python, pyi ]
\ No newline at end of file
+      types_or: [ python, pyi ]
diff --git a/pyproject.toml b/pyproject.toml
index cbee3e056..0d5845d78 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -115,11 +115,10 @@ mkdocstrings = {extras = ["python"], version = "^0.26.2"}
 
 [tool.ruff] # https://beta.ruff.rs/docs/
 line-length = 100
+
+[tool.ruff.lint]
 ignore = ["F401"]
-ignore-init-module-imports = true
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
-
-

From 856f228981a46ad931347c08a16db91886fcf95e Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 14:04:49 +0100
Subject: [PATCH 5/9] test: Add ruff linter github action

Added linting check with ruff in github actions

Test COG-650
---
 .github/workflows/ruff_lint.yaml | 9 +++++++++
 1 file changed, 9 insertions(+)
 create mode 100644 .github/workflows/ruff_lint.yaml

diff --git a/.github/workflows/ruff_lint.yaml b/.github/workflows/ruff_lint.yaml
new file mode 100644
index 000000000..43cfef95b
--- /dev/null
+++ b/.github/workflows/ruff_lint.yaml
@@ -0,0 +1,9 @@
+name: Ruff
+on: [ push, pull_request ]
+
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/ruff-action@v2

From f660127d2d25e0265cac1e865c8c962865551fe3 Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 14:24:14 +0100
Subject: [PATCH 6/9] refactor: Remove changes to cognify router

Remove changes to cognify router

Refactor COG-650
---
 .../v1/cognify/routers/get_cognify_router.py  | 26 +++----------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/cognee/api/v1/cognify/routers/get_cognify_router.py b/cognee/api/v1/cognify/routers/get_cognify_router.py
index 739bd1657..257ac994f 100644
--- a/cognee/api/v1/cognify/routers/get_cognify_router.py
+++ b/cognee/api/v1/cognify/routers/get_cognify_router.py
@@ -1,24 +1,15 @@
 from fastapi import APIRouter
-from typing import List, Optional, Any
-from pydantic import BaseModel, create_model
+from typing import List, Optional
+from pydantic import BaseModel
 from cognee.modules.users.models import User
 from fastapi.responses import JSONResponse
 from cognee.modules.users.methods import get_authenticated_user
 from fastapi import Depends
-
 from cognee.shared.data_models import KnowledgeGraph
 
-
 class CognifyPayloadDTO(BaseModel):
     datasets: List[str]
-    graph_model: Optional[Any] = None
-
-
-def json_to_pydantic_model(name: str, json_schema: dict) -> BaseModel:
-    """
-    Create a Pydantic model on the fly from JSON.
-    """
-    return create_model(name, **{k: (type(v), ...) for k, v in json_schema.items()})
+    graph_model: Optional[BaseModel] = KnowledgeGraph
 
 def get_cognify_router() -> APIRouter:
     router = APIRouter()
@@ -28,16 +19,7 @@ def get_cognify_router() -> APIRouter:
         """ This endpoint is responsible for the cognitive processing of the content."""
         from cognee.api.v1.cognify.cognify_v2 import cognify as cognee_cognify
         try:
-            # Dynamic conversion of `graph_model` to Pydantic
-            if payload.graph_model:
-                graph_model_schema = payload.graph_model
-                GraphModelDynamic = json_to_pydantic_model("GraphModelDynamic", graph_model_schema)
-                graph_model_instance = GraphModelDynamic(**graph_model_schema)
-                print(graph_model_instance)
-            else:
-                graph_model_instance = KnowledgeGraph
-
-            await cognee_cognify(payload.datasets, user, graph_model_instance)
+            await cognee_cognify(payload.datasets, user, payload.graph_model)
         except Exception as error:
             return JSONResponse(
                 status_code=409,

From 8aff9962dd3f458fde899e97cf25cc02df3811f0 Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 14:42:19 +0100
Subject: [PATCH 7/9] test: Add test for ruff format for cognee code

Test if code is formatted for cognee

Test COG-650
---
 .github/workflows/ruff_format.yaml | 11 +++++++++++
 1 file changed, 11 insertions(+)
 create mode 100644 .github/workflows/ruff_format.yaml

diff --git a/.github/workflows/ruff_format.yaml b/.github/workflows/ruff_format.yaml
new file mode 100644
index 000000000..e036c3ac8
--- /dev/null
+++ b/.github/workflows/ruff_format.yaml
@@ -0,0 +1,11 @@
+name: Ruff
+on: [ push, pull_request ]
+
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/ruff-action@v2
+        with:
+          args: "format --check"

From 7a9f7b07f6465a37063365a94383d16a4cfe5ec9 Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 14:43:31 +0100
Subject: [PATCH 8/9] refactor: Rename ruff gh actions

Rename ruff gh actions to be more understandable

Refactor COG-650
---
 .github/workflows/ruff_format.yaml | 2 +-
 .github/workflows/ruff_lint.yaml   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ruff_format.yaml b/.github/workflows/ruff_format.yaml
index e036c3ac8..899dfff22 100644
--- a/.github/workflows/ruff_format.yaml
+++ b/.github/workflows/ruff_format.yaml
@@ -1,4 +1,4 @@
-name: Ruff
+name: ruff format
 on: [ push, pull_request ]
 
 jobs:
diff --git a/.github/workflows/ruff_lint.yaml b/.github/workflows/ruff_lint.yaml
index 43cfef95b..cf09ab53d 100644
--- a/.github/workflows/ruff_lint.yaml
+++ b/.github/workflows/ruff_lint.yaml
@@ -1,4 +1,4 @@
-name: Ruff
+name: ruff lint
 on: [ push, pull_request ]
 
 jobs:

From 8ec639a12a97b684ee665ef06955f2486b53eb48 Mon Sep 17 00:00:00 2001
From: Igor Ilic <igorilic03@gmail.com>
Date: Wed, 18 Dec 2024 15:01:13 +0100
Subject: [PATCH 9/9] chore: Remove checking of ruff lint and format on push

Remove checking of ruff lint and format on push

Chore COG-650
---
 .github/workflows/ruff_format.yaml | 2 +-
 .github/workflows/ruff_lint.yaml   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/ruff_format.yaml b/.github/workflows/ruff_format.yaml
index 899dfff22..959b7fc4b 100644
--- a/.github/workflows/ruff_format.yaml
+++ b/.github/workflows/ruff_format.yaml
@@ -1,5 +1,5 @@
 name: ruff format
-on: [ push, pull_request ]
+on: [ pull_request ]
 
 jobs:
   ruff:
diff --git a/.github/workflows/ruff_lint.yaml b/.github/workflows/ruff_lint.yaml
index cf09ab53d..214e8ec6d 100644
--- a/.github/workflows/ruff_lint.yaml
+++ b/.github/workflows/ruff_lint.yaml
@@ -1,5 +1,5 @@
 name: ruff lint
-on: [ push, pull_request ]
+on: [ pull_request ]
 
 jobs:
   ruff: