gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: Resolve code graph pipeline issue

Browse source
This commit is contained in:
Igor Ilic 2025-07-10 22:20:30 +02:00
parent 80896fdcc5
commit 67b61ff964
3 changed files with 55 additions and 49 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
cognee/api/v1/cognify/code_graph_pipeline.py
View file

@ -79,7 +79,9 @@ async def run_code_graph_pipeline(repo_path, include_docs=False):
async for run_status in non_code_pipeline_run: async for run_status in non_code_pipeline_run:
yield run_status yield run_status
async for run_status in run_tasks(tasks, dataset.id, repo_path, user, "cognify_code_pipeline"): async for run_status in run_tasks(
tasks, dataset.id, repo_path, user, "cognify_code_pipeline", incremental_loading=False
):
yield run_status yield run_status

7
cognee/modules/pipelines/operations/run_tasks.py
View file

@ -95,6 +95,8 @@ async def run_tasks(
# TODO: Convert to async gather task instead of for loop (just make sure it can work there were some issues when async gathering datasets) # TODO: Convert to async gather task instead of for loop (just make sure it can work there were some issues when async gathering datasets)
for data_item in data: for data_item in data:
# If incremental_loading of data is set to True don't process documents already processed by pipeline
if incremental_loading:
# If data is being added to Cognee for the first time calculate the id of the data # If data is being added to Cognee for the first time calculate the id of the data
if not isinstance(data_item, Data): if not isinstance(data_item, Data):
data = await resolve_data_directories(data) data = await resolve_data_directories(data)
@ -108,8 +110,6 @@ async def run_tasks(
# If data was already processed by Cognee get data id # If data was already processed by Cognee get data id
data_id = data_item.id data_id = data_item.id
# If incremental_loading is set to True don't process documents already processed by pipeline
if incremental_loading:
# Check pipeline status, if Data already processed for pipeline before skip current processing # Check pipeline status, if Data already processed for pipeline before skip current processing
async with db_engine.get_async_session() as session: async with db_engine.get_async_session() as session:
data_point = ( data_point = (
@ -134,6 +134,7 @@ async def run_tasks(
payload=result, payload=result,
) )
if incremental_loading:
data_items_pipeline_run_info[data_id] = { data_items_pipeline_run_info[data_id] = {
"run_info": PipelineRunCompleted( "run_info": PipelineRunCompleted(
pipeline_run_id=pipeline_run_id, pipeline_run_id=pipeline_run_id,
@ -158,7 +159,7 @@ async def run_tasks(
logger.error( logger.error(
f"Exception caught while processing data: {error}.\n Data processing failed for data item: {data_item}." f"Exception caught while processing data: {error}.\n Data processing failed for data item: {data_item}."
) )
if incremental_loading:
data_items_pipeline_run_info = { data_items_pipeline_run_info = {
"run_info": PipelineRunErrored( "run_info": PipelineRunErrored(
pipeline_run_id=pipeline_run_id, pipeline_run_id=pipeline_run_id,

3
cognee/tasks/repo_processor/get_repo_file_dependencies.py
View file

@ -103,6 +103,9 @@ async def get_repo_file_dependencies(
extraction of dependencies (default is False). (default False) extraction of dependencies (default is False). (default False)
""" """
if isinstance(repo_path, list) and len(repo_path) == 1:
repo_path = repo_path[0]
if not os.path.exists(repo_path): if not os.path.exists(repo_path):
raise FileNotFoundError(f"Repository path {repo_path} does not exist.") raise FileNotFoundError(f"Repository path {repo_path} does not exist.")