fix: add default params to run_tasks (#563)

<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Enhanced the task execution process by enabling default values for
certain parameters, allowing users to trigger task processing without
supplying every input explicitly.
  
- **Bug Fixes**
- Adjusted asynchronous handling for the `retrieved_edges_to_string`
function to ensure proper execution flow in various components.

- **Documentation**
- Updated markdown formatting in the Jupyter notebook for improved
readability and structure.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: hajdul88 <52442977+hajdul88@users.noreply.github.com>

cognee/modules/pipelines/operations/run_tasks.py

@@ -1,7 +1,7 @@
 import inspect
 import json
 import logging
-from uuid import UUID
+from uuid import UUID, uuid4
 
 from typing import Any
 from cognee.modules.pipelines.operations import (
@@ -269,7 +269,12 @@ async def run_tasks_with_telemetry(tasks: list[Task], data, pipeline_name: str):
         raise error
 
 
-async def run_tasks(tasks: list[Task], dataset_id: UUID, data: Any, pipeline_name: str):
+async def run_tasks(
+    tasks: list[Task],
+    dataset_id: UUID = uuid4(),
+    data: Any = None,
+    pipeline_name: str = "unknown_pipeline",
+):
     pipeline_id = uuid5(NAMESPACE_OID, pipeline_name)
 
     pipeline_run = await log_pipeline_run_start(pipeline_id, dataset_id, data)

evals/eval_swe_bench.py

@@ -13,7 +13,7 @@ from cognee.infrastructure.llm.prompts import read_query_prompt
 from cognee.modules.retrieval.description_to_codepart_search import (
     code_description_to_code_part_search,
 )
-from evals.eval_utils import download_github_repo, retrieved_edges_to_string
+from evals.eval_utils import download_github_repo
 
 
 def check_install_package(package_name):

evals/qa_context_provider_utils.py

@@ -122,7 +122,7 @@ async def get_context_with_brute_force_triplet_search(instance: dict) -> str:
 
     found_triplets = await brute_force_triplet_search(instance["question"], top_k=5)
 
-    search_results_str = retrieved_edges_to_string(found_triplets)
+    search_results_str = await retrieved_edges_to_string(found_triplets)
 
     return search_results_str
 

examples/python/graphiti_example.py

@@ -51,7 +51,7 @@ async def main():
 
     args = {
         "question": query,
-        "context": retrieved_edges_to_string(triplets),
+        "context": await retrieved_edges_to_string(triplets),
     }
 
     user_prompt = render_prompt("graph_context_for_question.txt", args)

notebooks/cognee_graphiti_demo.ipynb

@@ -3,7 +3,9 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "# Cognee Graphiti integration demo"
+   "source": [
+    "# Cognee Graphiti integration demo"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -12,7 +14,9 @@
      "languageId": "plaintext"
     }
    },
-   "source": "First we import the necessary libaries"
+   "source": [
+    "First we import the necessary libaries"
+   ]
   },
   {
    "cell_type": "code",
@@ -90,7 +94,9 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "## Input texts with temporal information"
+   "source": [
+    "## Input texts with temporal information"
+   ]
   },
   {
    "cell_type": "code",
@@ -113,7 +119,9 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "## Running graphiti + transforming its graph into cognee's core system (graph transformation + vector embeddings)"
+   "source": [
+    "## Running graphiti + transforming its graph into cognee's core system (graph transformation + vector embeddings)"
+   ]
   },
   {
    "cell_type": "code",
@@ -181,11 +189,13 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "## Retrieving and generating answer from graphiti graph with cognee retriever"
+   "source": [
+    "## Retrieving and generating answer from graphiti graph with cognee retriever"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2025-01-15T10:44:27.844438Z",
@@ -213,7 +223,7 @@
     ")\n",
     "\n",
     "# Step 3: Preparing the Context for the LLM\n",
-    "context = retrieved_edges_to_string(triplets)\n",
+    "context = await retrieved_edges_to_string(triplets)\n",
     "\n",
     "args = {\"question\": query, \"context\": context}\n",
     "\n",