feat: add support for AWS session token in S3 configuration (#1363)

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

## Description
<!-- Provide a clear description of the changes in this PR -->
feat: add support for AWS session token in S3 configuration

## 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.

cognee/infrastructure/files/storage/S3FileStorage.py

@@ -21,10 +21,15 @@ class S3FileStorage(Storage):
     def __init__(self, storage_path: str):
         self.storage_path = storage_path
         s3_config = get_s3_config()
-        if s3_config.aws_access_key_id is not None and s3_config.aws_secret_access_key is not None:
+        if (
+            s3_config.aws_access_key_id is not None
+            and s3_config.aws_secret_access_key is not None
+            and s3_config.aws_session_token is not None
+        ):
             self.s3 = s3fs.S3FileSystem(
                 key=s3_config.aws_access_key_id,
                 secret=s3_config.aws_secret_access_key,
+                token=s3_config.aws_session_token,
                 anon=False,
                 endpoint_url=s3_config.aws_endpoint_url,
                 client_kwargs={"region_name": s3_config.aws_region},

cognee/infrastructure/files/storage/s3_config.py

@@ -8,6 +8,7 @@ class S3Config(BaseSettings):
     aws_endpoint_url: Optional[str] = None
     aws_access_key_id: Optional[str] = None
     aws_secret_access_key: Optional[str] = None
+    aws_session_token: Optional[str] = None
     model_config = SettingsConfigDict(env_file=".env", extra="allow")
 
 

cognee/tasks/ingestion/resolve_data_directories.py

@@ -32,7 +32,10 @@ async def resolve_data_directories(
         import s3fs
 
         fs = s3fs.S3FileSystem(
-            key=s3_config.aws_access_key_id, secret=s3_config.aws_secret_access_key, anon=False
+            key=s3_config.aws_access_key_id,
+            secret=s3_config.aws_secret_access_key,
+            token=s3_config.aws_session_token,
+            anon=False,
         )
 
     for item in data:

distributed/pyproject.toml

@@ -40,7 +40,7 @@ dependencies = [
     "aiohttp>=3.11.14,<4.0.0",
     "aiofiles>=23.2.1,<24.0.0",
     "rdflib>=7.1.4,<7.2.0",
-    "pypdf>=4.1.0,<6.0.0",
+    "pypdf>=4.1.0,<7.0.0",
     "jinja2>=3.1.3,<4",
     "matplotlib>=3.8.3,<4",
     "networkx>=3.4.2,<4",

pyproject.toml

@@ -41,7 +41,7 @@ dependencies = [
     "aiohttp>=3.11.14,<4.0.0",
     "aiofiles>=23.2.1,<24.0.0",
     "rdflib>=7.1.4,<7.2.0",
-    "pypdf>=4.1.0,<6.0.0",
+    "pypdf>=4.1.0,<7.0.0",
     "jinja2>=3.1.3,<4",
     "matplotlib>=3.8.3,<4",
     "networkx>=3.4.2,<4",