diff --git a/memgpt/client/client.py b/memgpt/client/client.py
index 71469c3011..4324bdd108 100644
--- a/memgpt/client/client.py
+++ b/memgpt/client/client.py
@@ -3,9 +3,10 @@
 from requests.exceptions import RequestException
 import uuid
 from typing import Dict, List, Union, Optional, Tuple
+import time
 
 from memgpt.data_types import AgentState, User, Preset, LLMConfig, EmbeddingConfig, Source
-from memgpt.models.pydantic_models import HumanModel, PersonaModel, PresetModel, SourceModel
+from memgpt.models.pydantic_models import HumanModel, PersonaModel, PresetModel, SourceModel, JobModel, JobStatus
 from memgpt.cli.cli import QuickstartChoice
 from memgpt.cli.cli import set_config_with_dict, quickstart as quickstart_func, str_to_quickstart_choice
 from memgpt.config import MemGPTConfig
@@ -436,18 +437,36 @@ def delete_source(self, source_id: uuid.UUID):
         response = requests.delete(f"{self.base_url}/api/sources/{str(source_id)}", headers=self.headers)
         assert response.status_code == 200, f"Failed to delete source: {response.text}"
 
-    def load_file_into_source(self, filename: str, source_id: uuid.UUID):
+    def get_job_status(self, job_id: uuid.UUID):
+        response = requests.get(f"{self.base_url}/api/sources/status/{str(job_id)}", headers=self.headers)
+        return JobModel(**response.json())
+
+    def load_file_into_source(self, filename: str, source_id: uuid.UUID, blocking=True):
         """Load {filename} and insert into source"""
         files = {"file": open(filename, "rb")}
+
+        # create job
         response = requests.post(f"{self.base_url}/api/sources/{source_id}/upload", files=files, headers=self.headers)
-        return UploadFileToSourceResponse(**response.json())
+        if response.status_code != 200:
+            raise ValueError(f"Failed to upload file to source: {response.text}")
+
+        job = JobModel(**response.json())
+        if blocking:
+            # wait until job is completed
+            while True:
+                job = self.get_job_status(job.id)
+                if job.status == JobStatus.completed:
+                    break
+                elif job.status == JobStatus.failed:
+                    raise ValueError(f"Job failed: {job.metadata}")
+                time.sleep(1)
+        return job
 
     def create_source(self, name: str) -> Source:
         """Create a new source"""
         payload = {"name": name}
         response = requests.post(f"{self.base_url}/api/sources", json=payload, headers=self.headers)
         response_json = response.json()
-        print("CREATE SOURCE", response_json, response.text)
         response_obj = SourceModel(**response_json)
         return Source(
             id=uuid.UUID(response_obj.id),
diff --git a/memgpt/config.py b/memgpt/config.py
index 1df21fff42..50406b6b00 100644
--- a/memgpt/config.py
+++ b/memgpt/config.py
@@ -341,10 +341,9 @@ def __init__(
         # functions
         functions=None,  # schema definitions ONLY (linked at runtime)
     ):
-        if name is None:
-            self.name = f"agent_{self.generate_agent_id()}"
-        else:
-            self.name = name
+
+        assert name, f"Agent name must be provided"
+        self.name = name
 
         config = MemGPTConfig.load()  # get default values
         self.persona = config.persona if persona is None else persona
@@ -397,15 +396,6 @@ def __init__(
             os.path.join(MEMGPT_DIR, "agents", self.name, "config.json") if agent_config_path is None else agent_config_path
         )
 
-    def generate_agent_id(self, length=6):
-        ## random character based
-        # characters = string.ascii_lowercase + string.digits
-        # return ''.join(random.choices(characters, k=length))
-
-        # count based
-        agent_count = len(utils.list_agent_config_files())
-        return str(agent_count + 1)
-
     def attach_data_source(self, data_source: str):
         # TODO: add warning that only once source can be attached
         # i.e. previous source will be overriden
diff --git a/memgpt/data_sources/connectors.py b/memgpt/data_sources/connectors.py
index 3611563693..2128115a0f 100644
--- a/memgpt/data_sources/connectors.py
+++ b/memgpt/data_sources/connectors.py
@@ -97,7 +97,7 @@ def load_data(
 
             passages.append(passage)
             embedding_to_document_name[hashable_embedding] = document_name
-            if len(passages) >= embedding_config.embedding_chunk_size:
+            if len(passages) >= 100:
                 # insert passages into passage store
                 passage_store.insert_many(passages)
 
diff --git a/memgpt/metadata.py b/memgpt/metadata.py
index f0b83c4255..34f2c663c9 100644
--- a/memgpt/metadata.py
+++ b/memgpt/metadata.py
@@ -8,12 +8,12 @@
 
 from memgpt.settings import settings
 from memgpt.constants import DEFAULT_HUMAN, DEFAULT_MEMGPT_MODEL, DEFAULT_PERSONA, DEFAULT_PRESET, LLM_MAX_TOKENS
-from memgpt.utils import enforce_types, printd
+from memgpt.utils import enforce_types, printd, get_utc_time
 from memgpt.data_types import AgentState, Source, User, LLMConfig, EmbeddingConfig, Token, Preset
 from memgpt.config import MemGPTConfig
 from memgpt.functions.functions import load_all_function_sets
 
-from memgpt.models.pydantic_models import PersonaModel, HumanModel, ToolModel
+from memgpt.models.pydantic_models import PersonaModel, HumanModel, ToolModel, JobModel, JobStatus
 
 from sqlalchemy import create_engine, Column, String, BIGINT, select, inspect, text, JSON, BLOB, BINARY, ARRAY, Boolean
 from sqlalchemy import func
@@ -334,6 +334,7 @@ def __init__(self, config: MemGPTConfig):
                 HumanModel.__table__,
                 PersonaModel.__table__,
                 ToolModel.__table__,
+                JobModel.__table__,
             ],
         )
         self.session_maker = sessionmaker(bind=self.engine)
@@ -754,3 +755,31 @@ def delete_preset(self, name: str, user_id: uuid.UUID):
         with self.session_maker() as session:
             session.query(PresetModel).filter(PresetModel.name == name).filter(PresetModel.user_id == user_id).delete()
             session.commit()
+
+    # job related functions
+    def create_job(self, job: JobModel):
+        with self.session_maker() as session:
+            session.add(job)
+            session.commit()
+            session.expunge_all()
+
+    def update_job_status(self, job_id: uuid.UUID, status: JobStatus):
+        with self.session_maker() as session:
+            session.query(JobModel).filter(JobModel.id == job_id).update({"status": status})
+            if status == JobStatus.COMPLETED:
+                session.query(JobModel).filter(JobModel.id == job_id).update({"completed_at": get_utc_time()})
+            session.commit()
+
+    def update_job(self, job: JobModel):
+        with self.session_maker() as session:
+            session.add(job)
+            session.commit()
+            session.refresh(job)
+
+    def get_job(self, job_id: uuid.UUID) -> Optional[JobModel]:
+        with self.session_maker() as session:
+            results = session.query(JobModel).filter(JobModel.id == job_id).all()
+            if len(results) == 0:
+                return None
+            assert len(results) == 1, f"Expected 1 result, got {len(results)}"
+            return results[0]
diff --git a/memgpt/models/pydantic_models.py b/memgpt/models/pydantic_models.py
index f23952d7c4..4d0ac71afd 100644
--- a/memgpt/models/pydantic_models.py
+++ b/memgpt/models/pydantic_models.py
@@ -1,11 +1,13 @@
 from typing import List, Optional, Dict, Literal, Type
 from pydantic import BaseModel, Field, Json, ConfigDict
+from enum import StrEnum
 import uuid
 import base64
 import numpy as np
 from datetime import datetime
 from sqlmodel import Field, SQLModel
-from sqlalchemy import JSON, Column, BINARY, TypeDecorator
+from sqlalchemy_utils import ChoiceType
+from sqlalchemy import JSON, Column, BINARY, TypeDecorator, String
 
 from memgpt.constants import DEFAULT_HUMAN, DEFAULT_MEMGPT_MODEL, DEFAULT_PERSONA, DEFAULT_PRESET, LLM_MAX_TOKENS, MAX_EMBEDDING_DIM
 from memgpt.utils import get_human_text, get_persona_text, printd, get_utc_time
@@ -132,6 +134,23 @@ class SourceModel(SQLModel, table=True):
     metadata_: Optional[dict] = Field(None, sa_column=Column(JSON), description="Metadata associated with the source.")
 
 
+class JobStatus(StrEnum):
+    created = "created"
+    running = "running"
+    completed = "completed"
+    failed = "failed"
+
+
+class JobModel(SQLModel, table=True):
+    id: uuid.UUID = Field(default_factory=uuid.uuid4, description="The unique identifier of the job.", primary_key=True)
+    # status: str = Field(default="created", description="The status of the job.")
+    status: JobStatus = Field(default=JobStatus.created, description="The status of the job.", sa_column=Column(ChoiceType(JobStatus)))
+    created_at: datetime = Field(default_factory=get_utc_time, description="The unix timestamp of when the job was created.")
+    completed_at: Optional[datetime] = Field(None, description="The unix timestamp of when the job was completed.")
+    user_id: uuid.UUID = Field(..., description="The unique identifier of the user associated with the job.")
+    metadata_: Optional[dict] = Field({}, sa_column=Column(JSON), description="The metadata of the job.")
+
+
 class PassageModel(BaseModel):
     user_id: Optional[uuid.UUID] = Field(None, description="The unique identifier of the user associated with the passage.")
     agent_id: Optional[uuid.UUID] = Field(None, description="The unique identifier of the agent associated with the passage.")
diff --git a/memgpt/server/rest_api/admin/users.py b/memgpt/server/rest_api/admin/users.py
index 0f6f575ca0..b4c485f89e 100644
--- a/memgpt/server/rest_api/admin/users.py
+++ b/memgpt/server/rest_api/admin/users.py
@@ -136,7 +136,6 @@ def get_api_keys(
         """
         Get a list of all API keys for a user
         """
-        print("GET USERS", user_id)
         try:
             tokens = server.ms.get_all_api_keys_for_user(user_id=user_id)
             processed_tokens = [t.token for t in tokens]
diff --git a/memgpt/server/rest_api/server.py b/memgpt/server/rest_api/server.py
index fce26567c6..21a5c3c8c4 100644
--- a/memgpt/server/rest_api/server.py
+++ b/memgpt/server/rest_api/server.py
@@ -39,13 +39,11 @@
   cd memgpt/server/rest_api
   poetry run uvicorn server:app --reload
 """
-
 config = MemGPTConfig.load()
 for memory_type in ("archival", "recall", "metadata"):
     setattr(config, f"{memory_type}_storage_uri", settings.pg_uri)
 config.save()
 
-
 interface: QueuingInterface = QueuingInterface()
 server: SyncServer = SyncServer(default_interface=interface)
 
diff --git a/memgpt/server/rest_api/sources/index.py b/memgpt/server/rest_api/sources/index.py
index c5ce812648..76eda13103 100644
--- a/memgpt/server/rest_api/sources/index.py
+++ b/memgpt/server/rest_api/sources/index.py
@@ -5,11 +5,12 @@
 from functools import partial
 from typing import List, Optional
 
-from fastapi import APIRouter, Body, Depends, Query, HTTPException, status, UploadFile
+from fastapi import APIRouter, Body, Depends, Query, HTTPException, status, UploadFile, BackgroundTasks
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel, Field
+from starlette.responses import StreamingResponse
 
-from memgpt.models.pydantic_models import SourceModel, PassageModel, DocumentModel
+from memgpt.models.pydantic_models import SourceModel, PassageModel, DocumentModel, JobModel, JobStatus
 from memgpt.server.rest_api.auth_token import get_current_user
 from memgpt.server.rest_api.interface import QueuingInterface
 from memgpt.server.server import SyncServer
@@ -57,6 +58,44 @@ class GetSourceDocumentsResponse(BaseModel):
     documents: List[DocumentModel] = Field(..., description="List of documents from the source.")
 
 
+def load_file_to_source(server: SyncServer, user_id: uuid.UUID, source: Source, job_id: uuid.UUID, file: UploadFile):
+    # update job status
+    job = server.ms.get_job(job_id=job_id)
+    job.status = JobStatus.running
+    server.ms.update_job(job)
+
+    try:
+        # write the file to a temporary directory (deleted after the context manager exits)
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            file_path = os.path.join(tmpdirname, file.filename)
+            with open(file_path, "wb") as buffer:
+                buffer.write(file.file.read())
+
+            # read the file
+            connector = DirectoryConnector(input_files=[file_path])
+
+            # TODO: pre-compute total number of passages?
+
+            # load the data into the source via the connector
+            num_passages, num_documents = server.load_data(user_id=user_id, source_name=source.name, connector=connector)
+    except Exception as e:
+        # job failed with error
+        error = str(e)
+        print(error)
+        job.status = JobStatus.failed
+        job.metadata_["error"] = error
+        server.ms.update_job(job)
+        # TODO: delete any associated passages/documents?
+        return 0, 0
+
+    # update job status
+    job.status = JobStatus.completed
+    job.metadata_["num_passages"] = num_passages
+    job.metadata_["num_documents"] = num_documents
+    print("job completed", job.metadata_, job.id)
+    server.ms.update_job(job)
+
+
 def setup_sources_index_router(server: SyncServer, interface: QueuingInterface, password: str):
     get_current_user_with_server = partial(partial(get_current_user, server), password)
 
@@ -64,7 +103,9 @@ def setup_sources_index_router(server: SyncServer, interface: QueuingInterface,
     async def list_sources(
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """List all data sources created by a user."""
+        """
+        List all data sources created by a user.
+        """
         # Clear the interface
         interface.clear()
 
@@ -81,7 +122,9 @@ async def create_source(
         request: CreateSourceRequest = Body(...),
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """Create a new data source."""
+        """
+        Create a new data source.
+        """
         interface.clear()
         try:
             # TODO: don't use Source and just use SourceModel once pydantic migration is complete
@@ -104,7 +147,9 @@ async def delete_source(
         source_id: uuid.UUID,
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """Delete a data source."""
+        """
+        Delete a data source.
+        """
         interface.clear()
         try:
             server.delete_source(source_id=source_id, user_id=user_id)
@@ -120,7 +165,9 @@ async def attach_source_to_agent(
         agent_id: uuid.UUID = Query(..., description="The unique identifier of the agent to attach the source to."),
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """Attach a data source to an existing agent."""
+        """
+        Attach a data source to an existing agent.
+        """
         interface.clear()
         assert isinstance(agent_id, uuid.UUID), f"Expected agent_id to be a UUID, got {agent_id}"
         assert isinstance(user_id, uuid.UUID), f"Expected user_id to be a UUID, got {user_id}"
@@ -141,41 +188,58 @@ async def detach_source_from_agent(
         agent_id: uuid.UUID = Query(..., description="The unique identifier of the agent to detach the source from."),
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """Detach a data source from an existing agent."""
+        """
+        Detach a data source from an existing agent.
+        """
         server.detach_source_from_agent(source_id=source_id, agent_id=agent_id, user_id=user_id)
 
-    @router.post("/sources/{source_id}/upload", tags=["sources"], response_model=UploadFileToSourceResponse)
+    @router.get("/sources/status/{job_id}", tags=["sources"], response_model=JobModel)
+    async def get_job_status(
+        job_id: uuid.UUID,
+        user_id: uuid.UUID = Depends(get_current_user_with_server),
+    ):
+        """
+        Get the status of a job.
+        """
+        job = server.ms.get_job(job_id=job_id)
+        if job is None:
+            raise HTTPException(status_code=404, detail=f"Job with id={job_id} not found.")
+        return job
+
+    @router.post("/sources/{source_id}/upload", tags=["sources"], response_model=JobModel)
     async def upload_file_to_source(
         # file: UploadFile = UploadFile(..., description="The file to upload."),
         file: UploadFile,
         source_id: uuid.UUID,
+        background_tasks: BackgroundTasks,
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """Upload a file to a data source."""
+        """
+        Upload a file to a data source.
+        """
         interface.clear()
         source = server.ms.get_source(source_id=source_id, user_id=user_id)
 
-        # write the file to a temporary directory (deleted after the context manager exits)
-        with tempfile.TemporaryDirectory() as tmpdirname:
-            file_path = os.path.join(tmpdirname, file.filename)
-            with open(file_path, "wb") as buffer:
-                buffer.write(file.file.read())
-
-            # read the file
-            connector = DirectoryConnector(input_files=[file_path])
+        # create job
+        job = JobModel(user_id=user_id, metadata={"type": "embedding", "filename": file.filename, "source_id": source_id})
+        job_id = job.id
+        server.ms.create_job(job)
 
-            # load the data into the source via the connector
-            passage_count, document_count = server.load_data(user_id=user_id, source_name=source.name, connector=connector)
+        # create background task
+        background_tasks.add_task(load_file_to_source, server, user_id, source, job_id, file)
 
-        # TODO: actually return added passages/documents
-        return UploadFileToSourceResponse(source=source, added_passages=passage_count, added_documents=document_count)
+        # return job information
+        job = server.ms.get_job(job_id=job_id)
+        return job
 
     @router.get("/sources/{source_id}/passages ", tags=["sources"], response_model=GetSourcePassagesResponse)
     async def list_passages(
         source_id: uuid.UUID,
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """List all passages associated with a data source."""
+        """
+        List all passages associated with a data source.
+        """
         passages = server.list_data_source_passages(user_id=user_id, source_id=source_id)
         return GetSourcePassagesResponse(passages=passages)
 
@@ -184,7 +248,9 @@ async def list_documents(
         source_id: uuid.UUID,
         user_id: uuid.UUID = Depends(get_current_user_with_server),
     ):
-        """List all documents associated with a data source."""
+        """
+        List all documents associated with a data source.
+        """
         documents = server.list_data_source_documents(user_id=user_id, source_id=source_id)
         return GetSourceDocumentsResponse(documents=documents)
 
diff --git a/poetry.lock b/poetry.lock
index a7670983d7..272b14ce6c 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -801,21 +801,21 @@ typing-inspect = ">=0.4.0,<1"
 
 [[package]]
 name = "datasets"
-version = "2.18.0"
+version = "2.19.0"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = true
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.18.0-py3-none-any.whl", hash = "sha256:f1bbf0e2896917a914de01cbd37075b14deea3837af87ad0d9f697388ccaeb50"},
-    {file = "datasets-2.18.0.tar.gz", hash = "sha256:cdf8b8c6abf7316377ba4f49f9589a4c74556d6b481afd0abd2284f3d69185cb"},
+    {file = "datasets-2.19.0-py3-none-any.whl", hash = "sha256:f57c5316e123d4721b970c68c1cb856505f289cda58f5557ffe745b49c011a8e"},
+    {file = "datasets-2.19.0.tar.gz", hash = "sha256:0b47e08cc7af2c6800a42cadc4657b22a0afc7197786c8986d703c08d90886a6"},
 ]
 
 [package.dependencies]
 aiohttp = "*"
 dill = ">=0.3.0,<0.3.9"
 filelock = "*"
-fsspec = {version = ">=2023.1.0,<=2024.2.0", extras = ["http"]}
-huggingface-hub = ">=0.19.4"
+fsspec = {version = ">=2023.1.0,<=2024.3.1", extras = ["http"]}
+huggingface-hub = ">=0.21.2"
 multiprocess = "*"
 numpy = ">=1.17"
 packaging = "*"
@@ -831,15 +831,15 @@ xxhash = "*"
 apache-beam = ["apache-beam (>=2.26.0)"]
 audio = ["librosa", "soundfile (>=0.12.1)"]
 benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
-dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
-docs = ["s3fs", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos", "torch", "transformers"]
+dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
 jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
 metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
 quality = ["ruff (>=0.3.0)"]
 s3 = ["s3fs"]
-tensorflow = ["tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos"]
-tensorflow-gpu = ["tensorflow-gpu (>=2.2.0,!=2.6.0,!=2.6.1)"]
-tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
+tensorflow = ["tensorflow (>=2.6.0)"]
+tensorflow-gpu = ["tensorflow (>=2.6.0)"]
+tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
@@ -1196,13 +1196,13 @@ files = [
 
 [[package]]
 name = "fsspec"
-version = "2024.2.0"
+version = "2024.3.1"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "fsspec-2024.2.0-py3-none-any.whl", hash = "sha256:817f969556fa5916bc682e02ca2045f96ff7f586d45110fcb76022063ad2c7d8"},
-    {file = "fsspec-2024.2.0.tar.gz", hash = "sha256:b6ad1a679f760dda52b1168c859d01b7b80648ea6f7f7c7f5a8a91dc3f3ecb84"},
+    {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
+    {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
 ]
 
 [package.dependencies]
@@ -1933,13 +1933,13 @@ sentence-transformers = ">=2.6.1,<3.0.0"
 
 [[package]]
 name = "llama-index-embeddings-openai"
-version = "0.1.7"
+version = "0.1.8"
 description = "llama-index embeddings openai integration"
 optional = false
-python-versions = ">=3.8.1,<4.0"
+python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "llama_index_embeddings_openai-0.1.7-py3-none-any.whl", hash = "sha256:6023925ed1487b0688323d21711efbf8880e82ed3b87ef413255c3dc63a2f2fe"},
-    {file = "llama_index_embeddings_openai-0.1.7.tar.gz", hash = "sha256:c71cc9820680c4cedfc9845dc87b94f6851d1ccce1e486fc91298f8fa8d9f27d"},
+    {file = "llama_index_embeddings_openai-0.1.8-py3-none-any.whl", hash = "sha256:186be52c29a8c82a39ff6e033e3a61b9c5a17cf6177a5507abe4f5c79fea3a53"},
+    {file = "llama_index_embeddings_openai-0.1.8.tar.gz", hash = "sha256:aae4ce3ec2fe2cb604d944646982c71663a8b99ed5f8c370823ee82eef4ddd3b"},
 ]
 
 [package.dependencies]
@@ -2018,13 +2018,13 @@ llama-index-llms-openai = ">=0.1.1,<0.2.0"
 
 [[package]]
 name = "llama-index-llms-openai"
-version = "0.1.15"
+version = "0.1.16"
 description = "llama-index llms openai integration"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "llama_index_llms_openai-0.1.15-py3-none-any.whl", hash = "sha256:401ba9db1549e4287b73749dee57b11db1e0ffa814bb1464475aea1ff84442c7"},
-    {file = "llama_index_llms_openai-0.1.15.tar.gz", hash = "sha256:6bdbf307b1d43a9a7c2a52f72ba7db61cb96d904f99e7ea5d889dd7818f10814"},
+    {file = "llama_index_llms_openai-0.1.16-py3-none-any.whl", hash = "sha256:4a9c0fe969302731907c8fa31631812397637e114a44ebbad11fd6c59def9315"},
+    {file = "llama_index_llms_openai-0.1.16.tar.gz", hash = "sha256:313bbc17c241992430a6bf686a1b1edc4276c8256ad6b0550aa1bea1e0fed1a6"},
 ]
 
 [package.dependencies]
@@ -2901,13 +2901,13 @@ sympy = "*"
 
 [[package]]
 name = "openai"
-version = "1.23.1"
+version = "1.23.2"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.23.1-py3-none-any.whl", hash = "sha256:7941c1bc6fcdb1b6b889dfcfabff775ca52558a79d57dd1b9e15b463de1b3a4c"},
-    {file = "openai-1.23.1.tar.gz", hash = "sha256:6df937e2a1ad64494951ea3614f5516db4d67c3fcc0b751b8e5edf1bc57e2d3d"},
+    {file = "openai-1.23.2-py3-none-any.whl", hash = "sha256:293a36effde29946eb221040c89c46a4850f2f2e30b37ef09ff6d75226d71b42"},
+    {file = "openai-1.23.2.tar.gz", hash = "sha256:b84aa3005357ceb38f22a269e0e22ee58ce103897f447032d021906f18178a8e"},
 ]
 
 [package.dependencies]
@@ -4877,6 +4877,34 @@ sqlalchemy = ">=0.7"
 [package.extras]
 dev = ["pytest"]
 
+[[package]]
+name = "sqlalchemy-utils"
+version = "0.41.2"
+description = "Various utility functions for SQLAlchemy."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "SQLAlchemy-Utils-0.41.2.tar.gz", hash = "sha256:bc599c8c3b3319e53ce6c5c3c471120bd325d0071fb6f38a10e924e3d07b9990"},
+    {file = "SQLAlchemy_Utils-0.41.2-py3-none-any.whl", hash = "sha256:85cf3842da2bf060760f955f8467b87983fb2e30f1764fd0e24a48307dc8ec6e"},
+]
+
+[package.dependencies]
+SQLAlchemy = ">=1.3"
+
+[package.extras]
+arrow = ["arrow (>=0.3.4)"]
+babel = ["Babel (>=1.3)"]
+color = ["colour (>=0.0.4)"]
+encrypted = ["cryptography (>=0.6)"]
+intervals = ["intervals (>=0.7.1)"]
+password = ["passlib (>=1.6,<2.0)"]
+pendulum = ["pendulum (>=2.0.5)"]
+phone = ["phonenumbers (>=5.9.2)"]
+test = ["Jinja2 (>=2.3)", "Pygments (>=1.2)", "backports.zoneinfo", "docutils (>=0.10)", "flake8 (>=2.4.0)", "flexmock (>=0.9.7)", "isort (>=4.2.2)", "pg8000 (>=1.12.4)", "psycopg (>=3.1.8)", "psycopg2 (>=2.5.1)", "psycopg2cffi (>=2.8.1)", "pymysql", "pyodbc", "pytest (==7.4.4)", "python-dateutil (>=2.6)", "pytz (>=2014.2)"]
+test-all = ["Babel (>=1.3)", "Jinja2 (>=2.3)", "Pygments (>=1.2)", "arrow (>=0.3.4)", "backports.zoneinfo", "colour (>=0.0.4)", "cryptography (>=0.6)", "docutils (>=0.10)", "flake8 (>=2.4.0)", "flexmock (>=0.9.7)", "furl (>=0.4.1)", "intervals (>=0.7.1)", "isort (>=4.2.2)", "passlib (>=1.6,<2.0)", "pendulum (>=2.0.5)", "pg8000 (>=1.12.4)", "phonenumbers (>=5.9.2)", "psycopg (>=3.1.8)", "psycopg2 (>=2.5.1)", "psycopg2cffi (>=2.8.1)", "pymysql", "pyodbc", "pytest (==7.4.4)", "python-dateutil", "python-dateutil (>=2.6)", "pytz (>=2014.2)"]
+timezone = ["python-dateutil"]
+url = ["furl (>=0.4.1)"]
+
 [[package]]
 name = "sqlmodel"
 version = "0.0.16"
@@ -5263,18 +5291,18 @@ telegram = ["requests"]
 
 [[package]]
 name = "traitlets"
-version = "5.14.2"
+version = "5.14.3"
 description = "Traitlets Python configuration system"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "traitlets-5.14.2-py3-none-any.whl", hash = "sha256:fcdf85684a772ddeba87db2f398ce00b40ff550d1528c03c14dbf6a02003cd80"},
-    {file = "traitlets-5.14.2.tar.gz", hash = "sha256:8cdd83c040dab7d1dee822678e5f5d100b514f7b72b01615b26fc5718916fdf9"},
+    {file = "traitlets-5.14.3-py3-none-any.whl", hash = "sha256:b74e89e397b1ed28cc831db7aea759ba6640cb3de13090ca145426688ff1ac4f"},
+    {file = "traitlets-5.14.3.tar.gz", hash = "sha256:9ed0579d3502c94b4b3732ac120375cda96f923114522847de4b3bb98b96b6b7"},
 ]
 
 [package.extras]
 docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"]
-test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,<8.1)", "pytest-mock", "pytest-mypy-testing"]
+test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,<8.2)", "pytest-mock", "pytest-mypy-testing"]
 
 [[package]]
 name = "transformers"
@@ -6054,4 +6082,4 @@ server = ["fastapi", "uvicorn", "websockets"]
 [metadata]
 lock-version = "2.0"
 python-versions = "<3.13,>=3.10"
-content-hash = "591fab811980666e62dc6b33ed4248fbab38bf3fb6b63f9caa85f1a2c00ea1fa"
+content-hash = "81e487963aaa7b393d7bf71d603481b9fd515002f23f9aed9ebb9581b3fe9729"
diff --git a/pyproject.toml b/pyproject.toml
index 79c6173cfd..ba4d0beb39 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -54,6 +54,7 @@ llama-index-embeddings-openai = "^0.1.1"
 llama-index-embeddings-huggingface = {version = "^0.2.0", optional = true}
 llama-index-embeddings-azure-openai = "^0.1.6"
 python-multipart = "^0.0.9"
+sqlalchemy-utils = "^0.41.2"
 pytest-order = {version = "^1.2.0", optional = true}
 pytest-asyncio = {version = "^0.23.2", optional = true}
 pytest = { version = "^7.4.4", optional = true }
diff --git a/tests/test_client.py b/tests/test_client.py
index ac09de3a70..87192d34b6 100644
--- a/tests/test_client.py
+++ b/tests/test_client.py
@@ -38,8 +38,6 @@
 
 def run_server():
     import uvicorn
-    from memgpt.server.rest_api.server import app
-    from memgpt.server.rest_api.server import start_server
 
     load_dotenv()
 
@@ -98,7 +96,10 @@ def run_server():
     config.save()
     credentials.save()
 
-    print("Starting server...")
+    from memgpt.server.rest_api.server import app
+    from memgpt.server.rest_api.server import start_server
+
+    print("Starting server...", config.config_path)
     start_server(debug=True)
 
 
@@ -272,7 +273,8 @@ def test_sources(client, agent):
 
     # load a file into a source
     filename = "CONTRIBUTING.md"
-    response = client.load_file_into_source(filename=filename, source_id=source.id)
+    upload_job = client.load_file_into_source(filename=filename, source_id=source.id)
+    print("Upload job", upload_job, upload_job.status, upload_job.metadata)
 
     # TODO: make sure things run in the right order
     archival_memories = client.get_agent_archival_memory(agent_id=agent.id).archival_memory