# Persistence Knowledge

**URL:** <https://community.crewai.com/t/persistence-knowledge/6574>\
**Category:** CrewAI Community Support\
**Tags:** crewai\
**Created:** [July 15, 2025, 3:04am UTC](https://community.crewai.com/t/persistence-knowledge/6574 "2025-07-15T03:04:49Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Amado\_Tairone](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/amado_tairone/32/4094_2.png) [@Amado\_Tairone](https://community.crewai.com/u/Amado_Tairone)\
**Post date:** [July 15, 2025, 3:04am UTC](https://community.crewai.com/t/persistence-knowledge/6574/1 "2025-07-15T03:04:49Z")

</div>

My Crewai app generates the storage bank but it doesn’t reuse the saved embeddings when I run the app again. I have local storage set to:

```python
custom_storage_dir = Path( __file__ ).parent / "storage"
os.environ["CREWAI_STORAGE_DIR"] = str(custom_storage_dir). 

```

My script:

```python
import os
from pathlib import Path

custom_storage_dir = Path( __file__ ).parent / "storage"
os.environ["CREWAI_STORAGE_DIR"] = str(custom_storage_dir)

from crewai import Agent, Task, Crew, Process
from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource

custom_storage = KnowledgeStorage( 
embedder={ 
"provider": "openai", 
"config": {"model": "text-embedding-3-small"}
},
collection_name="custom_dba",

)

doc_sources = TextFileKnowledgeSource(
file_paths=["estrutura_db.txt"])

doc_sources.storage = custom_storage

agent = Agent(
role="Answer only SQL-related questions, always using very short answers.",
goal="Display queries according to the question and show the query results.",
backstory="You are an assistant who helps users solve SQL problems. You have access to documentation and in-depth knowledge of SQL.",
verbose=True,
allow_delegation=False,
memory=True,
knowledge_sources=[doc_sources],

)

```

If I ask the same question again, it regenerates the 14,000 tokens from my txt file. When I run the app, it always asks the same question and generates 14,000 tokens again.

I ran this script

```python
from pathlib import Path
import them

# Configuration of the storage directory
custom_storage_dir = Path( __file__ ).parent / "storage"
os.environ["CREWAI_STORAGE_DIR"] = str(custom_storage_dir)

import chromadb
from crewai.utilities.paths import db_storage_path

# Connect to CrewAI's ChromaDB
storage_path = db_storage_path()
chroma_path = os.path.join(storage_path, "knowledge")

if os.path.exists(chroma_path): 
client = chromadb.PersistentClient(path=chroma_path) 
collections = client.list_collections() 

print("ChromaDB Collections:") 
for collection in collections: 
print(f" - {collection.name}: {collection.count()} documents")
else:
print("No ChromaDB storage found")

print("CREWAI_STORAGE_DIR:", os.getenv("CREWAI_STORAGE_DIR"))
print("Current working directory:", os.getcwd())
print("Computed storage path:", db_storage_path())

```

And I got this result:

```bash
E:\projects\api_teste_python
(.venv) λ python pa.py
ChromaDB Collections:
- knowledge_Answer_only_SQL_related_questions__uses: 13 documents
CREWAI_STORAGE_DIR: E:\projects\api_teste_python\storage
Current working directory: E:\projects\api_teste_python
Computed storage path: E:\projects\api_test_python\storage

```

What I can’t understand, since it stores the embeddings, is why every time I ask a question, it sends the entire document to text-embedding-3-small.  
In the tokenizer, my document gives 14,000 tokens, and every time I ask a question, I check the text-embedding-3-small dashboard, and it increases by 14,000, so it doesn’t update anything.

Note: The question is always the same one embedded in the script.

---

<div class="post-metadata">

**Author:** ![tonykipkemboi](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/tonykipkemboi/32/4070_2.png) [@tonykipkemboi](https://community.crewai.com/u/tonykipkemboi)\
**Post date:** [July 15, 2025, 12:51pm UTC](https://community.crewai.com/t/persistence-knowledge/6574/2 "2025-07-15T12:51:21Z")

</div>

firstly, i noticed your storage paths don’t match. was this intentional or am missing something?

- `CREWAI_STORAGE_DIR: E:\projects\api_teste_python\storage`
- `Computed storage path: E:\projects\api_test_python\storage`

secondly, try using crew-level knowledge sources instead of agent-level and see if that fixes the issue.

---

<div class="post-metadata">

**Author:** ![Amado\_Tairone](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/amado_tairone/32/4094_2.png) [@Amado\_Tairone](https://community.crewai.com/u/Amado_Tairone)\
**Post date:** [July 15, 2025, 1:38pm UTC](https://community.crewai.com/t/persistence-knowledge/6574/3 "2025-07-15T13:38:25Z")

</div>

Hi, thanks for replying!  
I used os.environ[“CREWAI\_STORAGE\_DIR”] = str(Path( **file** ).parent / “storage”).

My script:  
import os  
from pathlib import Path  
from crewai import Agent, Task, Crew, Process, LLM  
from crewai.knowledge.source.text\_file\_knowledge\_source import TextFileKnowledgeSource  
import warnings  
warnings.filterwarnings(“ignore”)

os.environ[“CREWAI\_STORAGE\_DIR”] = str(Path( **file** ).parent / “storage”)

doc\_sources = TextFileKnowledgeSource(  
file\_paths=[“estrutura\_db.txt”])

llm = LLM(  
model=“gpt-4.1-nano-2025-04-14”,  
max\_tokens=150,  
temperature=0,  
)

agent = Agent(  
role=“Responda apenas perguntas relacionadas a SQL, utilizando sempre respostas super curtas.”,  
goal=“Mostrar as queries de acordo com a pergunta e mostrar os resultados da consulta.”,  
backstory=“Você é um assistente que ajuda os usuários a resolver problemas de SQL. Tem acesso a documentação e conhecimento profundo sobre sql.”,  
verbose=True,  
allow\_delegation=False,  
memory= True,  
llm=llm,

)

task = Task(  
description=“Interaja com o usuario: {question}”,  
expected\_output=“Uma resposta a interação.”,  
agent=agent,  
)

crew = Crew(  
agents=[agent],  
tasks=[task],  
verbose=True,  
knowledge\_sources=[doc\_sources],  
memory=True,  
process=Process.sequential,  
)

result = crew.kickoff(inputs={“question”: “mostre os campos que tem chave estrangeira na channel”})  
print(result)

Even at crew-level knowledge sources, the complete content of the doc is still sent to the model.