Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

FixedSizeList is not the same. input list: fixed_size_list<item: float>[3072] output list: fixed_size_list<item: float>[4096] #1857

Open
AhmadShaik opened this issue Jan 22, 2025 · 2 comments

Comments

@AhmadShaik
Copy link

Exception has occurred: ArrowTypeError
Size of FixedSizeList is not the same. input list: fixed_size_list<item: float>[3072] output list: fixed_size_list<item: float>[4096]
File "/media/ahamad/work/projects/auto_zone/Autozone_experiments/knowledge_base.py", line 47, in
knowledge_base.load(recreate=False)
pyarrow.lib.ArrowTypeError: Size of FixedSizeList is not the same. input list: fixed_size_list<item: float>[3072] output list: fixed_size_list<item: float>[4096]

@ysolanky
Copy link
Contributor

Hello @AhmadShaik! Can you please share your Agent config including the config for the knowledge base?

@AhmadShaik
Copy link
Author

@ysolanky - here is the agent config and the knowledge base config. The error poppedup at the knowledge_base.load()

txt_path = "/directory/path/to/files"
# # html_paths = get_sds_paths(pdf_dir, extn=".html")  
# chunking_strategy=SemanticChunking()

vector_db = LanceDb(
    table_name="auto_zone",
    uri="/tmp/lancedb",
    embedder=OllamaEmbedder()
)

knowledge_base = PDFKnowledgeBase(
    path=txt_path,
    vector_db=vector_db,     
    # vector_db=ChromaDb(collection="auto_zone", embedder=OllamaEmbedder()),
    # chunking_strategy=SemanticChunking()
    chunking_strategy=FixedSizeChunking()
)

knowledge_base.load(recreate=False)

agent = Agent(
    knowledge_base=knowledge_base,
    search_knowledge=True,
)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants