ollama-chromadb-sqlite , "RAG document is not being used — zero retrieval, Ollama ignores it" #1003
Replies: 1 comment
-
|
@zainhoda model='qwen2.5-coder:14b' created_at='2025-11-13T10:17:10.669570031Z' done=True done_reason='stop' total_duration=7139062357 load_duration=6414092905 prompt_eval_count=15 prompt_eval_duration=27353395 eval_count=67 eval_duration=552871053 message=Message(role='assistant', content='I'm sorry, but I couldn't find any information about that's related to a company or its services. It would be helpful if you could provide more context or clarify your question. Are you looking for information about a specific industry or type of business? Please let me know so I can assist you better.', thinking=None, images=None, tool_name=None, tool_calls=None) |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
@zainhoda
code :- [ vanna version 0.7 ]
note:- running locally not using google collab.
from vanna.chromadb import ChromaDB_VectorStore
class MyVanna(ChromaDB_VectorStore, Ollama):
def init(self, config=None):
ChromaDB_VectorStore.init(self, config=config)
Ollama.init(self, config=config)
vn = MyVanna(config={'model': 'qwen2.5-coder:14b'})
vn.connect_to_sqlite('/home/my_database.db')
vn.allow_llm_to_see_data = True
vn.train(documentation='/home/RAG_json_format_3')
training_data = vn.get_training_data()
print(training_data)
vn.ask(question= ' ')
error :- hallucinating no proper context failling
Beta Was this translation helpful? Give feedback.
All reactions