LlamaIndex
Log in

Find answers from the community

Home
Members
Vishwas
V
Vishwas
Offline, last seen last week
Joined September 25, 2024
VVishwas
·

Insufficient Balance Error When Using Deepseek API Key

Hy @Logan M
When i'm using deepseek api key then its showing :
Plain Text
openai.APIStatusError: Error code: 402 - {'error': {'message': 'Insufficient Balance', 'type': 'unknown_error', 'param': None, 'code': 'invalid_request_error'}}


This is my source code:
Plain Text
from llama_index.llms.deepseek import DeepSeek

# Set up the DeepSeek class with the required model and API key

llm = DeepSeek(model="deepseek-chat", api_key="******************")

# Call the complete method with a query
response = llm.complete("Explain the importance of low latency LLMs")

print(f'Response: {response}')
1 comment
L
VVishwas
·

Hello guys, When I execute this piece

Hello guys, When I execute this piece of code
Plain Text
from llama_index.core.postprocessor import SentenceTransformerRerank
rerank = SentenceTransformerRerank(
            model="cross-encoder/ms-marco-MiniLM-L-2-v2", top_n=3
        )


Then this error will occur.
ImportError: ('Cannot import sentence-transformers or torch package,', 'please pip install torch sentence-transformers')

Even though I have already installed these packages properly, the error still occurs.
10 comments
L
V
W
VVishwas
·

TTS

Hello guys,
Is it possible to voice chat with OpenAI (any gpt model) without converting speech-to-text or text-to-speech?
I was thinking of sending a prompt in audio format and having GPT also give a response in audio format.
3 comments
V
W
VVishwas
·

Hi, @Logan M

Hi,
Can we use VectorStore in the llama_index Ollama (LLaMA 3 model)? using Qdrant
My task is to chat with my own document, which is uploaded on the Quadrant server, chat using Ollama (LLaMA 3 model).
26 comments
V
W
L
VVishwas
·

Hello, instead of

Hello, instead of SentenceTransformerRerank, which node postprocessor is the best?
5 comments
V
W
VVishwas
·

Hello guys, @Logan M , @WhiteFang_Jr

Hello guys, @Logan M , @WhiteFang_Jr
I am facing some issue with torch module in llama-index.
Plain Text
ImportError: libcufft.so.11: failed to map segment from shared object

how can i fixed this issue
2 comments
L
V
VVishwas
·

Hello guys, i used below code.

Hello guys, i used below code.

rerank = SentenceTransformerRerank(
model="cross-encoder/ms-marco-MiniLM-L-2-v2", top_n=3
)
response_synthesizer = get_response_synthesizer(streaming=True)
try:
vector_retriever = self._vector_index.as_retriever(
similarity_top_k=10)
keyword_retriever = self._keyword_index.as_retriever()
custom_retriever = CustomRetriever(
vector_retriever, keyword_retriever)
custom_query_engine = RetrieverQueryEngine(
retriever=custom_retriever, response_synthesizer=response_synthesizer, node_postprocessors=[rerank])
response = custom_query_engine.query(query)
answer = generatorize_response(response.response_gen)

But getting the error :
tenacity.RetryError: RetryError[<Future at 0x7c4b17a48610 state=finished raised APIRemovedInV1>]

in this line of execution(response = custom_query_engine.query(query).
10 comments
L
V