360

[1atAlcone]

def generate_llm_response(messages, processed_results) -> str:
SYSTEM_PROMPT = """You're an AI assistant that writes technical documentation. You can search a vector store for
information relevant to the user's query. Use the provided vector store results to inform your response, but don't
mention the vector store directly."""

vs_results = "\n=========\n".join(
    [f"{result.get('chunk_text', 'No text available')}" for result in processed_results]
)
messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    *messages,
    {
        "role": "system",
        "content": f"User query: {messages[-1]['content']}\n\nRelevant information:\n{vs_results}",
    },
]
return inference.completions(model="qwen2p5-72b-instruct", messages=messages, max_tokens=16000)

Get an LLM response using the vector store

search_query = "example search query"
client_config = ClientConfig(base_url=CONFIG.nearai_hub.base_url, auth=CONFIG.auth)
inference = InferenceRouter(client_config)
vector_results = inference.query_vector_store(vs.id, search_query)
processed_results = process_vector_results([vector_results])
llm_response = generate_llm_response(messages, processed_results)
print(llm_response["choices"][0]["message"]["content"])