Gradient Model Adapter

%pip install llama-index-embeddings-langchain
%pip install llama-index-llms-gradient

%pip install llama-index --quiet
%pip install gradientai --quiet

import os

os.environ["GRADIENT_ACCESS_TOKEN"] = "{GRADIENT_ACCESS_TOKEN}"
os.environ["GRADIENT_WORKSPACE_ID"] = "{GRADIENT_WORKSPACE_ID}"

Flow 1: Query Gradient LLM directly

from llama_index.llms.gradient import GradientModelAdapterLLM

llm = GradientModelAdapterLLM(
    model_adapter_id="{YOUR_MODEL_ADAPTER_ID}",
    max_tokens=400,
)

result = llm.complete("Can you tell me about large language models?")
print(result)

Flow 2: Retrieval Augmented Generation (RAG) with Gradient LLM

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.embeddings.langchain import LangchainEmbedding
from langchain.embeddings import HuggingFaceEmbeddings

Download Data

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

Load Documents

documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

Configure Gradient LLM

embed_model = LangchainEmbedding(HuggingFaceEmbeddings())
splitter = SentenceSplitter(chunk_size=1024)

Setup and Query Index

index = VectorStoreIndex.from_documents(
    documents,
    transformations=[splitter],
    embed_model=embed_model,
)
query_engine = index.as_query_engine(llm=llm)

response = query_engine.query(
    "What did the author do after his time at Y Combinator?"
)
print(response)