Predibase¶

This notebook shows how you can use Predibase-hosted LLM's within Llamaindex. You can add Predibase to your existing Llamaindex worklow to:

1. Deploy and query pre-trained or custom open source LLM’s without the hassle
2. Operationalize an end-to-end Retrieval Augmented Generation (RAG) system
3. Fine-tune your own LLM in just a few lines of code

Getting Started¶

1. Sign up for a free Predibase account here
2. Create an Account
3. Go to Settings > My profile and Generate a new API Token.

In [ ]:

%pip install llama-index-llms-predibase

%pip install llama-index-llms-predibase

In [ ]:

!pip install llama-index --quiet
!pip install predibase --quiet
!pip install sentence-transformers --quiet

!pip install llama-index --quiet !pip install predibase --quiet !pip install sentence-transformers --quiet

In [ ]:

import os

os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
from llama_index.llms.predibase import PredibaseLLM

import os os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}" from llama_index.llms.predibase import PredibaseLLM

Flow 1: Query Predibase LLM directly¶

In [ ]:

llm = PredibaseLLM(
    model_name="llama-2-13b", temperature=0.3, max_new_tokens=512
)
# You can query any HuggingFace or fine-tuned LLM that's hosted on Predibase

llm = PredibaseLLM( model_name="llama-2-13b", temperature=0.3, max_new_tokens=512 ) # You can query any HuggingFace or fine-tuned LLM that's hosted on Predibase

In [ ]:

result = llm.complete("Can you recommend me a nice dry white wine?")
print(result)

result = llm.complete("Can you recommend me a nice dry white wine?") print(result)

Flow 2: Retrieval Augmented Generation (RAG) with Predibase LLM¶

In [ ]:

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core.embeddings import resolve_embed_model
from llama_index.core.node_parser import SentenceSplitter

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader from llama_index.core.embeddings import resolve_embed_model from llama_index.core.node_parser import SentenceSplitter

Download Data¶

In [ ]:

!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'

!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¶

In [ ]:

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

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

Configure Predibase LLM¶

In [ ]:

llm = PredibaseLLM(
    model_name="llama-2-13b",
    temperature=0.3,
    max_new_tokens=400,
    context_window=1024,
)

llm = PredibaseLLM( model_name="llama-2-13b", temperature=0.3, max_new_tokens=400, context_window=1024, )

In [ ]:

embed_model = resolve_embed_model("local:BAAI/bge-small-en-v1.5")
splitter = SentenceSplitter(chunk_size=1024)

embed_model = resolve_embed_model("local:BAAI/bge-small-en-v1.5") splitter = SentenceSplitter(chunk_size=1024)

Setup and Query Index¶

In [ ]:

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 growing up?")

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 growing up?")

In [ ]:

print(response)

print(response)