DataBricks¶

Integrate with DataBricks LLMs APIs.

Pre-requisites¶

• Databricks personal access token to query and access Databricks model serving endpoints.

• Databricks workspace in a supported region for Foundation Model APIs pay-per-token.

Setup¶

If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.

In [ ]:

% pip install llama-index-llms-databricks

% pip install llama-index-llms-databricks

In [ ]:

!pip install llama-index

!pip install llama-index

In [ ]:

from llama_index.llms.databricks import DataBricks

from llama_index.llms.databricks import DataBricks

None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

export DATABRICKS_API_KEY=<your api key>
export DATABRICKS_API_BASE=<your api serving endpoint>

Alternatively, you can pass your API key and serving endpoint to the LLM when you init it:

In [ ]:

llm = DataBricks(
    model="databricks-dbrx-instruct",
    api_key="your_api_key",
    api_base="https://[your-work-space].cloud.databricks.com/serving-endpoints/[your-serving-endpoint]",
)

llm = DataBricks( model="databricks-dbrx-instruct", api_key="your_api_key", api_base="https://[your-work-space].cloud.databricks.com/serving-endpoints/[your-serving-endpoint]", )

A list of available LLM models can be found here.

In [ ]:

response = llm.complete("Explain the importance of open source LLMs")

response = llm.complete("Explain the importance of open source LLMs")

In [ ]:

print(response)

print(response)

Call chat with a list of messages¶

In [ ]:

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality"
    ),
    ChatMessage(role="user", content="What is your name"),
]
resp = llm.chat(messages)

from llama_index.core.llms import ChatMessage messages = [ ChatMessage( role="system", content="You are a pirate with a colorful personality" ), ChatMessage(role="user", content="What is your name"), ] resp = llm.chat(messages)

In [ ]:

print(resp)

print(resp)

Streaming¶

Using stream_complete endpoint

In [ ]:

response = llm.stream_complete("Explain the importance of open source LLMs")

response = llm.stream_complete("Explain the importance of open source LLMs")

In [ ]:

for r in response:
    print(r.delta, end="")

for r in response: print(r.delta, end="")

Using stream_chat endpoint

In [ ]:

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality"
    ),
    ChatMessage(role="user", content="What is your name"),
]
resp = llm.stream_chat(messages)

from llama_index.core.llms import ChatMessage messages = [ ChatMessage( role="system", content="You are a pirate with a colorful personality" ), ChatMessage(role="user", content="What is your name"), ] resp = llm.stream_chat(messages)

In [ ]:

for r in resp:
    print(r.delta, end="")

for r in resp: print(r.delta, end="")