Registry / llm-agents / llama-index-llms-vertex

llama-index-llms-vertex

library0.7.0pypypi✓ verified 84d ago

LlamaIndex integration for Google Vertex AI LLMs (e.g., Gemini, PaLM). Allows using Vertex AI models as LLMs within LlamaIndex. Current version 0.7.0, release cadence is frequent (weekly/biweekly).

llm-agents ai-ml gcp

pip install llama-index-llms-vertex

package ↗homepage ↗

INSTALL

IMPORT

SIG · LLAMA-INDEX-LLMS-V

llama-index-llms-vertex

llm-agentspythonv0.7.0

Install

30.6s avg

Import

19829ms

Disk

479MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.7.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 20.478s · 457.3MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 30.6s · import 11.248s · 451MB

479MB installed

● package 479MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

Vertex

✓ from llama_index.llms.vertex import Vertex

✗ from llama_index.llms import Vertex

Correct import is the submodule path, not the top-level llms.

Initialize Vertex LLM with a Gemini model and call complete().

import os from llama_index.llms.vertex import Vertex # Ensure credentials are set os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'path/to/service-account.json' llm = Vertex( model='gemini-2.0-flash-001', project='your-project-id', location='us-central1', ) resp = llm.complete('Hello, who are you?') print(resp)

Debug

Known issues

breakingVersion 0.7.0 changed default model from 'text-bison' to 'gemini-2.0-flash-001'. Existing code using default model will break if you rely on PaLM behavior.

fix

Explicitly set model parameter to your desired model (e.g., 'text-bison@001').

affects: >=0.7.0

deprecatedThe 'temperature', 'max_tokens', etc. kwargs in the constructor are deprecated in favor of passing them to the call (complete/chat) methods. Constructor params may be removed in future version.

fix

Pass generation config via generation_config dict or kwargs at call time instead of constructor.

affects: >=0.6.0

gotchaAuthentication requires a service account JSON or ADC. Forgetting to set GOOGLE_APPLICATION_CREDENTIALS raises a vague google.auth.exceptions.DefaultCredentialsError.

fix

Ensure credentials are set via environment variable or `google.auth.default()` is configured.

affects: all

gotchaModel names must match exactly what Vertex AI expects (e.g., 'gemini-2.0-flash-001', not 'gemini-pro'). Using an invalid model raises a 404 or 400 error.

fix

Refer to Vertex AI documentation for exact model names. Use `Vertex.available_models()` to list supported models.

affects: all

Errors

Common errors & fixes

google.auth.exceptions.DefaultCredentialsError: Could not automatically determine credentials.

Missing or misconfigured Google Cloud credentials (service account file or ADC).

fix

Set GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your service account JSON, or run `gcloud auth application-default login`.

google.api_core.exceptions.InvalidArgument: 400 Request contains an invalid argument.

Invalid model name or region. For example, using 'gemini-pro' instead of 'gemini-2.0-flash-001'.

fix

Double-check model name and location. Use `Vertex.available_models()` to see supported models for your project.

ModuleNotFoundError: No module named 'llama_index.llms.vertex'

Wrong import path. Users often try `from llama_index.llms import Vertex` but that doesn't work.

fix

Use correct import: `from llama_index.llms.vertex import Vertex`.

TypeError: __init__() got an unexpected keyword argument 'temperature'

Constructor parameters like temperature, max_tokens are deprecated/removed in recent versions.

fix

Pass temperature and other generation config as keyword arguments to `llm.complete()` or `llm.chat()` instead of constructor.

Upgrade

Version history

0.7.0latest on PyPI · released Mar 12, 2026

Audit

Dependencies

google-cloud-aiplatformrequiredRequired for Vertex AI API calls

Agent activity

18 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/llama-index-llms-vertex/ ↗

homepagehttps://llamahub.ai/l/llms/vertex ↗