…ease

DeepInfra based models do not seem to support json schema. See
https://deepinfra.com/docs/advanced/json_mode for reference

Reaching >94% in research mode on SimpleQA. When answers can be
researched online, it becomes too easy. And the FRAMES eval does a
more thorough job of evaluating that use-case anyway.

This env var was already being used to set seed for OpenAI and Offline
models

Previously google auth library was explicitly installed only for the
cloud variant of Khoj to minimize packages installed for non
production use-cases.

But it was being implicitly installed as a dependency of an explicit
package in the default installation anyway.

Making the dependency on google auth package explicit simplifies
the conditional import of google auth in code while not incurring any
additional cost in terms of space or complexity.

- The 3.4.1 release of sentence tranformer fixes offline load latency
  of sentence transformer models (and Khoj) by avoiding call to HF

- The 4.50.0 release of transformers is resulting in
  jax error (unexpected keyword argument 'flatten_with_keys') on load.

Enable configuring a Khoj AI model API for Vertex AI using GCP credentials.

Specifically use the api key & api base url fields of the AI Model API
associated with the current chat model to extract gcp region, gcp
project id & credentials. This helps create a AnthropicVertex client.

The api key field should contain the GCP service account keyfile as a
base64 encoded string.

The api base url field should be of the form
`https://{MODEL_GCP_REGION}-aiplatform.googleapis.com/v1/projects/{YOUR_GCP_PROJECT_ID}`

Accepting GCP credentials via the AI model API makes it easy to use
across local and cloud environments. As it bypasses the need for a
separate service account key file on the Khoj server.

Support accessing Claude and Gemini AI models via Vertex AI on Google Cloud. 

See the documentation at docs.khoj.dev for setup details

…nges

- Anthropic expects a 0-1 range. Gemini & OpenAI expect a 0-2 range
- Anneal temperature to explore reasoning trajectories but respond factually
- Default send_message_to_model and extract_question temps to the same