Add OllamaTextVectorizer for local embedding workflows #492

Summary

Add an OllamaTextVectorizer to support local embedding models without external API keys.

Level: Intermediate

Current State

• RedisVL supports many hosted providers and local HF models.
• Ollama is a common local setup but has no first-class RedisVL vectorizer.

Proposed Change

• Implement OllamaTextVectorizer in redisvl/utils/vectorize/text/.
• Register provider in vectorizer enum/factory exports.
• Add optional dependency handling and clear startup errors.
• Add docs snippet and tests (mocked plus optional integration gate).

Definition of Done

• Ollama vectorizer can embed single and batch text.
• Optional dependency behavior is clear and non-breaking.
• Unit tests pass; optional integration path documented.

Out of Scope

• Supporting every Ollama model/task variant in the first pass.