feat: add (openai, anthropic, gemini) providers via litellm (#1267)

# What does this PR do?

This PR introduces more non-llama model support to llama stack.
Providers introduced: openai, anthropic and gemini. All of these
providers use essentially the same piece of code -- the implementation
works via the `litellm` library.

We will expose only specific models for providers we enable making sure
they all work well and pass tests. This setup (instead of automatically
enabling _all_ providers and models allowed by LiteLLM) ensures we can
also perform any needed prompt tuning on a per-model basis as needed
(just like we do it for llama models.)

## Test Plan

```bash
#!/bin/bash

args=("$@")
for model in openai/gpt-4o anthropic/claude-3-5-sonnet-latest gemini/gemini-1.5-flash; do
    LLAMA_STACK_CONFIG=dev pytest -s -v tests/client-sdk/inference/test_text_inference.py \
        --embedding-model=all-MiniLM-L6-v2 \
        --vision-inference-model="" \
        --inference-model=$model "${args[@]}"
done
```

llama_stack/templates/dev/build.yaml

@@ -0,0 +1,36 @@
+version: '2'
+distribution_spec:
+  description: Distribution for running e2e tests in CI
+  providers:
+    inference:
+    - remote::openai
+    - remote::fireworks
+    - remote::anthropic
+    - remote::gemini
+    - inline::sentence-transformers
+    vector_io:
+    - inline::sqlite-vec
+    - remote::chromadb
+    - remote::pgvector
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+    eval:
+    - inline::meta-reference
+    datasetio:
+    - remote::huggingface
+    - inline::localfs
+    scoring:
+    - inline::basic
+    - inline::llm-as-judge
+    - inline::braintrust
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::code-interpreter
+    - inline::rag-runtime
+    - remote::model-context-protocol
+image_type: conda