From 1d86fc84fe5c4c697ed58669810bd977aed21077 Mon Sep 17 00:00:00 2001
From: Cole McIntosh <82463175+colesmcintosh@users.noreply.github.com>
Date: Sat, 7 Jun 2025 10:13:03 -0600
Subject: [PATCH] Update web search documentation for new provider support
(xAI, VertexAI, Google AI Studio) (#11515)
* Update web_search.md to include new supported providers and models, enhance web search options, and improve documentation for using web search with various AI models.
* Update LiteLLM version in web_search.md to reflect the latest stable release.
* Fix formatting in web_search.md for model declaration consistency.
---
docs/my-website/docs/completion/web_search.md | 127 +++++++++++++++++-
1 file changed, 120 insertions(+), 7 deletions(-)
diff --git a/docs/my-website/docs/completion/web_search.md b/docs/my-website/docs/completion/web_search.md
index 7a67dc265e4..18ea8c9b4ff 100644
--- a/docs/my-website/docs/completion/web_search.md
+++ b/docs/my-website/docs/completion/web_search.md
@@ -8,9 +8,9 @@ Use web search with litellm
| Feature | Details |
|---------|---------|
| Supported Endpoints | - `/chat/completions`
- `/responses` |
-| Supported Providers | `openai` |
+| Supported Providers | `openai`, `xai`, `vertex_ai`, `gemini` |
| LiteLLM Cost Tracking | ✅ Supported |
-| LiteLLM Version | `v1.63.15-nightly` or higher |
+| LiteLLM Version | `v1.71.0+` |
## `/chat/completions` (litellm.completion)
@@ -31,8 +31,12 @@ response = completion(
"content": "What was a positive news story from today?",
}
],
+ web_search_options={
+ "search_context_size": "medium" # Options: "low", "medium", "high"
+ }
)
```
+
@@ -40,10 +44,30 @@ response = completion(
```yaml
model_list:
+ # OpenAI
- model_name: gpt-4o-search-preview
litellm_params:
model: openai/gpt-4o-search-preview
api_key: os.environ/OPENAI_API_KEY
+
+ # xAI
+ - model_name: grok-3
+ litellm_params:
+ model: xai/grok-3
+ api_key: os.environ/XAI_API_KEY
+
+ # VertexAI
+ - model_name: gemini-2-flash
+ litellm_params:
+ model: gemini-2.0-flash
+ vertex_project: your-project-id
+ vertex_location: us-central1
+
+ # Google AI Studio
+ - model_name: gemini-2-flash-studio
+ litellm_params:
+ model: gemini/gemini-2.0-flash
+ api_key: os.environ/GOOGLE_API_KEY
```
2. Start the proxy
@@ -64,7 +88,7 @@ client = OpenAI(
)
response = client.chat.completions.create(
- model="gpt-4o-search-preview",
+ model="grok-3", # or any other web search enabled model
messages=[
{
"role": "user",
@@ -81,6 +105,7 @@ response = client.chat.completions.create(
+**OpenAI (using web_search_options)**
```python showLineNumbers
from litellm import completion
@@ -98,6 +123,44 @@ response = completion(
}
)
```
+
+**xAI (using web_search_options)**
+```python showLineNumbers
+from litellm import completion
+
+# Customize search context size for xAI
+response = completion(
+ model="xai/grok-3",
+ messages=[
+ {
+ "role": "user",
+ "content": "What was a positive news story from today?",
+ }
+ ],
+ web_search_options={
+ "search_context_size": "high" # Options: "low", "medium" (default), "high"
+ }
+)
+```
+
+**VertexAI/Gemini (using web_search_options)**
+```python showLineNumbers
+from litellm import completion
+
+# Customize search context size for Gemini
+response = completion(
+ model="gemini-2.0-flash",
+ messages=[
+ {
+ "role": "user",
+ "content": "What was a positive news story from today?",
+ }
+ ],
+ web_search_options={
+ "search_context_size": "low" # Options: "low", "medium" (default), "high"
+ }
+)
+```
@@ -112,7 +175,7 @@ client = OpenAI(
# Customize search context size
response = client.chat.completions.create(
- model="gpt-4o-search-preview",
+ model="grok-3", # works with any web search enabled model
messages=[
{
"role": "user",
@@ -127,6 +190,8 @@ response = client.chat.completions.create(
+
+
## `/responses` (litellm.responses)
### Quick Start
@@ -253,25 +318,61 @@ print(response.output_text)
-Use `litellm.supports_web_search(model="openai/gpt-4o-search-preview")` -> returns `True` if model can perform web searches
+Use `litellm.supports_web_search(model="model_name")` -> returns `True` if model can perform web searches
```python showLineNumbers
+# Check OpenAI models
assert litellm.supports_web_search(model="openai/gpt-4o-search-preview") == True
+
+# Check xAI models
+assert litellm.supports_web_search(model="xai/grok-3") == True
+
+# Check VertexAI models
+assert litellm.supports_web_search(model="gemini-2.0-flash") == True
+
+# Check Google AI Studio models
+assert litellm.supports_web_search(model="gemini/gemini-2.0-flash") == True
```
-1. Define OpenAI models in config.yaml
+1. Define models in config.yaml
```yaml
model_list:
+ # OpenAI
- model_name: gpt-4o-search-preview
litellm_params:
model: openai/gpt-4o-search-preview
api_key: os.environ/OPENAI_API_KEY
model_info:
supports_web_search: True
+
+ # xAI
+ - model_name: grok-3
+ litellm_params:
+ model: xai/grok-3
+ api_key: os.environ/XAI_API_KEY
+ model_info:
+ supports_web_search: True
+
+ # VertexAI
+ - model_name: gemini-2-flash
+ litellm_params:
+ model: gemini-2.0-flash
+ vertex_project: your-project-id
+ vertex_location: us-central1
+ model_info:
+ supports_web_search: True
+
+ # Google AI Studio
+ - model_name: gemini-2-flash-studio
+ litellm_params:
+ model: gemini/gemini-2.0-flash
+ api_key: os.environ/GOOGLE_API_KEY
+ model_info:
+ supports_web_search: True
```
2. Run proxy server
@@ -298,7 +399,19 @@ Expected Response
"model_group": "gpt-4o-search-preview",
"providers": ["openai"],
"max_tokens": 128000,
- "supports_web_search": true, # 👈 supports_web_search is true
+ "supports_web_search": true
+ },
+ {
+ "model_group": "grok-3",
+ "providers": ["xai"],
+ "max_tokens": 131072,
+ "supports_web_search": true
+ },
+ {
+ "model_group": "gemini-2-flash",
+ "providers": ["vertex_ai"],
+ "max_tokens": 8192,
+ "supports_web_search": true
}
]
}