Skip to content

docs: document configurable Cohere reranker API URL #571

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
npeham wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: document configurable Cohere reranker API URL #571

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions content/docs/configuration/librechat_yaml/object_structure/web_search.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ webSearch:
jinaApiKey: "${JINA_API_KEY}"
jinaApiUrl: "${JINA_API_URL}"
cohereApiKey: "${COHERE_API_KEY}"
cohereApiUrl: "${COHERE_API_URL}"
rerankerType: "jina" # Options: "jina", "cohere", "none"

# General Settings
Expand Down Expand Up @@ -417,6 +418,16 @@ webSearch:

**Note:** Get your API key from [Cohere Dashboard](https://dashboard.cohere.com/welcome/login)

### cohereApiUrl

<OptionTable
options={[
['cohereApiUrl', 'String', 'Environment variable name for the Cohere API URL. If not set in .env, users will be prompted to provide it via UI.', '${COHERE_API_URL}'],
]}
/>

**Note:** This is optional and only needed if you're using a Cohere-compatible endpoint such as Azure AI Foundry's serverless deployments. Defaults to `https://api.cohere.com/v2/rerank`.

### rerankerType

<OptionTable
Expand Down
9 changes: 8 additions & 1 deletion content/docs/features/web_search.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,8 @@ To get started with web search, you'll need to configure API keys for a search p
JINA_API_URL=your_jina_api_url
# or
COHERE_API_KEY=your_cohere_api_key
# Optional: Custom Cohere API URL (e.g., Azure AI Foundry serverless deployment)
COHERE_API_URL=your_cohere_api_url
```

2. **User Interface** (If environment variables are not set):
Expand Down Expand Up @@ -134,6 +136,7 @@ Rerankers analyze the scraped content to determine the most relevant parts and r
- API URL is optional (defaults to Jina's hosted service)
- **Cohere**: Advanced reranking service
- Get your API key from [Cohere Dashboard](https://dashboard.cohere.com/welcome/login)
- API URL is optional (defaults to Cohere's hosted service; supports Azure AI Foundry serverless Cohere endpoints)
- **None**: Skips reranking when `rerankerType` is set to `"none"`

**Planned Rerankers:**
Expand Down Expand Up @@ -174,9 +177,11 @@ webSearch:
jinaApiKey: "${CUSTOM_JINA_API_KEY}"
jinaApiUrl: "${CUSTOM_JINA_API_URL}"
cohereApiKey: "${CUSTOM_COHERE_API_KEY}"
cohereApiUrl: "${CUSTOM_COHERE_API_URL}"
# jinaApiKey: "jn-123..." # ❌ Wrong: Never put actual API keys here
# jinaApiUrl: "https://..." # ❌ Wrong: Never put actual URLs here
# cohereApiKey: "ch-123..." # ❌ Wrong: Never put actual API keys here
# cohereApiUrl: "https://..." # ❌ Wrong: Never put actual URLs here

# General Settings
safeSearch: 1 # Options: 0 (OFF), 1 (MODERATE - default), 2 (STRICT)
Expand Down Expand Up @@ -208,7 +213,8 @@ If the admin hasn't configured all the necessary API keys, users will be prompte
2. Enter API keys for the required services
3. Configure the Firecrawl API URL if needed (optional)
4. Configure the Jina API URL if needed (optional)
5. Configure Tavily Search or Extract API URLs if needed (optional)
5. Configure the Cohere API URL if needed (optional)
6. Configure Tavily Search or Extract API URLs if needed (optional)

## Usage

Expand All @@ -222,6 +228,7 @@ Once configured, you can use web search in two ways:
- Search provider and scraper configuration are required; reranking can be disabled with `rerankerType: "none"`
- The Firecrawl API URL is optional and defaults to their hosted service
- The Jina API URL is optional and defaults to their hosted service
- The Cohere API URL is optional and defaults to their hosted service
- The Tavily Search and Extract API URLs are optional and default to Tavily's hosted services
- Safe search provides three levels of content filtering: OFF (0), MODERATE (1 - default), and STRICT (2)
- Tavily does not inherit the global `safeSearch` setting by default; use `tavilySearchOptions.safeSearch` only if your Tavily account supports `safe_search`
Expand Down