agentjido / req_llm
52%
main: 53%

LAST BUILD BRANCH: feat/fixture-credential-fallback
DEFAULT BRANCH: main
Repo Added
Token Qrw4J5oDDoi2zjHqBZDp1Hok4eVoONJAy regen
Build 410 Last
Files 87
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

LAST BUILD ON BRANCH feat/google-context-caching
branch: feat/google-context-caching
CHANGE BRANCH
x
Sync Branches

coverage: 51.792% (-1.0%) from 52.762%
20cb655c7e63ec10c089c22690d0b034dda10c47-PR-193

Pull #193

github

neilberkman 
feat: Add Google Context Caching support for Gemini models

Adds explicit context caching API for Gemini models to reduce costs by up to
90% when reusing large amounts of content.

## Changes

- Add ReqLLM.Providers.Google.CachedContent module for cache CRUD operations
- Support for both Google AI Studio and Vertex AI (when Gemini support is added)
- Add cached_content provider option to reference existing caches
- Comprehensive tests for cache creation, listing, updating, and deletion
- Documentation and examples in Google provider moduledoc
- Updated CHANGELOG

## Usage

```elixir
# Create a cache
{:ok, cache} = ReqLLM.Providers.Google.CachedContent.create(
  provider: :google,
  model: "gemini-2.5-flash",
  api_key: System.get_env("GOOGLE_API_KEY"),
  contents: [%{role: "user", parts: [%{text: large_document}]}],
  ttl: "3600s"
)

# Use the cache in requests
{:ok, response} = ReqLLM.generate_text(
  "google:gemini-2.5-flash",
  "Question about the document?",
  provider_options: [cached_content: cache.name]
)

# Check cached tokens in usage
IO.inspect(response.usage.cached_tokens)
```

## Requirements

- Gemini 2.5 Flash: 1,024 minimum tokens
- Gemini 2.5 Pro: 4,096 minimum tokens
Pull Request #193: feat: Add Google Context Caching support for Gemini models

11 of 165 new or added lines in 2 files covered. (6.67%)

2 existing lines in 1 file now uncovered.

4003 of 7729 relevant lines covered (51.79%)

345.99 hits per line

Relevant lines Covered
7729 RELEVANT LINES 4003 COVERED LINES
345.99 HITS PER LINE
Source Files on feat/google-context-caching

Recent builds

Builds Branch Commit Type Ran Committer Via Coverage
20cb655c... feat/google-context-caching feat: Add Google Context Caching support for Gemini models Adds explicit context caching API for Gemini models to reduce costs by up to 90% when reusing large amounts of content. ## Changes - Add ReqLLM.Providers.Google.CachedContent module for... Pull #193 neilberkman github
51.79
See All Builds (410)

Badge your Repo: req_llm

We detected this repo isn’t badged! Grab the embed code to the right, add it to your repo to show off your code coverage, and when the badge is live hit the refresh button to remove this message.
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

Refresh