examples: change maximum tokens from 104 to 1024 in openai_chat_example.go as it says in README.md of the example
Fixing a typo of llms.WithMaxtokens(104) to llms.WithMaxtokens(1024)
chore: update all examples to use v0.1.14-pre.4
- Remove replace directives from 5 examples that had local path references
- Update all 75 example go.mod files to use the latest pre-release version
- Ensures examples work correctly for users who clone the repository
docs: complete basic chat application tutorial with progressive examples
Completely rewrite the basic chat application tutorial with a structured, step-by-step approach:
**Tutorial Documentation**:
- Restructure tutorial into 6 clear progressive steps
- Add proper setup instructions and prerequisites
- Include code examples for each step with explanations
- Improve clarity and flow from basic to advanced concepts
**Complete Working Example**:
- Add `examples/tutorial-basic-chat-app/` with full implementation
- Include separate files for each tutorial step (step3-step6)
- Add comprehensive README with usage instructions
- Support multiple execution modes via command-line arguments
**Progressive Implementation Steps**:
- Step 3: Basic single-shot LLM interaction
- Step 4: Interactive chat loop without memory
- Step 5: Chat with manual conversation memory management
- Step 6: Advanced chat using chains with automatic memory
**Features Added**:
- Go module setup with proper dependencies
- Error handling and graceful exit functionality
- Multiple chat implementations demonstrating different approaches
- Clear documentation linking tutorial to working code
- Support for running individual steps or complete implementation
The tutorial now provides a complete learning path from basic LLM usage to sophisticated conversation management using LangChainGo's chains and memory systems.
* llms: add prompt caching and reasoning token support
Add comprehensive infrastructure for prompt caching and reasoning/thinking tokens:
- Add ReasoningModel interface for models supporting extended reasoning
- Add CacheControl and CachedContent types for prompt caching
- Add ThinkingConfig with modes (none, low, medium, high, auto)
- Add token budget calculation and usage tracking for thinking tokens
- Add WithPromptCaching, WithThinking, and related call options
- Add model detection for reasoning-capable models (OpenAI o1/o3, Claude 3.7+, DeepSeek)
- Update options documentation for better provider compatibility notes
- Remove testify imports tracking file
Supports provider-specific implementations while maintaining consistent API.
* testing: add comprehensive LLM testing framework
Add standardized testing infrastructure for all LLM providers following Go's testing/fstest design philosophy:
- Add llmtest package with automatic capability discovery and parallel testing
- Add TestLLM function that probes and tests all supported LLM features
- Add provider-specific test files for all LLM implementations (anthropic, bedrock, cloudflare, cohere, ernie, fake, googleai, huggingface, llamafile, local, maritaca, mistral, ollama, openai, watsonx)
- Add comprehensive tests for prompt caching, reasoning tokens, and token utilization
- Add MockLLM implementation for testing without API calls
- Add ValidateLLM function for basic model validation
- Support automatic detection of streaming, tool calls, reasoning, and caching capabilities
The framework provides a simple API (TestLLM) that automatically discovers and tests all supported capabilities, enabling consistent testing across all provider implementations.
* llms: implement provider-specific prompt caching and reasoning support
Add comprehensive provider-specific implementations for prompt caching and reasoning tokens:
**Anthropic (Claude)**:
- Add prompt caching with ephemeral cache controls and beta headers
- Add extended thinking support for Claude 3.7+ with budget token configuration
- Add interleaved thinking for tool calls and 128K output support
- Add thinking content extraction from <thinking> tags
- Add cache token tracking (creation/read input tokens)
**Google AI (Gemini)**:
- Add CachingHelper for pre-created cached content management
- Add reasoning detection for Gemini 2.0+ models
- Add cached content support via metadata
- Add standardized token usage reporting with cache information
**Ollama**:
- Add ContextCache for in-memory conversation context caching
- Add reasoning support detection for DeepSeek R1, QwQ, and thinking models
- Add Think parameter support for reasoning-capable models
- Add cache statistics and hit/miss tracking
**OpenAI**:
- Add reasoning support detection for o1/o3 series and future GPT-5
- Add system message handling for models without system support (o1/o3)
- Add thinking content extraction and standardized token reporting
- Add metadata filtering to prevent internal fields from reaching API
- Add ReasoningEffort parameter preparation for future models
**Cross-provider features**:
- Implement ReasoningModel interface across all providers
- Add standardized GenerationInfo fields (ThinkingContent, ThinkingTokens, etc.)
- Add provider-specific options (WithPromptCaching, WithExtendedOutput, etc.)
- Add comprehensive test coverage for caching and reasoning features
- Add model capability detection and validation
All providers now support the unified prompt caching and reasoning interfaces while maintaining their specific implementation details and capabilities.
* examples: add comprehensive prompt caching and reasoning examples
Add practical examples demonstrating prompt caching and reasoning token features across multiple LLM providers:
**Anthropic Examples**:
- Add anthropic-extended-capabilities example showing combined extended thinking + 128K output
- Add anthropic-interleaved-thinking example demonstrating thinking between tool calls
- Show token budget management and thinking content extraction
- Include comprehensive README documentation for each example
**Multi-Provider Examples**:
- Add googleai-reasoning-caching example with Gemini 2.0+ reasoning and cached content
- Add ollama-reasoning-caching example with DeepSeek R1/QwQ models and context caching
- Add prompt-caching example showing Anthropic's 90% cost reduction on cached tokens
- Add reasoning-tokens example comparing o1-mini, Claude 3.7, and standard models
**Key Features Demonstrated**:
- Prompt caching for cost optimization and faster responses
- Reasoning/thinking tokens for improved response quality
- Token usage analysis and cache hit/miss tracking
- Provider-specific capabilities and configuration options
- Real-world use cases like data analysis, Q&A systems, and multi-step reasoning
All examples include detailed documentation, error handling, and clear output formatting to help developers understand and implement these advanced LLM features.
* gofmt: fix formatting in messages.go
examples/groq: add temporary replace directive
Add replace directive to use local langchaingo module. This ensures the example
works with the current codebase that includes the metadata filtering fix from
PR #1376.
The replace directive should be removed after the next release.
Update all example project go.mod files to reference v0.1.14-pre.3
instead of v0.1.14-pre.2. This ensures examples use the latest pre-release
version with recent fixes and improvements.
Update all example project go.mod files to reference v0.1.14-pre.2
instead of v0.1.14-pre.1. This ensures examples use the latest pre-release
version with recent fixes and improvements.
* build: add examples-updater tool and update examples to v0.1.14-pre.1
Add a new tool to automate updating langchaingo version references in example
projects and use it to update all examples to v0.1.14-pre.1. The tool also
removes temporary replace directives that are no longer needed.
- Add update-examples Makefile target that runs the new tool
- Create internal/devtools/examples-updater implementation
- Update all example go.mod files to reference v0.1.14-pre.1
- Remove replace directives in googleai and vertex examples
- Update dependencies in main go.mod/go.sum
* httprr: improve header normalization and test container setup
Add header normalization to make HTTP recordings more stable:
- Add normalizeGoogleAPIClientHeader and normalizeVersionHeader functions
- Normalize User-Agent, x-goog-api-client and other version headers
- Remove OpenAI-Project header for consistency
- Preserve body for both replay lookup and recording
- Add comprehensive tests for header normalization
Improve testcontainer environment detection:
- Better handling of non-standard Docker socket paths
- Disable Ryuk reaper by default for resource efficiency
- Add verbose logging option via environment variable
* httputil: add ApiKeyTransport for query parameter API keys
Add a reusable ApiKeyTransport that adds API keys to URL query parameters:
- Create ApiKeyTransport implementation in httputil package
- Add comprehensive tests for the new transport
- Refactor googleai_test.go to use the shared transport
- Update chains/llm_test.go to use ApiKeyTransport with proper key scrubbing
This improves how API keys are handled with client libraries that don't
properly set keys when using custom HTTP clients, particularly useful
with httprr for testing Google API integrations.
* openai: remove duplicate MaxTokens field assignment
Remove redundant assignment where both MaxTokens and MaxCompletionTokens
were being set to the same value. MaxCompletionTokens is the preferred
field name that reflects OpenAI's API changes, while MaxTokens was
previously kept for backward compatibility.
* vectorstores/maridadb: add test infrastructure for MariaDB vectorstore
Add TestMain function for MariaDB vectorstore tests that ensures the proper
test environment is set up using the testctr package. This enables consistent
test container setup and teardown for MariaDB integration tests.
* all: normalize all httprr recordings for consistency
Update test recordings across all packages to use normalized headers:
- Standardize User-Agent to 'langchaingo-httprr'
- Normalize version information in x-goog-api-client headers
- Remove OpenAI-Project headers for consistency
- Fix deprecated Anthropic completion API tests
- Update HuggingFace test recordings with valid responses
These changes make test recordings stable across dependency updates
and different environments, preventing test failures from version changes.
* devtools: add utility tool for normalizing httprr test recordings
Add a command-line tool that standardizes version information in httprr recordings:
- Normalizes x-goog-api-client headers to use placeholder versions
- Standardizes x-amz-user-agent headers for consistency
- Replaces Go version strings with generic placeholders
- Supports dry-run mode to preview changes without modifying files
- Includes verbose output option for detailed change reporting
This tool helps maintain consistent test recordings across different environments
and dependency versions, preventing test failures from version changes.
* llms/openai: update OpenAI embedding test to use text-embedding-3-small model
Update the embedding test to use the current text-embedding-3-small model:
- Change model from text-embedding-ada-002 to text-embedding-3-small
- Adjust dimensions parameter from 1234 to 256 to match model capabilities
- Update test recording with appropriate response data
This change ensures tests remain compatible with OpenAI's current embedding
models and prevents test failures from API version changes.
- Add WithModelProvider option to explicitly set provider for edge cases
- Improve provider detection to handle Nova models and inference profiles
- Add comprehensive unit tests for Nova provider detection
- Add bedrock-provider-example demonstrating usage
- Fix CreateCompletion to accept optional provider parameter
This allows users to specify the provider explicitly when automatic
detection doesn't work correctly (e.g., custom inference endpoints),
and adds full support for Amazon Nova models.
Fixes: #1345
Co-authored-by: Travis Cline <travis.cline@gmail.com>
* llms: fix memory leaks by adding Close methods and improving goroutine handling
Add Close methods to GoogleAI and Vertex clients to properly clean up resources
and prevent memory leaks from underlying gRPC connections. Update examples to
demonstrate proper client cleanup with defer statements.
Improve goroutine management in OpenAI streaming response handling with proper
context cancellation and non-blocking channel operations to prevent goroutine
leaks in error scenarios.
* examples: add replace directives for testing memory leak fixes
Add temporary replace directives to GoogleAI and Vertex example go.mod files
to test the Close() method changes from the previous commit. These directives
allow the examples to use the local version of the library with the memory
leak fixes before they're included in the next release.
This commit adds full support for OpenRouter, fixing streaming response parsing
errors that occurred when providers send non-JSON prefixes in their SSE streams.
Fixes#1172, Fixes#942
* prompts: add secure template rendering with filesystem support
* prompts: add comprehensive tests and examples
- Add security effectiveness tests for all attack vectors
- Add template rendering tests with all formats
- Add filesystem template tests with MapFS
- Add prompt template examples demonstrating all features
- Improve error handling and add local package references
* docs: add comprehensive prompt template documentation
- Add prompt template user guide with security section
- Add detailed API documentation for new functions
- Update partial values documentation
- Add template-related terms to style guide
- Document migration patterns and security considerations
* prompts: split template implementations by engine type
- Move Go template implementation to templates_go.go
- Move Jinja2 template implementation to templates_jinja2.go
- Clean up imports in templates.go
- Maintain all existing functionality with better code organization
* prompts: move security tests to dedicated file with expanded coverage
- Create new security_test.go file for all template security tests
- Expand test coverage for path traversal attacks in Jinja2 templates
- Add tests for migration patterns from vulnerable to secure implementations
- Remove redundant security tests from templates_test.go
- Improve organization of test code for better maintainability
* all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23
update go version to 1.23
add lots of test coverage via httprr recordings
update dependencies and organize go.mod
add testutil/testctr which helps work around a testcontainers-go+colima bug
expand the huggingface implementation and tests
expand capabilities of the ollama package
* httprr: add HTTP record/replay framework with default API key scrubbing
- Add httprr package for deterministic HTTP testing
- Implement default scrubbing for common API key headers
* httputil: reorganize transport layer and add logging infrastructure
- Replace debug transports with structured logging via slog
- Add comprehensive user agent handling with version info
- Improve transport layer organization and documentation
- Maintain backward compatibility with deprecated types
- Add JSON debug transport with color output support
* examples: update examples, clean up module declarations
- Fix and relax lint rules (for now)
- Clean up and fix module declarations
- Add .gitattributes to mark go.sum as binary
* ci: separate and enhance CI workflows
- Split example builds into dedicated workflow
- Add comprehensive test coverage reporting
- Improve CI structure with matrix testing
- Add race condition testing
- Add automated PR coverage comments
* test: improve test reliability and agent message handling
- Simplify MRKL agent test to use basic math calculation
- Update OpenAI functions agent to use ToolChatMessage
- Add proper environment checks for Zep integration tests
* agents: fix issue in tool call handling for openai function agent
Alexander Nalobin