5d347f6d6f
Currently, checking the length of prompts for embeddings to ensure they fit in the context window (and possible truncation) occurs in two places - the Ollama server and runner. This can lead to inconsistencies in both the checks and reported number of tokens processed. Since we have to do this processing in the runner, this consolidates all of the logic there. |
||
|---|---|---|
| .. | ||
| testdata | ||
| api_test.go | ||
| basic_test.go | ||
| concurrency_test.go | ||
| context_test.go | ||
| embed_test.go | ||
| library_models_test.go | ||
| llm_image_test.go | ||
| max_queue_test.go | ||
| model_arch_test.go | ||
| model_perf_test.go | ||
| quantization_test.go | ||
| README.md | ||
| utils_test.go | ||
Integration Tests
This directory contains integration tests to exercise Ollama end-to-end to verify behavior
By default, these tests are disabled so go test ./... will exercise only unit tests. To run integration tests you must pass the integration tag. go test -tags=integration ./... Some tests require additional tags to enable to allow scoped testing to keep the duration reasonable. For example, testing a broad set of models requires -tags=integration,models and a longer timeout (~60m or more depending on the speed of your GPU.). To view the current set of tag combinations use find integration -type f | xargs grep "go:build"
The integration tests have 2 modes of operating.
- By default, they will start the server on a random port, run the tests, and then shutdown the server.
- If
OLLAMA_TEST_EXISTINGis set to a non-empty string, the tests will run against an existing running server, which can be remote based on yourOLLAMA_HOSTenvironment variable
Important
Before running the tests locally without the "test existing" setting, compile ollama from the top of the source tree
go build .in addition to GPU support with cmake if applicable on your platform. The integration tests expect to find an ollama binary at the top of the tree.
Many tests use a default small model suitable to run on many systems. You can override this default model by setting OLLAMA_TEST_DEFAULT_MODEL