Commit Graph

100 Commits

Author SHA1 Message Date
Bagatur
e4d3ccf62f
json mode standard test (#25497)
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-12-17 18:47:34 +00:00
Erick Friis
534b8f4364
standard-tests: release 0.3.7 (#28637) 2024-12-09 15:12:18 -05:00
Erick Friis
4c70ffff01
standard-tests: sync/async vectorstore tests conditional (#28636)
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-12-09 18:02:55 +00:00
Erick Friis
5e8553c31a
standard-tests: retriever docstrings (#28596) 2024-12-07 00:32:19 +00:00
ccurme
d801c6ffc7
tests[patch]: nits (#28601) 2024-12-07 00:13:04 +00:00
Erick Friis
4a7dc6ec4c
standard-tests: release 0.3.6 (#28599) 2024-12-07 00:05:04 +00:00
ccurme
80a88f8f04
tests[patch]: update API ref for chat models (#28594) 2024-12-06 19:00:14 -05:00
Erick Friis
b7c2029e84
standard-tests: root docstrings (#28595) 2024-12-06 15:14:52 -08:00
Erick Friis
9e2abcd152
standard-tests: show right classes in api docs (#28591) 2024-12-06 14:48:13 -08:00
Erick Friis
246c10a1cc
standard-tests: private members and tools unit troubleshoot (#28590) 2024-12-06 13:52:58 -08:00
ccurme
2c6bc74cb1
multiple: combine sync/async vector store standard test suites (#28580)
Breaking change in `langchain-tests`.
2024-12-06 14:55:06 -05:00
ccurme
f3dc142d3c
cli[patch]: implement minimal starter vector store (#28577)
Basically the same as core's in-memory vector store. Removed some
optional methods.
2024-12-06 13:10:22 -05:00
Erick Friis
5277a021c1
docs: raw loader codeblock (#28548)
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-12-06 09:26:34 -08:00
Erick Friis
18386c16c7
core, tests: more tolerant _aget_relevant_documents function (#28462) 2024-12-06 00:49:30 +00:00
ccurme
ecdfc98ef6
tests[patch]: run standard tests for embeddings and populate embeddings API ref (#28545)
plus minor updates to chat models and vector store API refs
2024-12-05 19:39:03 +00:00
Erick Friis
0f539f0246
standard-tests: release 0.3.5 (#28526) 2024-12-05 00:41:07 -08:00
Erick Friis
43c35d19d4
cli: standard tests in cli, test that they run, skip vectorstore tests (#28521) 2024-12-05 00:38:32 -08:00
ccurme
f459754470
tests[patch]: populate API reference for vector stores (#28520) 2024-12-05 00:02:31 +00:00
ccurme
ab831ce05c
tests[patch]: populate API reference for chat models (#28487)
Populate API reference for test class properties and test methods for
chat models.

Also:
- Make `standard_chat_model_params` private.
- `pytest.skip` some tests that were previously passed if features are
not supported.
2024-12-03 15:24:54 -05:00
Erick Friis
000be1f32c
tests: init retriever standard tests (#28459) 2024-12-02 23:36:09 +00:00
ccurme
a433039a56
core[patch]: support final AIMessage responses in tool_example_to_messages (#28267)
We have a test
[test_structured_few_shot_examples](ad4333ca03/libs/standard-tests/langchain_tests/integration_tests/chat_models.py (L546))
in standard integration tests that implements a version of tool-calling
few shot examples that works with ~all tested providers. The formulation
supported by ~all providers is: `human message, tool call, tool message,
AI reponse`.

Here we update
`langchain_core.utils.function_calling.tool_example_to_messages` to
support this formulation.

The `tool_example_to_messages` util is undocumented outside of our API
reference. IMO, if we are testing that this function works across all
providers, it can be helpful to feature it in our guides. The structured
few-shot examples we document at the moment require users to implement
this function and can be simplified.
2024-11-22 15:38:49 +00:00
Erick Friis
9a717c9b32
docs: poetry publish 2 (#28277)
- **docs: poetry publish**
- **x**
- **x**
- **x**
- **x**
- **x**
- **x**
- **x**
- **x**
- **x**
2024-11-21 20:49:38 -08:00
Erick Friis
5bc2df3060
standard-tests: troubleshooting docstrings (#28268) 2024-11-21 22:05:31 +00:00
Erick Friis
4f76246cf2
standard-tests: release 0.3.4 (#28245) 2024-11-20 19:35:58 -08:00
Erick Friis
4bdf1d7d1a
standard-tests: fix decorator init test (#28246) 2024-11-21 03:35:43 +00:00
Erick Friis
60e572f591
standard-tests: tool tests (#28244) 2024-11-20 19:26:16 -08:00
Erick Friis
161ab736ce
standard-tests: release 0.3.3 (#28242) 2024-11-20 23:47:02 +00:00
Erick Friis
43e24cd4a1
docs, standard-tests: property tags, support tool decorator (#28234) 2024-11-20 17:19:03 +00:00
Erick Friis
0dbaf05bb7
standard-tests: rename langchain_standard_tests to langchain_tests, release 0.3.2 (#28203) 2024-11-18 19:10:39 -08:00
Erick Friis
6d2004ee7d
multiple: langchain-standard-tests -> langchain-tests (#28139) 2024-11-15 11:32:04 -08:00
Erick Friis
409c7946ac
docs, standard-tests: how to standard test a custom tool, imports (#27931) 2024-11-15 10:49:14 -08:00
ccurme
776e3271e3
standard-tests[patch]: add test for async tool calling (#28133) 2024-11-15 16:09:50 +00:00
Erick Friis
a8c473e114
standard-tests: ci pipeline (#27923) 2024-11-05 20:55:38 +00:00
Erick Friis
bff2a8b772
standard-tests: add tools standard tests (#27899) 2024-11-05 11:44:34 -08:00
Erick Friis
31f4fb790d
standard-tests: release 0.3.0 (#27900) 2024-11-04 17:29:15 -08:00
Bagatur
ee63d21915
many: use core 0.3.15 (#27834) 2024-11-01 20:35:55 +00:00
Erick Friis
b84e00283f
standard-tests: test that only one chunk sets input_tokens (#27177) 2024-10-08 11:35:32 -07:00
Bagatur
0b8416bd2e
anthropic[patch]: fix input_tokens when cached (#27125) 2024-10-04 22:35:51 +00:00
Bagatur
bd5b335cb4
standard-tests[patch]: fix oai usage metadata test (#27122) 2024-10-04 20:00:48 +00:00
Bagatur
546dc44da5
core[patch]: add UsageMetadata details (#27072) 2024-10-03 20:36:17 +00:00
Bagatur
5ced41bf50
anthropic[patch]: fix tool call and tool res image_url handling (#26587)
Co-authored-by: ccurme <chester.curme@gmail.com>
2024-09-17 14:30:07 -07:00
ccurme
88bc15d69b
standard-tests[patch]: add async test for structured output (#26527) 2024-09-16 11:15:23 -04:00
Erick Friis
4131be63af
multiple: 0.3.0 not dev version (#26502) 2024-09-15 18:26:50 +00:00
Erick Friis
c2a3021bb0
multiple: pydantic 2 compatibility, v0.3 (#26443)
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Dan O'Donovan <dan.odonovan@gmail.com>
Co-authored-by: Tom Daniel Grande <tomdgrande@gmail.com>
Co-authored-by: Grande <Tom.Daniel.Grande@statsbygg.no>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com>
Co-authored-by: ZhangShenao <15201440436@163.com>
Co-authored-by: Friso H. Kingma <fhkingma@gmail.com>
Co-authored-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: Morgante Pell <morgantep@google.com>
2024-09-13 14:38:45 -07:00
Bagatur
fdf6fbde18 fmt 2024-09-04 11:12:11 -07:00
Bagatur
3ec93c2817 standard-tests[patch]: add Ser/Des test 2024-09-04 10:24:06 -07:00
Bagatur
bc3b02651c
standard-tests[patch]: test init from env vars (#25983) 2024-09-03 19:05:39 +00:00
Christophe Bornet
038c287b3a
all: Improve make lint command (#25344)
* Removed `ruff check --select I` as `I` is already selected and checked
in the main `ruff check` command
* Added checks for non-empty `PYTHON_FILES`
* Run `ruff check` only on `PYTHON_FILES`

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-08-23 18:23:52 -07:00
Bagatur
cf9c484715
standard-tests[patch]: test Message.name (#25677)
Tests:
https://github.com/langchain-ai/langchain/actions/runs/10516092584
2024-08-22 14:47:31 -07:00
ccurme
c5bf114c0f
together, standard-tests: specify tool_choice in standard tests (#25548)
Here we allow standard tests to specify a value for `tool_choice` via a
`tool_choice_value` property, which defaults to None.

Chat models [available in
Together](https://docs.together.ai/docs/chat-models) have issues passing
standard tool calling tests:
- llama 3.1 models currently [appear to rely on user-side
parsing](https://docs.together.ai/docs/llama-3-function-calling) in
Together;
- Mixtral-8x7B and Mistral-7B (currently tested) consistently do not
call tools in some tests.

Specifying tool_choice also lets us remove an existing `xfail` and use a
smaller model in Groq tests.
2024-08-19 16:37:36 -04:00