github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-07-15 15:40:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
14,643 Commits 1,182 Branches 1,307 Tags
cc/summarization_middleware_behavior
Commit Graph

95 Commits

Author SHA1 Message Date
Mason Daugherty
f94108b4bc fix: links (#33691) 
* X-ref to new docs
* Formatting updates
 2025-10-27 19:04:29 -04:00
ccurme
60a0ff8217 fix(standard-tests): fix tool description in agent loop test (#33690) 2025-10-27 15:02:13 -04:00
Mason Daugherty
e731ba1e47 style: more refs work (#33616) 2025-10-20 18:40:19 -04:00
Mason Daugherty
1d2273597a docs: more fixes for refs (#33554) 2025-10-16 22:54:16 -04:00
Mason Daugherty
26e0a00c4c style: more work for refs (#33508) 
Largely:
- Remove explicit `"Default is x"` since new refs show default inferred
from sig
- Inline code (useful for eventual parsing)
- Fix code block rendering (indentations)
 2025-10-15 18:46:55 -04:00
ccurme
89b7933ef1 feat(standard-tests): parametrize tool calling test (#33496) 2025-10-15 14:43:09 +00:00
ccurme
c1b816cb7e fix(fireworks): parse standard blocks in input (#33426) 2025-10-10 16:18:37 -04:00
Mason Daugherty
291a9fcea1 style: llm -> model (#33423) 2025-10-10 13:19:13 -04:00
Mason Daugherty
ed2ee4e8cc style: fix tables, capitalization (#33417) 2025-10-10 11:09:59 -04:00
Mason Daugherty
6fc21afbc9 style: .. code-block:: admonition translations (#33400) 
biiiiiiiiiiiiiiiigggggggg pass
 2025-10-09 16:52:58 -04:00
ccurme
50445d4a27 fix(standard-tests): update Anthropic inputs test (#33391) 
Since 10/7 Anthropic will raise BadRequestError if given an invalid
thinking signature.
 2025-10-09 14:13:26 -04:00
Mason Daugherty
d8a680ee57 style: address Sphinx double-backtick snippet syntax (#33389) 2025-10-09 13:35:51 -04:00
Mason Daugherty
3576e690fa chore: update Sphinx links to markdown (#33386) 2025-10-09 11:54:14 -04:00
Mason Daugherty
b6132fc23e style: remove more Optional syntax (#33371) 2025-10-08 23:28:43 -04:00
Mason Daugherty
d13823043d style: monorepo pass for refs (#33359) 
* Delete some double backticks previously used by Sphinx (not done
everywhere yet)
* Fix some code blocks / dropdowns

Ignoring CLI CI for now
 2025-10-08 18:41:39 -04:00
ccurme
d0f5a1cc96 fix(standard-tests,openai): minor fix for Responses API tests (#33315) 
Following https://github.com/langchain-ai/langchain/pull/33301
 2025-10-06 16:46:41 -04:00
ccurme
426b8e2e6a feat(standard-tests): enable parametrization of output_version (#33301) 2025-10-06 14:37:33 -04:00
Mason Daugherty
5a016de53f chore: delete deprecated items (#33192) 
Removed:
- `libs/core/langchain_core/chat_history.py`: `add_user_message` and
`add_ai_message` in favor of `add_messages` and `aadd_messages`
- `libs/core/langchain_core/language_models/base.py`: `predict`,
`predict_messages`, and async versions in favor of `invoke`. removed
`_all_required_field_names` since it was a wrapper on
`get_pydantic_field_names`
- `libs/core/langchain_core/language_models/chat_models.py`:
`callback_manager` param in favor of `callbacks`. `__call__` and
`call_as_llm` method in favor of `invoke`
- `libs/core/langchain_core/language_models/llms.py`: `callback_manager`
param in favor of `callbacks`. `__call__`, `predict`, `apredict`, and
`apredict_messages` methods in favor of `invoke`
- `libs/core/langchain_core/prompts/chat.py`: `from_role_strings` and
`from_strings` in favor of `from_messages`
- `libs/core/langchain_core/prompts/pipeline.py`: removed
`PipelinePromptTemplate`
- `libs/core/langchain_core/prompts/prompt.py`: `input_variables` param
on `from_file` as it wasn't used
- `libs/core/langchain_core/tools/base.py`: `callback_manager` param in
favor of `callbacks`
- `libs/core/langchain_core/tracers/context.py`: `tracing_enabled` in
favor of `tracing_enabled_v2`
- `libs/core/langchain_core/tracers/langchain_v1.py`: entire module
- `libs/core/langchain_core/utils/loading.py`: entire module,
`try_load_from_hub`
- `libs/core/langchain_core/vectorstores/in_memory.py`: `upsert` in
favor of `add_documents`
- `libs/standard-tests/langchain_tests/integration_tests/chat_models.py`
and `libs/standard-tests/langchain_tests/unit_tests/chat_models.py`:
`tool_choice_value` as models should accept `tool_choice="any"`
- `langchain` will consequently no longer expose these items if it was
previously

---------

Co-authored-by: Mohammad Mohtashim <45242107+keenborder786@users.noreply.github.com>
Co-authored-by: Caspar Broekhuizen <caspar@langchain.dev>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Sadra Barikbin <sadraqazvin1@yahoo.com>
Co-authored-by: Vadym Barda <vadim.barda@gmail.com>
 2025-10-03 03:33:24 +00:00
Mason Daugherty
ae5b105d11 docs: v1 docs updates (#33173) 
Co-authored-by: Mohammad Mohtashim <45242107+keenborder786@users.noreply.github.com>
Co-authored-by: Caspar Broekhuizen <caspar@langchain.dev>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Sadra Barikbin <sadraqazvin1@yahoo.com>
Co-authored-by: Vadym Barda <vadim.barda@gmail.com>
 2025-10-02 18:46:26 -04:00
Mason Daugherty
9c9b80c70a docs(standard-tests): add clarity to docstrings (#33218) 2025-10-02 16:09:34 -04:00
Mason Daugherty
eaa6dcce9e release: v1.0.0 (#32567) 
Co-authored-by: Mohammad Mohtashim <45242107+keenborder786@users.noreply.github.com>
Co-authored-by: Caspar Broekhuizen <caspar@langchain.dev>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Sadra Barikbin <sadraqazvin1@yahoo.com>
Co-authored-by: Vadym Barda <vadim.barda@gmail.com>
 2025-10-02 10:49:42 -04:00
ccurme
002d623f2d feat: (core, standard-tests) support PDF inputs in ToolMessages (#33183) 2025-10-01 10:16:16 -04:00
Mason Daugherty
5bea28393d docs: standardize .. code-block directive usage (#33122) 
and fix typos
 2025-09-25 16:49:56 -04:00
Christophe Bornet
ee268db1c5 feat(standard-tests): add a property to skip relevant tests if the vector store doesn't support get_by_ids() (#32633) 2025-09-09 11:37:23 -04:00
Mason Daugherty
35e9d36b0e fix(standard-tests): ensure non-negative token counts in usage metadata assertions (#32593) 2025-09-08 16:49:26 -04:00
Christophe Bornet
05d14775f2 chore(standard-tests): enable ruff docstring-code-format (#32852) 2025-09-08 16:39:53 -04:00
Stefano Lottini
390606c155 fix(standard-tests): standard vectorstore tests accept out-of-order get_by_ids (#32821) 
- **Description:** The vectorstore standard-test mistakenly assumes that
the store's `get_by_ids` respects the order of the provided `ids`. This
is not the case (as the base class docstring states). This PR fixes
those tests that would fail otherwise (see issue #32820 for details,
repro and all). Fixes #32820
- **Issue:** Fixes #32820
- **Dependencies:** none

Co-authored-by: Stefano Lottini <stefano.lottini@ibm.com>
 2025-09-08 14:22:14 -04:00
Christophe Bornet
c672590f42 chore(standard-tests): select ALL rules with exclusions (#31937) 
Co-authored-by: Mason Daugherty <mason@langchain.dev>
 2025-09-08 14:57:47 +00:00
Christophe Bornet
323729915a chore(standard-tests): add mypy strict checking (#32384) 
Co-authored-by: Mason Daugherty <mason@langchain.dev>
 2025-09-08 10:50:38 -04:00
Matthew Farrellee
f2dcdae467 fix(standard-tests): update function_args to match my_adder_tool param types (#32689) 
**Description:**

https://api.llama.com implements strong type checking, which results in
a false negative.

with type mismatch (expected integer, received string) -

```
$ curl -X POST "https://api.llama.com/compat/v1/chat/completions" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
 "model": "Llama-3.3-70B-Instruct",
 "messages": [
     {"role": "user", "content": "What is 1 + 2"},
     {"role": "assistant", "content": "", "tool_calls": [{"id": "abc123", "type": "function", "function": {"name": "my_adder_tool", "arguments": "{\"a\": \"1\", \"b\": \"2\"}"}}]},
     {"role": "tool", "tool_call_id": "abc123", "content": "{\"result\": 3}"}
 ],
 "tools": [{"type": "function", "function": {"name": "my_adder_tool", "description": "Sum two integers", "parameters": {"properties": {"a": {"type": "integer"}, "b": {"type": "integer"}}, "required": ["a", "b"], "type": "object"}}}]
}'

{"title":"Bad request","detail":"Unexpected param value `a`: \"1\"","status":400}
```

with correct type -

```
$ curl -X POST "https://api.llama.com/compat/v1/chat/completions" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
 "model": "Llama-3.3-70B-Instruct",
 "messages": [
     {"role": "user", "content": "What is 1 + 2"},
     {"role": "assistant", "content": "", "tool_calls": [{"id": "abc123", "type": "function", "function": {"name": "my_adder_tool", "arguments": "{\"a\": 1, \"b\": 2}"}}]},
     {"role": "tool", "tool_call_id": "abc123", "content": "{\"result\": 3}"}
 ],
 "tools": [{"type": "function", "function": {"name": "my_adder_tool", "description": "Sum two integers", "parameters": {"properties": {"a": {"type": "integer"}, "b": {"type": "integer"}}, "required": ["a", "b"], "type": "object"}}}]
}'

{"id":"AhMwBbuaa5payFr_xsOHzxX","model":"Llama-3.3-70B-Instruct","choices":[{"finish_reason":"stop","index":0,"message":{"refusal":"","role":"assistant","content":"The result of 1 + 2 is 3.","id":"AhMwBbuaa5payFr_xsOHzxX"},"logprobs":null}],"created":1756167668,"object":"chat.completions","usage":{"prompt_tokens":248,"completion_tokens":17,"total_tokens":265}}
```
 2025-08-26 15:50:47 -04:00
Maitrey Talware
622337a297 docs(docs): fixed typos in documentations (#32661) 
Minor typo fixes. (Not linked to current open issues)
 2025-08-25 10:02:53 -04:00
Christophe Bornet
b825f85bf2 fix(standard-tests): fix BaseStoreAsyncTests.test_set_values_is_idempotent (#32638) 
The async version of the test should use the `ayield_keys` method
instead of `yield_keys`.
Otherwise tools such as `blockbuster` may trigger on a blocking call.
 2025-08-21 10:07:46 -04:00
Christophe Bornet
09a616fe85 chore(standard-tests): add ruff rules D (#32347) 
See https://docs.astral.sh/ruff/rules/#pydocstyle-d

Co-authored-by: Mason Daugherty <mason@langchain.dev>
 2025-08-11 22:26:11 +00:00
Mason Daugherty
ee4c2510eb feat: port various nit changes from wip-v0.4 (#32506) 
Lots of work that wasn't directly related to core
improvements/messages/testing functionality
 2025-08-11 15:09:08 -04:00
Mason Daugherty
e5d0a4e4d6 feat(standard-tests): formatting (#32504) 
Not touching `pyproject.toml` or chat model related items as to not
interfere with work in wip0.4 branch
 2025-08-11 13:30:30 -04:00
Christophe Bornet
a647073b26 feat(standard-tests): add a property to set the name of the parameter for the number of results to return (#32443) 
Not all retrievers use `k` as param name to set the number of results to
return. Even in LangChain itself. Eg:
bc4251b9e0/libs/core/langchain_core/indexing/in_memory.py (L31)

So it's helpful to be able to change it for a given retriever.
The change also adds hints to disable the tests if the retriever doesn't
support setting the param in the constructor or in the invoke method
(for instance, the `InMemoryDocumentIndex` in the link supports in the
constructor but not in the invoke method).

This change is backward compatible.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-08-07 11:22:24 -04:00
Mason Daugherty
12c0e9b7d8 fix(docs): local API reference documentation build (#32271) 
ensure all relevant packages are correctly processed - cli wasn't
included, also fix ValueError
 2025-07-28 00:50:20 -04:00
Mason Daugherty
96cbd90cba fix: formatting issues in docstrings (#32265) 
Ensures proper reStructuredText formatting by adding the required blank
line before closing docstring quotes, which resolves the "Block quote
ends without a blank line; unexpected unindent" warning.
 2025-07-27 23:37:47 -04:00
niceg
0d6f915442 fix: LLM mimicking Unicode responses due to forced Unicode conversion of non-ASCII characters. (#32222) 
fix: Fix LLM mimicking Unicode responses due to forced Unicode
conversion of non-ASCII characters.

- **Description:** This PR fixes an issue where the LLM would mimic
Unicode responses due to forced Unicode conversion of non-ASCII
characters in tool calls. The fix involves disabling the `ensure_ascii`
flag in `json.dumps()` when converting tool calls to OpenAI format.
- **Issue:** Fixes ↓↓↓
input：
```json
{'role': 'assistant', 'tool_calls': [{'type': 'function', 'id': 'call_nv9trcehdpihr21zj9po19vq', 'function': {'name': 'create_customer', 'arguments': '{"customer_name": "你好啊集团"}'}}]}
```
output:
```json
{'role': 'assistant', 'tool_calls': [{'type': 'function', 'id': 'call_nv9trcehdpihr21zj9po19vq', 'function': {'name': 'create_customer', 'arguments': '{"customer_name": "\\u4f60\\u597d\\u554a\\u96c6\\u56e2"}'}}]}
```
then:
llm will mimic outputting unicode. Unicode's vast number of symbols can
lengthen LLM responses, leading to slower performance.
<img width="686" height="277" alt="image"
src="https://github.com/user-attachments/assets/28f3b007-3964-4455-bee2-68f86ac1906d"
/>

---------

Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
 2025-07-24 17:01:31 -04:00
Mason Daugherty
d53ebf367e fix(docs): capitalization, codeblock formatting, and hyperlinks, note blocks (#32235) 
widespread cleanup attempt
 2025-07-24 16:55:04 -04:00
Christophe Bornet
9368b92b2c standard-tests: Ruff autofixes (#31862) 
Auto-fixes from ruff with rule ALL
 2025-07-07 10:27:39 -04:00
Christophe Bornet
1276bf3e1d standard-tests: Add ruff rules PGH (#31869) 
See https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
 2025-07-07 10:07:39 -04:00
Christophe Bornet
cd7dce687a standard-tests: Add ruff rule UP (pyupgrade) (#31842) 
See https://docs.astral.sh/ruff/rules/#pyupgrade-up
All auto-fixed
 2025-07-03 10:12:31 -04:00
Mason Daugherty
6d71b6b6ee standard-tests: refactoring and fixes (#31703) 
- `libs/core/langchain_core/messages/base.py`: add model name to
examples [per
docs](https://python.langchain.com/api_reference/standard_tests/integration_tests/langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.html#langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_usage_metadata)
("0.3.17: Additionally check for the presence of model_name in the
response metadata, which is needed for usage tracking in callback
handlers")
- `libs/core/langchain_core/utils/function_calling.py`: correct typo
-
`libs/standard-tests/langchain_tests/integration_tests/chat_models.py`:
- `magic_function(input)` -> `magic_function(_input)` to prevent warning
about redefining built in `input`
    - relocate a few tests for better grouping and narrative flow
    - suppress some type hint warnings following suit from similar tests
    - fix a few more typos
- validate not only that `model_name` is defined, but that it is not
empty (test_usage_metadata)
 2025-06-23 23:22:31 +00:00
Mason Daugherty
a79998800c fix: correct typo in docstring for three_values fixture (#31638) 
Docstring typo fix in `base_store.py`
 2025-06-17 16:51:07 -04:00
ccurme
9c639035c0 standard-tests: add cache_control to Anthropic inputs test (#31516) 2025-06-06 10:00:43 -04:00
ccurme
d3be4a0c56 infra: remove use of --vcr-record=none (#31452) 
This option is specific to `pytest-vcr`. `pytest-recording` runs in this
mode by default.
 2025-06-01 10:49:59 -04:00
ccurme
3db1aa0ba6 standard-tests: migrate to pytest-recording (#31425) 
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
 2025-05-31 15:21:15 -04:00
Sydney Runkle
1917dd1ccd benchmarks: always run (not conditional on changes) (#31409) 2025-05-29 11:45:57 -04:00
ccurme
49eeb0f3c3 standard-tests: add benchmarks (#31302) 
Co-authored-by: Sydney Runkle <sydneymarierunkle@gmail.com>
 2025-05-29 15:21:37 +00:00