github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-07-15 07:00:38 +00:00
Code Issues Packages Projects Releases Wiki Activity
14,133 Commits 1,183 Branches 1,307 Tags
2d450d4d3bf46cbfccbce8a3338f20e75837891b
Commit Graph

14133 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
ccurme
2d450d4d3b fix(core): (v1) finish test (#32701) 2025-08-26 18:03:47 -04:00
Mason Daugherty
e49156e63f chore: rfc to use .text instead of .text() (#32699) 2025-08-26 16:54:04 -04:00
ccurme
447db13473 feat(openai): (v1) support content_blocks on legacy v0 responses API format (#32700) 2025-08-26 16:33:59 -04:00
Mason Daugherty
395515762e Merge branch 'wip-v1.0' into cc/1.0/standard_content 2025-08-26 15:52:11 -04:00
Mason Daugherty
a2322f68ba Merge branch 'master' into wip-v1.0 2025-08-26 15:51:57 -04:00
Mason Daugherty
3d08b6bd11 chore: adress pytest-asyncio deprecation warnings + other nits (#32696) 
amongst some linting imcompatible rules
 2025-08-26 15:51:38 -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
ccurme
2bbd034f85 fix(core): (v1) invoke callback prior to yielding final chunk (#32695) 2025-08-26 14:58:43 -04:00
Chester Curme
659d282d1d standard tests: update multimodal tests 2025-08-26 13:55:44 -04:00
ccurme
c63c3ea290 feat(core): (v1) add sentinel value to output_version (#32692) 2025-08-26 13:29:20 -04:00
ccurme
dbebe2ca97 release(core): 0.3.75 (#32693) langchain-core==0.3.75 2025-08-26 11:12:03 -04:00
ccurme
008043977d release(openai): 0.3.32 (#32691) langchain-openai==0.3.32 2025-08-26 14:05:40 +00:00
Jacob Lee
1459d4f4ce fix(openai): Always add raw response object to OpenAI client errors for invoke (#32655) 2025-08-26 09:59:25 -04:00
ccurme
fe9599f118 feat(core): parse tool_call_chunks in content in aggregated stream (#32664) 2025-08-25 15:38:22 -04:00
ccurme
97bd2cf938 fix(core): (v1) fix PDF input translation for openai chat completions (#32673) 2025-08-25 15:15:03 -04:00
Mason Daugherty
5ef18e8f5b feat(core): add .text property, introduce TextAccessor for backward compatibility with text access methods (#32672) 2025-08-25 14:51:40 -04:00
ccurme
f33480c2cf feat(core): trace response body on error (#32653) 2025-08-25 14:28:19 -04:00
ccurme
7e9ae5df60 feat(openai): (v1) delete bind_functions and remove tool_calls from additional_kwargs (#32669) 2025-08-25 14:22:31 -04:00
Mason Daugherty
4e0fd330aa fix: update content_blocks property docstring 2025-08-25 14:10:21 -04:00
Mason Daugherty
1c55536ec1 chore(core): add note about backward compatibility for tool_calls in additional_kwargs in JsonOutputKeyToolsParser 2025-08-25 10:30:41 -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
Shahroz Ahmad
1819c73d10 docs(docs): update Docker to ClickHouse 25.7 with vector_similarity support (#32659) 
- **Description:** Updated Docker command to use ClickHouse 25.7 (has
`vector_similarity` index support). Added `CLICKHOUSE_SKIP_USER_SETUP=1`
env param to [bypass default user
setup](https://clickhouse.com/docs/install/docker#managing-default-user)
and allow external network access. There was also a bug where if you try
to access results using `similarity_search_with_relevance_scores`, they
need to unpacked first.

- **Issue:** Fixes #32094 if someone following tutorial with default
Clickhouse configurations.
 2025-08-25 09:59:28 -04:00
Kim
8171403b4a docs(docs): rebranding of Azure AI Studio to Azure AI Foundry (#32658) 
# Description
Updated documentation to reflect Microsoft’s rebranding of Azure AI
Studio to Azure AI Foundry. This ensures consistency with current Azure
terminology across the docs.

# Issue
N/A

# Dependencies
None
 2025-08-25 09:58:31 -04:00
Chester Curme
2d9fe703cb Merge branch 'wip-v1.0' into cc/1.0/standard_content 2025-08-25 09:56:39 -04:00
Chester Curme
7a108618ae Merge branch 'master' into wip-v1.0 2025-08-25 09:39:39 -04:00
ccurme
62d746e630 feat(core): (v1) restore separate type for AIMessage.tool_calls (#32668) 2025-08-25 09:37:41 -04:00
Mason Daugherty
2d0713c2fc fix(infra): ollama CI langchain-ollama==0.3.7 2025-08-22 16:40:03 -04:00
Mason Daugherty
8060b371bb fix(infra): ollama CI 2025-08-22 16:37:05 -04:00
ccurme
26833f2ebc feat(anthropic): v1 support (#32623) 2025-08-22 16:06:53 -04:00
Mason Daugherty
7851f66503 release(ollama): 0.3.7 (#32651) 2025-08-22 15:18:40 -04:00
Mason Daugherty
af3b88f58d feat(ollama): update reasoning type to support string values for custom intensity levels (e.g. gpt-oss) (#32650) 2025-08-22 15:11:32 -04:00
itaismith
1eb45d17fb feat(chroma): Add support for collection forking (#32627) 2025-08-21 17:57:55 -04:00
ccurme
8545d4731e release(openai): 0.3.31 (#32646) langchain-openai==0.3.31 2025-08-21 16:50:27 -04:00
Alex Naidis
21f7a9a9e5 fix(openai): allow temperature parameter for gpt-5-chat models (#32624) 2025-08-21 16:40:10 -04:00
sa411022
61bc1bf9cc fix(openai): construct responses api input (#32557) 2025-08-21 15:56:29 -04:00
Shahrukh Shaik
4ba222148d fix(openai): Chat Message Annotations defaults to [ ] if not list or None (#32614) 2025-08-21 15:30:12 -04:00
Mason Daugherty
5bcf7d006f refactor(core): data block handling, normalize message formats, strip IDs from messages (#32572) 
> [!WARNING]
> **BREAKING:** Simplifies message normalization to single consistent
path, requiring partner package updates

**Key Changes:**
- Consistent multimodal handling:
- OpenAI `image_url` blocks pass through unchanged (broad compatibility)
- OpenAI `input_audio` and `file` blocks convert to v1 standard
equivalents
  - Legacy v0 multimodal blocks convert to v1 standard
  - Everything else passes through unchanged
- Partner packages must update content block parsing logic

**Partner Updates**

`output_version` affects how messages are serialized into `.content`.
`_normalize_messages()` will now upgrade v0 content to v1, so, all
partners now receive v1 format input regardless of `output_version`.

Migration:
- Partner packages must update to handle v1 input content blocks
- `output_version` still controls serialization format of responses
(unchanged)

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
 2025-08-21 14:48:23 -04:00
Chester Curme
3c8edbecb2 Merge branch 'wip-v1.0' into cc/1.0/standard_content 
# Conflicts:
#	libs/core/langchain_core/messages/ai.py
 2025-08-21 14:12:29 -04:00
ccurme
6f058e7b9b fix(core): (v1) update BaseChatModel return type to AIMessage (#32626) 2025-08-21 14:02:24 -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
Mohammed Mohtasim .M.S
b5c44406eb docs(docs): fix typos in table in "How to load PDFs" documentation (#32635) 
**Description:**
Fixed corrupted text in the code cell output of the documentation
notebook. The code cell itself was correct, but the saved output
contained garbage text.

**Issue:**
The saved output in the documentation notebook contained garbage/typo
text in the table name.

**Dependencies:**
None
 2025-08-21 10:06:45 -04:00
Emmanuel Leroy
2ec63ca7da docs: migration to langchain_oci (#32619) 
Doc update. I missed a couple mentions of the old package.
 2025-08-21 10:03:44 -04:00
Christophe Bornet
f896bcdb1d chore(langchain): add mypy pydantic plugin (#32610) 2025-08-19 16:59:59 -04:00
Christophe Bornet
73a7de63aa chore(text-splitters): add mypy pydantic plugin (#32611) 2025-08-19 16:58:12 -04:00
Emmanuel Leroy
cd5f3ee364 docs: migrate from community package to langchain-oci (#32608) 
Migrate package from langchain_community to langchain_oci
 2025-08-19 16:57:37 -04:00
ccurme
0444e260be refactor: convert message content inside BaseChatModel (#32606) 2025-08-19 12:25:44 -04:00
Chester Curme
e41693a23e Merge branch 'wip-v1.0' into cc/1.0/standard_content 2025-08-19 12:11:41 -04:00
ccurme
dbc5a3b718 fix(anthropic): update cassette for streaming benchmark (#32609) 2025-08-19 11:18:36 -04:00
Mason Daugherty
43b9d3d904 feat(core): implement dynamic translator registration for model providers (#32602) 
Extensible registry system for translating AI message content blocks
from various model providers. Refactors the way provider-specific
content is handled, moving from hardcoded logic to a plugin-like
architecture.
 2025-08-19 10:08:56 -04:00
Christophe Bornet
02d6b9106b chore(core): add mypy pydantic plugin (#32604) 
This helps to remove a bunch of mypy false positives.
 2025-08-19 09:39:53 -04:00