ChatOpenAI supports a kwarg `stream_options` which can take values
`{"include_usage": True}` and `{"include_usage": False}`.
Setting include_usage to True adds a message chunk to the end of the
stream with usage_metadata populated. In this case the final chunk no
longer includes `"finish_reason"` in the `response_metadata`. This is
the current default and is not yet released. Because this could be
disruptive to workflows, here we remove this default. The default will
now be consistent with OpenAI's API (see parameter
[here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)).
Examples:
```python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI()
for chunk in llm.stream("hi"):
print(chunk)
```
```
content='' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='Hello' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='!' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='' response_metadata={'finish_reason': 'stop'} id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
```
```python
for chunk in llm.stream("hi", stream_options={"include_usage": True}):
print(chunk)
```
```
content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='Hello' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='!' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='' response_metadata={'finish_reason': 'stop'} id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}
```
```python
llm = ChatOpenAI().bind(stream_options={"include_usage": True})
for chunk in llm.stream("hi"):
print(chunk)
```
```
content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='Hello' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='!' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='' response_metadata={'finish_reason': 'stop'} id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}
```
OpenAI recently added a `stream_options` parameter to its chat
completions API (see [release
notes](https://platform.openai.com/docs/changelog/added-chat-completions-stream-usage)).
When this parameter is set to `{"usage": True}`, an extra "empty"
message is added to the end of a stream containing token usage. Here we
propagate token usage to `AIMessage.usage_metadata`.
We enable this feature by default. Streams would now include an extra
chunk at the end, **after** the chunk with
`response_metadata={'finish_reason': 'stop'}`.
New behavior:
```
[AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='Hello', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='!', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde', usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17})]
```
Old behavior (accessible by passing `stream_options={"include_usage":
False}` into (a)stream:
```
[AIMessageChunk(content='', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='Hello', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='!', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-1312b971-c5ea-4d92-9015-e6604535f339')]
```
From what I can tell this is not yet implemented in Azure, so we enable
only for ChatOpenAI.
```python
class UsageMetadata(TypedDict):
"""Usage metadata for a message, such as token counts.
Attributes:
input_tokens: (int) count of input (or prompt) tokens
output_tokens: (int) count of output (or completion) tokens
total_tokens: (int) total token count
"""
input_tokens: int
output_tokens: int
total_tokens: int
```
```python
class AIMessage(BaseMessage):
...
usage_metadata: Optional[UsageMetadata] = None
"""If provided, token usage information associated with the message."""
...
```
# Add pricing and max context window for GPT-4o
- community: add cost per 1k tokens and max context window
- partners: add max context window
**Description:** adds static information about GPT-4o based on
https://openai.com/api/pricing/ and
https://platform.openai.com/docs/models/gpt-4o so that GPT-4o reporting
is accurate.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
These packages all import `LangSmithParams` which was released in
langchain-core==0.2.0.
N.B. we will need to release `openai` and then bump `langchain-openai`
in `together` and `upstage`.
0.2 is not a breaking release for core (but it is for langchain and
community)
To keep the core+langchain+community packages in sync at 0.2, we will
relax deps throughout the ecosystem to tolerate `langchain-core` 0.2
**Description:** Add tests to check API keys and Active Directory tokens
are masked
**Issue:** Resolves#12165 for OpenAI and Azure OpenAI models
**Dependencies:** None
Also resolves#12473 which may be closed.
Additional contributors @alex4321 (#12473) and @onesolpark (#12542)
## Summary
I ran `ruff check --extend-select RUF100 -n` to identify `# noqa`
comments that weren't having any effect in Ruff, and then `ruff check
--extend-select RUF100 -n --fix` on select files to remove all of the
unnecessary `# noqa: F401` violations. It's possible that these were
needed at some point in the past, but they're not necessary in Ruff
v0.1.15 (used by LangChain) or in the latest release.
Co-authored-by: Erick Friis <erick@langchain.dev>
OpenAI API compatible server may not support `safe_len_embedding`，
use `disable_safe_len_embeddings=True` to disable it.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor]
```python
class ToolCall(TypedDict):
name: str
args: Dict[str, Any]
id: Optional[str]
class InvalidToolCall(TypedDict):
name: Optional[str]
args: Optional[str]
id: Optional[str]
error: Optional[str]
class ToolCallChunk(TypedDict):
name: Optional[str]
args: Optional[str]
id: Optional[str]
index: Optional[int]
class AIMessage(BaseMessage):
...
tool_calls: List[ToolCall] = []
invalid_tool_calls: List[InvalidToolCall] = []
...
class AIMessageChunk(AIMessage, BaseMessageChunk):
...
tool_call_chunks: Optional[List[ToolCallChunk]] = None
...
```
Important considerations:
- Parsing logic occurs within different providers;
- ~Changing output type is a breaking change for anyone doing explicit
type checking;~
- ~Langsmith rendering will need to be updated:
https://github.com/langchain-ai/langchainplus/pull/3561~
- ~Langserve will need to be updated~
- Adding chunks:
- ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has
non-null .tool_calls.~
- Tool call chunks are appended, merging when having equal values of
`index`.
- additional_kwargs accumulate the normal way.
- During streaming:
- ~Messages can change types (e.g., from AIMessageChunk to
AIToolCallsMessageChunk)~
- Output parsers parse additional_kwargs (during .invoke they read off
tool calls).
Packages outside of `partners/`:
- https://github.com/langchain-ai/langchain-cohere/pull/7
- https://github.com/langchain-ai/langchain-google/pull/123/files
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:**
Use the `Stream` context managers in `ChatOpenAi` `stream` and `astream`
method.
Using the context manager returned by the OpenAI client makes it
possible to terminate the stream early since the response connection
will be closed when the context manager exists.
**Issue:** #5340
**Twitter handle:** @snopoke
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description:**: adding checking codes for calling AI model get error
in chat_models/base.py and llms/base.py
**Issue**: Sometimes the AI Model calling will get error, we should
raise it.
Otherwise, the next code 'choices.extend(response["choices"])' will
throw a "TypeError: 'NoneType' object is not iterable" error to mask the
true error.
Because 'response["choices"]' is None.
**Dependencies**: None
---------
Co-authored-by: yangkx <yangkx@asiainfo-int.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Due to changes in the OpenAI SDK, the previous method of setting the
OpenAI proxy in ChatOpenAI no longer works. This PR fixes this issue,
making the previous way of setting the OpenAI proxy in ChatOpenAI
effective again.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Update the docstring of OpenAI, OpenAIEmbeddings and
ChatOpenAI classes
**Issue:** Update import module paths to the current LangChain API
**Dependencies:** None
**Lint and test**: `make format` and `make lint` were run
This incorporates the review comments from langchain-ai/langchain#18637
which I closed due to an issue I had in updating that pr branch
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
# Proper example for AzureOpenAI usage in error message
The original error message is wrong in part of a usage example it gives.
Corrected to the right one.
Co-authored-by: Dzmitry Kankalovich <dzmitry_kankalovich@epam.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Replacing the deprecated predict() and apredict()
methods in the unit tests
**Issue:** Not applicable
**Dependencies:** None
**Lint and test**: `make format`, `make lint` and `make test` have been
run
- make schema Optional with default val None, since in json_mode you
don't need it if not parsing to pydantic
- change return_type -> include_raw
- expand docstring examples
## Summary
This PR upgrades LangChain's Ruff configuration in preparation for
Ruff's v0.2.0 release. (The changes are compatible with Ruff v0.1.5,
which LangChain uses today.) Specifically, we're now warning when
linter-only options are specified under `[tool.ruff]` instead of
`[tool.ruff.lint]`.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
All models should be calling the callback for new token prior to
yielding the token.
Not doing this can cause callbacks for downstream steps to be called
prior to the callback for the new token; causing issues in
astream_events APIs and other things that depend in callback ordering
being correct.
We need to make this change for all chat models.
… converters
One way to convert anything to an OAI function:
convert_to_openai_function
One way to convert anything to an OAI tool: convert_to_openai_tool
Corresponding bind functions on OAI models: bind_functions, bind_tools
- bumps package post versions for packages without current unreleased
updates
- will bump package version in release prs associated with packages that
do have changes (mistral, vertex)
