This PR updates the documentation examples that used
RunnableWithMessageHistory to show how to achieve the same
implementation with langgraph memory.
Some of the underlying PRs (not all of them):
- docs[patch]: update chatbot tutorial and migration guide (#26780)
- docs[patch]: update chatbot memory how-to (#26790)
- docs[patch]: update chatbot tools how-to (#26816)
- docs: update chat history in rag how-to (#26821)
- docs: update trim messages notebook (#26793)
- docs: clean up imports in how to guide for rag qa with chat history
(#26825)
- docs[patch]: update conversational rag tutorial (#26814)
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Vadym Barda <vadym@langchain.dev>
Co-authored-by: mercyspirit <ziying.qiu@gmail.com>
Co-authored-by: aqiu7 <aqiu7@gatech.edu>
Co-authored-by: John <43506685+Coniferish@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
Co-authored-by: Subhrajyoty Roy <subhrajyotyroy@gmail.com>
Co-authored-by: Rajendra Kadam <raj.725@outlook.com>
Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
Co-authored-by: Devin Gaffney <itsme@devingaffney.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
This prevents `trim_messages` from raising an `IndexError` when invoked
with `include_system=True`, `strategy="last"`, and an empty message
list.
Fixes#26895
Dependencies: none
Ruff doesn't know about the python version in
`[tool.poetry.dependencies]`. It can get it from
`project.requires-python`.
Notes:
* poetry seems to have issues getting the python constraints from
`requires-python` and using `python` in per dependency constraints. So I
had to duplicate the info. I will open an issue on poetry.
* `inspect.isclass()` doesn't work correctly with `GenericAlias`
(`list[...]`, `dict[..., ...]`) on Python <3.11 so I added some `not
isinstance(type, GenericAlias)` checks:
Python 3.11
```pycon
>>> import inspect
>>> inspect.isclass(list)
True
>>> inspect.isclass(list[str])
False
```
Python 3.9
```pycon
>>> import inspect
>>> inspect.isclass(list)
True
>>> inspect.isclass(list[str])
True
```
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
**Description:**
LLM will stop generating text even in the middle of a sentence if
`finish_reason` is `length` (for OpenAI) or `stop_reason` is
`max_tokens` (for Anthropic).
To obtain longer outputs from LLM, we should call the message generation
API multiple times and merge the results into the text to circumvent the
API's output token limit.
The extra line breaks forced by the `merge_message_runs` function when
seamlessly merging messages can be annoying, so I added the option to
specify the chunk separator.
**Issue:**
No corresponding issues.
**Dependencies:**
No dependencies required.
**Twitter handle:**
@hanama_chem
https://x.com/hanama_chem
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Anthropic models (including via Bedrock and other cloud platforms)
accept a status/is_error attribute on tool messages/results
(specifically in `tool_result` content blocks for Anthropic API). Adding
a ToolMessage.status attribute so that users can set this attribute when
using those models
The functions `convert_to_messages` has had an expansion of the
arguments it can take:
1. Previously, it only could take a `Sequence` in order to iterate over
it. This has been broadened slightly to an `Iterable` (which should have
no other impact).
2. Support for `PromptValue` and `BaseChatPromptTemplate` has been
added. These are generated when combining messages using the overloaded
`+` operator.
Functions which rely on `convert_to_messages` (namely `filter_messages`,
`merge_message_runs` and `trim_messages`) have had the type of their
arguments similarly expanded.
Resolves#23706.
<!--
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
-->
---------
Signed-off-by: JP-Ellis <josh@jpellis.me>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Decisions to discuss:
1. is a new attr needed or could additional_kwargs be used for this
2. is raw_output a good name for this attr
3. should raw_output default to {} or None
4. should raw_output be included in serialization
5. do we need to update repr/str to exclude raw_output
- add version of AIMessageChunk.__add__ that can add many chunks,
instead of only 2
- In agenerate_from_stream merge and parse chunks in bg thread
- In output parse base classes do more work in bg threads where
appropriate
---------
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
resolves https://github.com/langchain-ai/langchain/issues/23911
When an AIMessageChunk is instantiated, we attempt to parse tool calls
off of the tool_call_chunks.
Here we add a special-case to this parsing, where `""` will be parsed as
`{}`.
This is a reaction to how Anthropic streams tool calls in the case where
a function has no arguments:
```
{'id': 'toolu_01J8CgKcuUVrMqfTQWPYh64r', 'input': {}, 'name': 'magic_function', 'type': 'tool_use', 'index': 1}
{'partial_json': '', 'type': 'tool_use', 'index': 1}
```
The `partial_json` does not accumulate to a valid json string-- most
other providers tend to emit `"{}"` in this case.
This change adds a new message type `RemoveMessage`. This will enable
`langgraph` users to manually modify graph state (or have the graph
nodes modify the state) to remove messages by `id`
Examples:
* allow users to delete messages from state by calling
```python
graph.update_state(config, values=[RemoveMessage(id=state.values[-1].id)])
```
* allow nodes to delete messages
```python
graph.add_node("delete_messages", lambda state: [RemoveMessage(id=state[-1].id)])
```
- Moved doc-strings below attribtues in TypedDicts -- seems to render
better on APIReference pages.
* Provided more description and some simple code examples
Anthropic's streaming treats tool calls as different content parts
(streamed back with a different index) from normal content in the
`content`.
This means that we need to update our chunk-merging logic to handle
chunks with multi-part content. The alternative is coerceing Anthropic's
responses into a string, but we generally like to preserve model
provider responses faithfully when we can. This will also likely be
useful for multimodal outputs in the future.
This current PR does unfortunately make `index` a magic field within
content parts, but Anthropic and OpenAI both use it at the moment to
determine order anyway. To avoid cases where we have content arrays with
holes and to simplify the logic, I've also restricted merging to chunks
in order.
TODO: tests
CC @baskaryan @ccurme @efriis
```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."""
...
```
- support two-tuples of any sequence type (eg. json.loads never produces
tuples)
- support type alias for role key
- if id is passed in in dict form use it
- if tool_calls passed in in dict form use them
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Mistral gives us one ID per response, no individual IDs for tool calls.
```python
from langchain.agents import AgentExecutor, create_tool_calling_agent, tool
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_mistralai import ChatMistralAI
prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant"),
("human", "{input}"),
MessagesPlaceholder("agent_scratchpad"),
]
)
model = ChatMistralAI(model="mistral-large-latest", temperature=0)
@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return input + 2
tools = [magic_function]
agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "what is the value of magic_function(3)?"})
```
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@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>
