**Description:** Invoke callback prior to yielding token for llama.cpp
**Issue:** [Callback for on_llm_new_token should be invoked before the
token is yielded by the model
#16913](https://github.com/langchain-ai/langchain/issues/16913)
**Dependencies:** None
```python
from langchain.agents import tool
from langchain_mistralai import ChatMistralAI
llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
@tool
def get_word_length(word: str) -> int:
"""Returns the length of a word."""
return len(word)
tools = [get_word_length]
llm_with_tools = llm.bind_tools(tools)
llm_with_tools.invoke("how long is the word chrysanthemum")
```
currently raises
```
AttributeError: 'dict' object has no attribute 'model_dump'
```
Same with `.with_structured_output`
```python
from langchain_mistralai import ChatMistralAI
from langchain_core.pydantic_v1 import BaseModel
class AnswerWithJustification(BaseModel):
"""An answer to the user question along with justification for the answer."""
answer: str
justification: str
llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification)
structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
```
This appears to fix.
For prompt templates with only 1 variable (common in e.g.,
MessageGraph), it's convenient to wrap the incoming object in the
variable before formatting.
The downside of this, of course, would be that some number of
invocations will successfully format when the user may have intended to
format it properly before
This is a basic VectorStore implementation using an in-memory dict to
store the documents.
It doesn't need any extra/optional dependency as it uses numpy which is
already a dependency of langchain.
This is useful for quick testing, demos, examples.
Also it allows to write vendor-neutral tutorials, guides, etc...
Classes and functions defined in __init__.py are not parsed into the API
Reference.
For example:
- libs/core/langchain_core/messages/__init__.py : AnyMessage,
MessageLikeRepresentation, get_buffer_string(), messages_from_dict(),
...
Opinionated: __init__.py is not a typical place to define artifacts.
Moved artifacts from __init__ into utils.py.
Added `MessageLikeRepresentation` to __all__ since it is used outside of
`messages`, for example, in
`libs/core/langchain_core/language_models/base.py`
Added `_message_from_dict` to __all__ since it is used outside of
`messages`(???) I would add `message_from_dict` (without underscore) as
an alias. Please, advise.
Covered by tests in
`libs/core/tests/unit_tests/language_models/chat_models/test_base.py`,
`libs/core/tests/unit_tests/language_models/llms/test_base.py` and
`libs/core/tests/unit_tests/runnables/test_runnable_events.py`
**Description:**
Currently, `CacheBackedEmbeddings` computes vectors for *all* uncached
documents before updating the store. This pull request updates the
embedding computation loop to compute embeddings in batches, updating
the store after each batch.
I noticed this when I tried `CacheBackedEmbeddings` on our 30k document
set and the cache directory hadn't appeared on disk after 30 minutes.
The motivation is to minimize compute/data loss when problems occur:
* If there is a transient embedding failure (e.g. a network outage at
the embedding endpoint triggers an exception), at least the completed
vectors are written to the store instead of being discarded.
* If there is an issue with the store (e.g. no write permissions), the
condition is detected early without computing (and discarding!) all the
vectors.
**Issue:**
Implements enhancement #18026.
**Testing:**
I was unable to run unit tests; details in [this
post](https://github.com/langchain-ai/langchain/discussions/15019#discussioncomment-8576684).
---------
Signed-off-by: chrispy <chrispy@synopsys.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
## Description
Semantic Cache can retrieve noisy information if the score threshold for
the value is too low. Adding the ability to set a `score_threshold` on
cache construction can allow for less noisy scores to appear.
- [x] **Add tests and docs**
1. Added tests that confirm the `score_threshold` query is valid.
- [x] **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/
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Classes and functions defined in __init__.py are not parsed into the API
Reference.
For example: libs/core/langchain_core/globals/__init__.py :
`set_verbose` `get_llm_cache`, `set_llm_cache`, ...
And the whole `langchain_core.globals` namespace is not visible in the
API Reference. The refactoring is just file renaming.
- **Description:** Enhanced the `BaseChatModel` to support an
`Optional[Union[bool, BaseCache]]` type for the `cache` attribute,
allowing for both boolean flags and custom cache implementations.
Implemented logic within chat model methods to utilize the provided
custom cache implementation effectively. This change aims to provide
more flexibility in caching strategies for chat models.
- **Issue:** Implements enhancement request #17242.
- **Dependencies:** No additional dependencies required for this change.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Changing OpenAIAssistantRunnable.create_assistant to send the `file_ids`
parameter to openai.beta.assistants.create
Co-authored-by: Frederico Wu <fred.diaswu@coxautoinc.com>
**Description**:
this PR enable VectorStore autoconfiguration for Infinispan: if
metadatas are only of basic types, protobuf
config will be automatically generated for the user.
When creating a new index, if we use a retrieval strategy that expects a
model to be deployed in Elasticsearch, check if a model with this name
is indeed deployed before creating an index. This lowers the probability
to get into a state in which an index was created with a faulty model
ID, which cannot be overwritten any more (the index has to manually be
deleted).
Add `keep_alive` parameter to control how long the model will stay
loaded into memory with Ollama。
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Issue : For functions which have an argument with the name 'title', the
convert_pydantic_to_openai_function generates an incorrect output and
omits the argument all together. This is because the _rm_titles function
removes all instances of the the key 'title' from the output.
Description : Updates the _rm_titles function to check the presence of
the 'type' key as well before removing the 'title' key. As the title key
that we wish to omit always has a type key along with it.
Potential gap if there is a function defined which has both title and
key as argument names, in which case this would fail. Maybe we could set
a filter on the function argument names and reject those with keyword
argument names.
No dependencies. Passed all tests.
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [x] **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!
- [x] **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.
- [x] **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: Eugene Yurtsev <eyurtsev@gmail.com>
