**Description:** We improve the performance of the InMemoryVectorStore.
**Isue:** Originally, similarity was computed document by document:
```
for doc in self.store.values():
vector = doc["vector"]
similarity = float(cosine_similarity([embedding], [vector]).item(0))
```
This is inefficient and does not make use of numpy vectorization.
This PR computes the similarity in one vectorized go:
```
docs = list(self.store.values())
similarity = cosine_similarity([embedding], [doc["vector"] for doc in docs])
```
**Dependencies:** None
**Twitter handle:** @b12_consulting, @Vincent_Min
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Fixes#27411
**Description:** Adds `template_format` to the `ImagePromptTemplate`
class and updates passing in the `template_format` parameter from
ChatPromptTemplate instead of the hardcoded "f-string".
Also updated docs and typing related to `template_format` to be more
up-to-date and specific.
**Dependencies:** None
**Add tests and docs**: Added unit tests to validate fix. Needed to
update `test_chat` snapshot due to adding new attribute
`template_format` in `ImagePromptTemplate`.
---------
Co-authored-by: Vadym Barda <vadym@langchain.dev>
## Description
This PR fixes the context loss issue in `AsyncCallbackManager`,
specifically in `on_llm_start` and `on_chat_model_start` methods. It
properly honors the `run_inline` attribute of callback handlers,
preventing race conditions and ordering issues.
Key changes:
1. Separate handlers into inline and non-inline groups.
2. Execute inline handlers sequentially for each prompt.
3. Execute non-inline handlers concurrently across all prompts.
4. Preserve context for stateful handlers.
5. Maintain performance benefits for non-inline handlers.
**These changes are implemented in `AsyncCallbackManager` rather than
`ahandle_event` because the issue occurs at the prompt and message_list
levels, not within individual events.**
## Testing
- Test case implemented in #26857 now passes, verifying execution order
for inline handlers.
## Related Issues
- Fixes issue discussed in #23909
## Dependencies
No new dependencies are required.
---
@eyurtsev: This PR implements the discussed changes to respect
`run_inline` in `AsyncCallbackManager`. Please review and advise on any
needed changes.
Twitter handle: @parambharat
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Added `**kwargs` parameters to the `index` and `aindex` functions in
`libs/core/langchain_core/indexing/api.py`. This allows users to pass
additional arguments to the `add_documents` and `aadd_documents`
methods, enabling the specification of a custom `vector_field`. For
example, users can now use `vector_field="embedding"` when indexing
documents in `OpenSearchVectorStore`
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
This commit addresses a typographical error in the documentation for the
async astream_events method. The word 'evens' was incorrectly used in
the introductory sentence for the reference table, which could lead to
confusion for users.\n\n### Changes Made:\n- Corrected 'Below is a table
that illustrates some evens that might be emitted by various chains.' to
'Below is a table that illustrates some events that might be emitted by
various chains.'\n\nThis enhancement improves the clarity of the
documentation and ensures accurate terminology is used throughout the
reference material.\n\nIssue Reference: #27107
Given the current erroring behavior, every time we've moved a kwarg from
model_kwargs and made it its own field that was a breaking change.
Updating this behavior to support the old instantiations /
serializations.
Assuming build_extra_kwargs was not something that itself is being used
externally and needs to be kept backwards compatible
This adds support for inject tool args that are arbitrary types when
used with pydantic 2.
We'll need to add similar logic on the v1 path, and potentially mirror
the config from the original model when we're doing the subset.
- **Description:** prevent index function to re-index entire source
document even if nothing has changed.
- **Issue:** #22135
I worked on a solution to this issue that is a compromise between being
cheap and being fast.
In the previous code, when batch_size is greater than the number of docs
from a certain source almost the entire source is deleted (all documents
from that source except for the documents in the first batch)
My solution deletes documents from vector store and record manager only
if at least one document has changed for that source.
Hope this can help!
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
* [chore]: Agent Observation should be casted to string to avoid errors
* Merge branch 'master' into fix_observation_type_streaming
* [chore]: Using Json.dumps
* [chore]: Exact same logic as when casting agent oobservation to string
template_format is an init argument on ChatPromptTemplate but not an
attribute on the object so was getting shoved into
StructuredPrompt.structured_ouptut_kwargs
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
