- **Description:** Fixes minor typo for the
query_sql_database_tool_description in the db toolkit
- **Issue:** N/A
- **Dependencies:** N/A
- **Tag maintainer:** @nfcampos
- **Twitter handle:** N/A
LangChain relies on NumPy to compute cosine distances, which becomes a
bottleneck with the growing dimensionality and number of embeddings. To
avoid this bottleneck, in our libraries at
[Unum](https://github.com/unum-cloud), we have created a specialized
package - [SimSIMD](https://github.com/ashvardanian/simsimd), that knows
how to use newer hardware capabilities. Compared to SciPy and NumPy, it
reaches 3x-200x performance for various data types. Since publication,
several LangChain users have asked me if I can integrate it into
LangChain to accelerate their workflows, so here I am 🤗
## Benchmarking
To conduct benchmarks locally, run this in your Jupyter:
```py
import numpy as np
import scipy as sp
import simsimd as simd
import timeit as tt
def cosine_similarity_np(X: np.ndarray, Y: np.ndarray) -> np.ndarray:
X_norm = np.linalg.norm(X, axis=1)
Y_norm = np.linalg.norm(Y, axis=1)
with np.errstate(divide="ignore", invalid="ignore"):
similarity = np.dot(X, Y.T) / np.outer(X_norm, Y_norm)
similarity[np.isnan(similarity) | np.isinf(similarity)] = 0.0
return similarity
def cosine_similarity_sp(X: np.ndarray, Y: np.ndarray) -> np.ndarray:
return 1 - sp.spatial.distance.cdist(X, Y, metric='cosine')
def cosine_similarity_simd(X: np.ndarray, Y: np.ndarray) -> np.ndarray:
return 1 - simd.cdist(X, Y, metric='cosine')
X = np.random.randn(1, 1536).astype(np.float32)
Y = np.random.randn(1, 1536).astype(np.float32)
repeat = 1000
print("NumPy: {:,.0f} ops/s, SciPy: {:,.0f} ops/s, SimSIMD: {:,.0f} ops/s".format(
repeat / tt.timeit(lambda: cosine_similarity_np(X, Y), number=repeat),
repeat / tt.timeit(lambda: cosine_similarity_sp(X, Y), number=repeat),
repeat / tt.timeit(lambda: cosine_similarity_simd(X, Y), number=repeat),
))
```
## Results
I ran this on an M2 Pro Macbook for various data types and different
number of rows in `X` and reformatted the results as a table for
readability:
| Data Type | NumPy | SciPy | SimSIMD |
| :--- | ---: | ---: | ---: |
| `f32, 1` | 59,114 ops/s | 80,330 ops/s | 475,351 ops/s |
| `f16, 1` | 32,880 ops/s | 82,420 ops/s | 650,177 ops/s |
| `i8, 1` | 47,916 ops/s | 115,084 ops/s | 866,958 ops/s |
| `f32, 10` | 40,135 ops/s | 24,305 ops/s | 185,373 ops/s |
| `f16, 10` | 7,041 ops/s | 17,596 ops/s | 192,058 ops/s |
| `f16, 10` | 21,989 ops/s | 25,064 ops/s | 619,131 ops/s |
| `f32, 100` | 3,536 ops/s | 3,094 ops/s | 24,206 ops/s |
| `f16, 100` | 900 ops/s | 2,014 ops/s | 23,364 ops/s |
| `i8, 100` | 5,510 ops/s | 3,214 ops/s | 143,922 ops/s |
It's important to note that SimSIMD will underperform if both matrices
are huge.
That, however, seems to be an uncommon usage pattern for LangChain
users.
You can find a much more detailed performance report for different
hardware models here:
- [Apple M2
Pro](https://ashvardanian.com/posts/simsimd-faster-scipy/#appendix-1-performance-on-apple-m2-pro).
- [4th Gen Intel Xeon
Platinum](https://ashvardanian.com/posts/simsimd-faster-scipy/#appendix-2-performance-on-4th-gen-intel-xeon-platinum-8480).
- [AWS Graviton
3](https://ashvardanian.com/posts/simsimd-faster-scipy/#appendix-3-performance-on-aws-graviton-3).
## Additional Notes
1. Previous version used `X = np.array(X)`, to repackage lists of lists.
It's an anti-pattern, as it will use double-precision floating-point
numbers, which are slow on both CPUs and GPUs. I have replaced it with
`X = np.array(X, dtype=np.float32)`, but a more selective approach
should be discussed.
2. In numerical computations, it's recommended to explicitly define
tolerance levels, which were previously avoided in
`np.allclose(expected, actual)` calls. For now, I've set absolute
tolerance to distance computation errors as 0.01: `np.allclose(expected,
actual, atol=1e-2)`.
---
- **Dependencies:** adds `simsimd` dependency
- **Tag maintainer:** @hwchase17
- **Twitter handle:** @ashvardanian
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
#### Description
This PR adds the option to specify additional metadata columns in the
CSVLoader beyond just `Source`.
The current CSV loader includes all columns in `page_content` and if we
want to have columns specified for `page_content` and `metadata` we have
to do something like the below.:
```
csv = pd.read_csv(
"path_to_csv"
).to_dict("records")
documents = [
Document(
page_content=doc["content"],
metadata={
"last_modified_by": doc["last_modified_by"],
"point_of_contact": doc["point_of_contact"],
}
) for doc in csv
]
```
#### Usage
Example Usage:
```
csv_test = CSVLoader(
file_path="path_to_csv",
metadata_columns=["last_modified_by", "point_of_contact"]
)
```
Example CSV:
```
content, last_modified_by, point_of_contact
"hello world", "Person A", "Person B"
```
Example Result:
```
Document {
page_content: "hello world"
metadata: {
row: '0',
source: 'path_to_csv',
last_modified_by: 'Person A',
point_of_contact: 'Person B',
}
```
---------
Co-authored-by: Ben Chello <bchello@dropbox.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Fixes the comments in the ConvoOutputParser. Because
the \\\\ is escaping a single \\, they render something like:
`"action_input": string \ The input to the action` in the prompt.
Changing this to \\\\\\\\ lets it escape two slashes so that it renders
a proper comment: `"action_input": string \\ The input to the action`
- **Issue:** N/A
- **Dependencies:**
- **Tag maintainer:** @hwchase17
- **Twitter handle:**
**Description**:
- Added Momento Vector Index (MVI) as a vector store provider. This
includes an implementation with docstrings, integration tests, a
notebook, and documentation on the docs pages.
- Updated the Momento dependency in pyproject.toml and the lock file to
enable access to MVI.
- Refactored the Momento cache and chat history session store to prefer
using "MOMENTO_API_KEY" over "MOMENTO_AUTH_TOKEN" for consistency with
MVI. This change is backwards compatible with the previous "auth_token"
variable usage. Updated the code and tests accordingly.
**Dependencies**:
- Updated Momento dependency in pyproject.toml.
**Testing**:
- Run the integration tests with a Momento API key. Get one at the
[Momento Console](https://console.gomomento.com) for free. MVI is
available in AWS us-west-2 with a superuser key.
- `MOMENTO_API_KEY=<your key> poetry run pytest
tests/integration_tests/vectorstores/test_momento_vector_index.py`
**Tag maintainer:**
@eyurtsev
**Twitter handle**:
Please mention @momentohq for this addition to langchain. With the
integration of Momento Vector Index, Momento caching, and session store,
Momento provides serverless support for the core langchain data needs.
Also mention @mlonml for the integration.
Wraps every callback handler method in error handlers to avoid breaking
users' programs when an error occurs inside the handler.
Thanks @valdo99 for the suggestion 🙂
[The `duckduckgo-search` v3.9.2 was removed from
PyPi](https://pypi.org/project/duckduckgo-search/#history). That breaks
the build.
- **Description:** refreshes the Poetry dependency to v3.9.3
- **Tag maintainer:** @baskaryan
- **Twitter handle:** @ashvardanian
updating query constructor and self query retriever to
- make it easier to pass in examples
- validate attributes used in query
- remove invalid parts of query
- make it easier to get + edit prompt
- make query constructor a runnable
- make self query retriever use as runnable
- keep alias for RunnableMap
- update docs to use RunnableParallel and RunnablePassthrough.assign
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- **Description:** Add support for a SQLRecordManager in async
environments. It includes the creation of `RecorManagerAsync` abstract
class.
- **Issue:** None
- **Dependencies:** Optional `aiosqlite`.
- **Tag maintainer:** @nfcampos
- **Twitter handle:** @jvelezmagic
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Use `.copy()` to fix the bug that the first `llm_inputs` element is
overwritten by the second `llm_inputs` element in `intermediate_steps`.
***Problem description:***
In [line 127](
c732d8fffd/libs/experimental/langchain_experimental/sql/base.py (L127C17-L127C17)),
the `llm_inputs` of the sql generation step is appended as the first
element of `intermediate_steps`:
```
intermediate_steps.append(llm_inputs) # input: sql generation
```
However, `llm_inputs` is a mutable dict, it is updated in [line
179](https://github.com/langchain-ai/langchain/blob/master/libs/experimental/langchain_experimental/sql/base.py#L179)
for the final answer step:
```
llm_inputs["input"] = input_text
```
Then, the updated `llm_inputs` is appended as another element of
`intermediate_steps` in [line
180](c732d8fffd/libs/experimental/langchain_experimental/sql/base.py (L180)):
```
intermediate_steps.append(llm_inputs) # input: final answer
```
As a result, the final `intermediate_steps` returned in [line
189](c732d8fffd/libs/experimental/langchain_experimental/sql/base.py (L189C43-L189C43))
actually contains two same `llm_inputs` elements, i.e., the `llm_inputs`
for the sql generation step overwritten by the one for final answer step
by mistake. Users are not able to get the actual `llm_inputs` for the
sql generation step from `intermediate_steps`
Simply calling `.copy()` when appending `llm_inputs` to
`intermediate_steps` can solve this problem.
### Description
This pull request involves modifications to the extraction method for
abstracts/summaries within the PubMed utility. A condition has been
added to verify the presence of unlabeled abstracts. Now an abstract
will be extracted even if it does not have a subtitle. In addition, the
extraction of the abstract was extended to books.
### Issue
The PubMed utility occasionally returns an empty result when extracting
abstracts from articles, despite the presence of an abstract for the
paper on PubMed. This issue arises due to the varying structure of
articles; some articles follow a "subtitle/label: text" format, while
others do not include subtitles in their abstracts. An example of the
latter case can be found at:
[https://pubmed.ncbi.nlm.nih.gov/37666905/](url)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Description
SelfQueryRetriever is missing async support, so I am adding it.
I also removed deprecated predict_and_parse method usage here, and added
some tests.
### Issue
N/A
### Tag maintainer
Not yet
### Twitter handle
N/A
**Description**
It is for #10423 that it will be a useful feature if we can extract
images from pdf and recognize text on them. I have implemented it with
`PyPDFLoader`, `PyPDFium2Loader`, `PyPDFDirectoryLoader`,
`PyMuPDFLoader`, `PDFMinerLoader`, and `PDFPlumberLoader`.
[RapidOCR](https://github.com/RapidAI/RapidOCR.git) is used to recognize
text on extracted images. It is time-consuming for ocr so a boolen
parameter `extract_images` is set to control whether to extract and
recognize. I have tested the time usage for each parser on my own laptop
thinkbook 14+ with AMD R7-6800H by unit test and the result is:
| extract_images | PyPDFParser | PDFMinerParser | PyMuPDFParser |
PyPDFium2Parser | PDFPlumberParser |
| ------------- | ------------- | ------------- | ------------- |
------------- | ------------- |
| False | 0.27s | 0.39s | 0.06s | 0.08s | 1.01s |
| True | 17.01s | 20.67s | 20.32s | 19,75s | 20.55s |
**Issue**
#10423
**Dependencies**
rapidocr_onnxruntime in
[RapidOCR](https://github.com/RapidAI/RapidOCR/tree/main)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: The previous version of the MarkdownHeaderTextSplitter
did not take into account the possibility of '#' appearing within code
blocks, which caused segmentation anomalies in these situations. This PR
has fixed this issue.
- Issue:
- Dependencies: No
- Tag maintainer:
- Twitter handle:
cc @baskaryan @eyurtsev @rlancemartin
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: This PR adds a new chain `rl_chain.PickBest` for learned
prompt variable injection, detailed description and usage can be found
in the example notebook added. It essentially adds a
[VowpalWabbit](https://github.com/VowpalWabbit/vowpal_wabbit) layer
before the llm call in order to learn or personalize prompt variable
selections.
Most of the code is to make the API simple and provide lots of defaults
and data wrangling that is needed to use Vowpal Wabbit, so that the user
of the chain doesn't have to worry about it.
- Dependencies:
[vowpal-wabbit-next](https://pypi.org/project/vowpal-wabbit-next/),
- sentence-transformers (already a dep)
- numpy (already a dep)
- tagging @ataymano who contributed to this chain
- Tag maintainer: @baskaryan
- Twitter handle: @olgavrou
Added example notebook and unit tests
Replace this entire comment with:
- **Description:** minor update to constructor to allow for
specification of "source"
- **Tag maintainer:** @baskaryan
- **Twitter handle:** @ofermend
# Description
Attempts to fix RedisCache for ChatGenerations using `loads` and `dumps`
used in SQLAlchemy cache by @hwchase17 . this is better than pickle
dump, because this won't execute any arbitrary code during
de-serialisation.
# Issues
#7722 & #8666
# Dependencies
None, but removes the warning introduced in #8041 by @baskaryan
Handle: @jaikanthjay46
- Description: Updated output parser for mrkl to remove any
hallucination actions after the final answer; this was encountered when
using Anthropic claude v2 for planning; reopening PR with updated unit
tests
- Issue: #10278
- Dependencies: N/A
- Twitter handle: @johnreynolds
Description: this PR changes the `ArcGISLoader` to set
`return_all_records` to `False` when `result_record_count` is provided
as a keyword argument. Previously, `return_all_records` was `True` by
default and this made the API ignore `result_record_count`.
Issue: `ArcGISLoader` would ignore `result_record_count` unless user
also passed `return_all_records=False`.
- **Description:** Fix the `PyMuPDFLoader` to accept `loader_kwargs`
from the document loader's `loader_kwargs` option. This provides more
flexibility in formatting the output from documents.
- **Issue:** The `loader_kwargs` is not passed into the `load` method
from the document loader, which limits configuration options.
- **Dependencies:** None
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
I have restructured the code to ensure uniform handling of ImportError.
In place of previously used ValueError, I've adopted the standard
practice of raising ImportError with explanatory messages. This
modification enhances code readability and clarifies that any problems
stem from module importation.
### Description
Add instance anonymization - if `John Doe` will appear twice in the
text, it will be treated as the same entity.
The difference between `PresidioAnonymizer` and
`PresidioReversibleAnonymizer` is that only the second one has a
built-in memory, so it will remember anonymization mapping for multiple
texts:
```
>>> anonymizer = PresidioAnonymizer()
>>> anonymizer.anonymize("My name is John Doe. Hi John Doe!")
'My name is Noah Rhodes. Hi Noah Rhodes!'
>>> anonymizer.anonymize("My name is John Doe. Hi John Doe!")
'My name is Brett Russell. Hi Brett Russell!'
```
```
>>> anonymizer = PresidioReversibleAnonymizer()
>>> anonymizer.anonymize("My name is John Doe. Hi John Doe!")
'My name is Noah Rhodes. Hi Noah Rhodes!'
>>> anonymizer.anonymize("My name is John Doe. Hi John Doe!")
'My name is Noah Rhodes. Hi Noah Rhodes!'
```
### Twitter handle
@deepsense_ai / @MaksOpp
### Tag maintainer
@baskaryan @hwchase17 @hinthornw
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
PyPDF does not chunk at the character level to my understanding.
Description: PyPDF does not chunk at the character level, but instead
breaks up content by page. Fixup comment
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: There are cases when the output from the LLM comes fine
(i.e. function_call["arguments"] is a valid JSON object), but it does
not contain the key "actions". So I split the validation in 2 steps:
loading arguments as JSON and then checking for "actions" in it.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Google Cloud Enterprise Search was renamed to Vertex AI
Search
-
https://cloud.google.com/blog/products/ai-machine-learning/vertex-ai-search-and-conversation-is-now-generally-available
- This PR updates the documentation and Retriever class to use the new
terminology.
- Changed retriever class from `GoogleCloudEnterpriseSearchRetriever` to
`GoogleVertexAISearchRetriever`
- Updated documentation to specify that `extractive_segments` requires
the new [Enterprise
edition](https://cloud.google.com/generative-ai-app-builder/docs/about-advanced-features#enterprise-features)
to be enabled.
- Fixed spelling errors in documentation.
- Change parameter for Retriever from `search_engine_id` to
`data_store_id`
- When this retriever was originally implemented, there was no
distinction between a data store and search engine, but now these have
been split.
- Fixed an issue blocking some users where the api_endpoint can't be set
### Description
When using Weaviate Self-Retrievers, certain common filter comparators
generated by user queries were unimplemented, resulting in errors. This
PR implements some of them. All linting and format commands have been
run and tests passed.
### Issue
#10474
### Dependencies
timestamp module
---------
Co-authored-by: Patrick Randell <prandell@deloitte.com.au>
**Description:** Previously if the access to Azure Cognitive Search was
not done via an API key, the default credential was called which doesn't
allow to use an interactive login. I simply added the option to use
"INTERACTIVE" as a key name, and this will launch a login window upon
initialization of the AzureSearch object.
I was hoping this would pick up numpy 1.26, which is required to support
the new Python 3.12 release, but it didn't. It seems that some
transitive dependency requirement on numpy is preventing that, and the
highest we can currently go is 1.24.x.
But to find this out required a 15min `poetry lock`, so I figured we
might as well upgrade the dependencies we can and hopefully make the
next dependency upgrade a bit smaller.
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Consolidating to a single README for now, will be easier to maintain we
can differentiate between poetry and pip later. Does not seem critical.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
First version of CLI command to create a new langchain project template
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
## Description
Currently SQLAlchemy >=1.4.0 is a hard requirement. We are unable to run
`from langchain.vectorstores import FAISS` with SQLAlchemy <1.4.0 due to
top-level imports, even if we aren't even using parts of the library
that use SQLAlchemy. See Testing section for repro. Let's make it so
that langchain is still compatible with SQLAlchemy <1.4.0, especially if
we aren't using parts of langchain that require it.
The main conflict is that SQLAlchemy removed `declarative_base` from
`sqlalchemy.ext.declarative` in 1.4.0 and moved it to `sqlalchemy.orm`.
We can fix this by try-catching the import. This is the same fix as
applied in https://github.com/langchain-ai/langchain/pull/883.
(I see that there seems to be some refactoring going on about isolating
dependencies, e.g.
c87e9fb2ce,
so if this issue will be eventually fixed by isolating imports in
langchain.vectorstores that also works).
## Issue
I can't find a matching issue.
## Dependencies
No additional dependencies
## Maintainer
@hwchase17 since you reviewed
https://github.com/langchain-ai/langchain/pull/883
## Testing
I didn't add a test, but I manually tested this.
1. Current failure:
```
langchain==0.0.305
sqlalchemy==1.3.24
```
``` python
python -i
>>> from langchain.vectorstores import FAISS
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/pay/src/zoolander/vendor3/lib/python3.8/site-packages/langchain/vectorstores/__init__.py", line 58, in <module>
from langchain.vectorstores.pgembedding import PGEmbedding
File "/pay/src/zoolander/vendor3/lib/python3.8/site-packages/langchain/vectorstores/pgembedding.py", line 10, in <module>
from sqlalchemy.orm import Session, declarative_base, relationship
ImportError: cannot import name 'declarative_base' from 'sqlalchemy.orm' (/pay/src/zoolander/vendor3/lib/python3.8/site-packages/sqlalchemy/orm/__init__.py)
```
2. This fix:
```
langchain==<this PR>
sqlalchemy==1.3.24
```
``` python
python -i
>>> from langchain.vectorstores import FAISS
<succeeds>
```
- Make logs a dictionary keyed by run name (and counter for repeats)
- Ensure no output shows up in lc_serializable format
- Fix up repr for RunLog and RunLogPatch
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- default MessagesPlaceholder one to list of messages
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Removes human prompt prefix before system message for anthropic models
Bedrock anthropic api enforces that Human and Assistant messages must be
interleaved (cannot have same type twice in a row). We currently treat
System Messages as human messages when converting messages -> string
prompt. Our validation when using Bedrock/BedrockChat raises an error
when this happens. For ChatAnthropic we don't validate this so no error
is raised, but perhaps the behavior is still suboptimal
**Description:**
Added support for Cohere command model via Bedrock.
With this change it is now possible to use the `cohere.command-text-v14`
model via Bedrock API.
About Streaming: Cohere model outputs 2 additional chunks at the end of
the text being generated via streaming: a chunk containing the text
`<EOS_TOKEN>`, and a chunk indicating the end of the stream. In this
implementation I chose to ignore both chunks. An alternative solution
could be to replace `<EOS_TOKEN>` with `\n`
Tests: manually tested that the new model work with both
`llm.generate()` and `llm.stream()`.
Tested with `temperature`, `p` and `stop` parameters.
**Issue:** #11181
**Dependencies:** No new dependencies
**Tag maintainer:** @baskaryan
**Twitter handle:** mangelino
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Description: Similar in concept to the `MarkdownHeaderTextSplitter`, the
`HTMLHeaderTextSplitter` is a "structure-aware" chunker that splits text
at the element level and adds metadata for each header "relevant" to any
given chunk. It can return chunks element by element or combine elements
with the same metadata, with the objectives of (a) keeping related text
grouped (more or less) semantically and (b) preserving context-rich
information encoded in document structures. It can be used with other
text splitters as part of a chunking pipeline.
Dependency: lxml python package
Maintainer: @hwchase17
Twitter handle: @MartinZirulnik
---------
Co-authored-by: PresidioVantage <github@presidiovantage.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
I've refactored the code to ensure that ImportError is consistently
handled. Instead of using ValueError as before, I've now followed the
standard practice of raising ImportError along with clear and
informative error messages. This change enhances the code's clarity and
explicitly signifies that any problems are associated with module
imports.
Add device to GPT4All
- **Description:** GPT4All now supports GPU. This commit adds the option
to enable it.
- **Issue:** It closes
https://github.com/langchain-ai/langchain/issues/10486
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- **Description:** Adds Kotlin language to `TextSplitter`
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
For external libraries that depend on `type_to_cls_dict`, adds a
workaround to continue using the old format.
Recommend people use `get_type_to_cls_dict()` instead and only resolve
the imports when they're used.
- **Description:** use term keyword according to the official python doc
glossary, see https://docs.python.org/3/glossary.html
- **Issue:** not applicable
- **Dependencies:** not applicable
- **Tag maintainer:** @hwchase17
- **Twitter handle:** vreyespue
