Commit Graph

1368 Commits

Author SHA1 Message Date
Stephen Hankinson
316dddc7cd
fix wording of query_sql_database_tool_description (#11530)
- **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
2023-10-09 15:32:45 -07:00
Ash Vardanian
1acfe86353
Accelerating Math Utils with SimSIMD (#11566)
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>
2023-10-09 14:56:55 -07:00
benchello
5de64e6d60
Add option to specify metadata columns in CSV loader (#11576)
#### 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>
2023-10-09 14:56:45 -07:00
Stephen Hankinson
447a523662
fix comments in output format (#11536)
- **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:**
2023-10-09 14:55:44 -07:00
Michael Landis
8e45f720a8
feat: add momento vector index as a vector store provider (#11567)
**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.
2023-10-09 14:02:59 -07:00
Eugene Yurtsev
ca2eed36b7
LangChain cli fix a few bugs (#11573)
Code was assuming that `git` and `poetry` exist. In addition, it was not
ignoring pycache files that get generated during run time
2023-10-09 13:30:16 -07:00
Hugues Chocart
258ae1ba5f
[LLMonitor Callback Handler]: Add error handling (#11563)
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 🙂
2023-10-09 13:26:35 -07:00
Eugene Yurtsev
2aabfafe1e
Module documentation for langchain runnables (#11550)
Add in code documentation for langchain runnables module.
2023-10-09 16:02:29 -04:00
Eugene Yurtsev
d8fa94e6fa
RunnablePassthrough: In code documentation (#11552)
Add in code documentation for a runnable passthrough
2023-10-09 16:02:16 -04:00
Eugene Yurtsev
b42f218cfc
RunnableLambda: Add in code docs (#11521)
Add in code docs for Runnable Lambda
2023-10-09 14:37:46 -04:00
maks-operlejn-ds
f64522fbaf
Reset deanonymizer mapping (#11559)
@hwchase17 @baskaryan
2023-10-09 11:11:05 -07:00
maks-operlejn-ds
b14b65d62a
Support all presidio entities (#11558)
https://microsoft.github.io/presidio/supported_entities/

@baskaryan @hwchase17
2023-10-09 11:10:46 -07:00
maks-operlejn-ds
4d62def9ff
Better deanonymizer matching strategy (#11557)
@baskaryan, @hwchase17
2023-10-09 11:10:29 -07:00
Ash Vardanian
a992b9670d
Fix: Missing DuckDuckGo package version (#11535)
[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
2023-10-09 10:55:46 -07:00
Bagatur
8932ed3f07
bump 311 (#11555) 2023-10-09 08:17:07 -07:00
Bagatur
e7a0def1bc
QoL improvements to query constructor (#11504)
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
2023-10-09 08:10:52 -07:00
Taikono-Himazin
eec53fa294
Added autodetect_encoding option to csvLoader (#11327) 2023-10-09 08:06:43 -07:00
Holt Skinner
09c66fe04f
feat: Update Google Document AI Parser (#11413)
- **Description:** Code Refactoring, Documentation Improvements for
Google Document AI PDF Parser
  - Adds Online (synchronous) processing option.
  - Adds default field mask to limit payload size.
  - Skips Human review by default.
- **Issue:** Fixes #10589

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2023-10-09 08:04:25 -07:00
Nuno Campos
628cc4cce8
Rename RunnableMap to RunnableParallel (#11487)
- 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.
 -->
2023-10-09 11:22:03 +01:00
Eugene Yurtsev
6a10e8ef31
Add documentation to Runnable (#11516) 2023-10-08 08:09:04 +01:00
William FH
eb572f41a6
Add LangSmith Run Chat Loader (#11458) 2023-10-06 17:02:18 -07:00
David Duong
484947c492
Fetch up-to-date attributes for env-pulled kwargs during serialisation of OpenAI classes (#11499) 2023-10-06 22:43:29 +01:00
Bagatur
5470e730d2
raise openapi import error (#11495) 2023-10-06 12:57:24 -07:00
Erick Friis
29f5f70415
Rename some last hwchase17/langchain links (#11494) 2023-10-06 12:34:30 -07:00
Fabrice Pont
872836c541
feat: add markdown list parser (#11411)
**Description:** add `MarkdownListOutputParser` as a new
`ListOutputParser`
 **Issue:** #11410
2023-10-06 12:25:45 -07:00
Erick Friis
8f50b616c5
Remove optional from vectara source (#11493)
fyi @ofermend

---------

Co-authored-by: Ofer Mendelevitch <ofer@vectara.com>
Co-authored-by: Ofer Mendelevitch <ofermend@gmail.com>
2023-10-06 12:12:44 -07:00
Bagatur
53887242a1
bump 310 (#11486) 2023-10-06 09:49:10 -07:00
Jesús Vélez Santiago
a1c7532298
Add async sql record manager and async indexing API (#10726)
- **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>
2023-10-06 09:38:44 -04:00
Qihui Xie
57ade13b2b
fix llm_inputs duplication problem in intermediate_steps in SQLDatabaseChain (#10279)
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.
2023-10-05 21:32:08 -07:00
Florian
d78f418c0d
Extract abstracts from Pubmed articles, even if they have no extra label (#10245)
### 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>
2023-10-05 18:56:46 -07:00
Viktor Zhemchuzhnikov
fd9da60aea
Add async support to SelfQueryRetriever (#10175)
### 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
2023-10-05 18:54:21 -07:00
Theron Tau
35297ca0d3
Add feature for extracting images from pdf and recognizing text from images. (#10653)
**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>
2023-10-05 18:51:59 -07:00
Bagatur
8e3fbc97ca
Add vowpal_wabbit RL chain (#11462) 2023-10-05 18:39:45 -07:00
Haris Wang
f1269830a0
Fix bug in MarkdownHeaderTextSplitter for codeblock (#10262)
- 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>
2023-10-05 18:34:42 -07:00
Eddie Cohen
656d2303f7
add in, nin for pinecone (#10303)
Description: Adds the in and nin comparators for pinecone seen
[here](https://docs.pinecone.io/docs/metadata-filtering#metadata-query-language)

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-05 18:31:09 -07:00
Bagatur
a3a2ce623e Revise vowpal_wabbit notebook 2023-10-05 18:18:19 -07:00
Bagatur
8fafa1af91 merge 2023-10-05 18:09:35 -07:00
olgavrou
3b07c0cf3d
RL Chain with VowpalWabbit (#10242)
- 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
2023-10-05 18:07:22 -07:00
Manikanta5112
56048b909f
added ContentFormatter escape special characters for message content (#10319)
---------

Co-authored-by: Manikanta5112 <42089393+mani5112@users.noreply.github.com>
2023-10-05 18:02:29 -07:00
Leonid Ganeline
d17416ec79
docstrings callbacks (#11456)
Added missed docstrings to the `callbacks/`

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2023-10-05 17:13:14 -07:00
Ofer Mendelevitch
3c7653bf0f
"source" argument in constructor of Vectara (#11454)
Replace this entire comment with:
- **Description:** minor update to constructor to allow for
specification of "source"
  - **Tag maintainer:** @baskaryan
  - **Twitter handle:** @ofermend
2023-10-05 17:04:14 -07:00
Eugene Yurtsev
d9018ae5f1
Improve CLI ux (#11452)
Improve UX for cli
2023-10-05 19:40:00 -04:00
Jaikanth J
9f85f7c543
fix(cache): use dumps for RedisCache (#10408)
# 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
2023-10-05 16:34:07 -07:00
rodrigo-clickup
5944c1851b
Add ClickUp Toolkit (#10662)
- **Description:** Adds a toolkit to interact with the
[ClickUp](https://clickup.com/) [Public API](https://clickup.com/api/)
- **Dependencies:** None
- **Tag maintainer:** @rodrigo-georgian, @rodrigo-clickup,
@aiswaryasankarwork
- **Twitter handle:** 
- Aiswarya (https://twitter.com/Aiswarya_Sankar,
https://www.linkedin.com/in/sankaraiswarya/)
   - Rodrigo (https://www.linkedin.com/in/rodrigo-ceballos-lentini/)


---------

Co-authored-by: Aiswarya Sankar <aiswaryasankar@Aiswaryas-MacBook-Pro.local>
Co-authored-by: aiswaryasankarwork <143119412+aiswaryasankarwork@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-05 16:33:05 -07:00
John Reynolds
68901e1e40
Update output_parser.py (#10430)
- 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
2023-10-05 15:47:24 -07:00
Joshua Sundance Bailey
790010703b
ArcGISLoader: Limit number of results in query (#10615)
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`.
2023-10-05 15:46:02 -07:00
mrbean
9903a70379
Add youdotcom retriever (#11304)
---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-05 13:48:11 -07:00
ashish-dahal
1655ff2ded
Fix PyMuPDFLoader kwargs (#11434)
- **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>
2023-10-05 13:25:19 -07:00
Leonid Kuligin
e4a46747dc
integration test for DocAI parser (#11424)
- **Description:** added an integration test
  - **Issue:** #11407 

@baskaryan
2023-10-05 12:38:29 -07:00
Aashish Saini
2abbdc6ecb
Update bageldb.py (#11421)
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.
2023-10-05 12:37:56 -07:00
maks-operlejn-ds
2aae1102b0
Instance anonymization (#10501)
### 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>
2023-10-05 11:23:02 -07:00
Kyle Pancamo
203258b4d6
Update pdf.py comment for PyPDFLoader (#10495)
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>
2023-10-05 11:22:40 -07:00
Juan Daza
4236ae3851
Added Streaming Capability to SageMaker LLMs (#10535)
This PR adds the ability to declare a Streaming response in the
SageMaker LLM by leveraging the `invoke_endpoint_with_response_stream`
capability in `boto3`. It is heavily based on the AWS Blog Post
announcement linked
[here](https://aws.amazon.com/blogs/machine-learning/elevating-the-generative-ai-experience-introducing-streaming-support-in-amazon-sagemaker-hosting/).

It does not add any additional dependencies since it uses the existing
`boto3` version.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-05 11:08:43 -07:00
Laurentiu Piciu
d9670a5945
openai_functions_multi_agent: solved the case when the "arguments" is valid JSON but it does not contain actions key (#10543)
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>
2023-10-05 11:08:09 -07:00
Eugene Yurtsev
fcccde406d
Add SymbolicMathChain to experiment in preparation for deprecation (#11129)
Move symbolic math chain to experimental
2023-10-05 13:54:43 -04:00
Holt Skinner
9f73fec057
fix: Update Google Cloud Enterprise Search to Vertex AI Search (#10513)
- 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
2023-10-05 10:47:47 -07:00
Patrick Randell
1d678f805f
Additional Weaviate Filter Comparators (#10522)
### 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>
2023-10-05 10:40:04 -07:00
Nuno Campos
79011f835f
Remove str() from RunnableConfigurableAlternatives (#11446) 2023-10-05 18:40:00 +01:00
Harrison Chase
31d5bd84d7
make vectorstores optional (#11393) 2023-10-05 10:14:05 -07:00
Eugene Yurtsev
8aa545901a
Update agent type docs (#11137)
In code docs for agent types
2023-10-05 12:51:14 -04:00
Eugene Yurtsev
3e31d6e35f
Start deprecation of LLMBashChain (#11300)
In preparation for migration LLMBashChain and related tools add a
derprecation warning to the code.
2023-10-05 12:48:22 -04:00
Bagatur
8b6b8bf68c
bump 309 (#11443) 2023-10-05 09:29:14 -07:00
billytrend-cohere
2ff91a46c0
Add cohere /chat integration (#11389)
Add cohere /chat integration and an iPython notebook to demonstrate the
addition.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-05 09:20:47 -07:00
adrienohana
ca346011b7
added interactive login for azure cognitive search vector store (#11360)
**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.
2023-10-05 09:20:18 -07:00
Eugene Yurtsev
5a1f614175
Add docker compose to CLI (#11406)
Add docker compose to cli
2023-10-05 15:58:56 +01:00
Predrag Gruevski
e2d6c41177
Upgrade langchain dependencies. (#11420)
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.
2023-10-05 15:57:20 +01:00
Jacob Lee
71fd6428c5
Remove overridden async not implemented method on embeddings filters and add default async implementation for document compressors (#11415)
@nfcampos @eyurtsev @baskaryan

---------

Co-authored-by: Nuno Campos <nuno@boringbits.io>
2023-10-05 15:56:03 +01:00
Nuno Campos
2f490be09b
Fix .dict() for agent/chain (#11436)
<!-- 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.
 -->
2023-10-05 15:51:21 +01:00
Nuno Campos
1e59c44d36
Nc/5oct/runnable release (#11428)
<!-- 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.
 -->
2023-10-05 14:27:50 +01:00
Bagatur
58b7a3ba16
Rm bedrock anthropic error (#11403) 2023-10-04 23:31:51 -04:00
Predrag Gruevski
c9986bc3a9
Tweak type hints to match dependency's behavior. (#11355)
Needs #11353 to merge first, and a new `langchain` to be published with
those changes.
2023-10-04 22:36:58 -04:00
William FH
940b9ae30a
Normalize Option in Scoring Chain (#11412) 2023-10-04 15:59:28 -07:00
Eugene Yurtsev
70be04a816
CLI: Readme update (#11404)
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>
2023-10-04 16:25:37 -04:00
Nuno Campos
fde19c8667
Add CLI command to create a new project (#7837)
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>
2023-10-04 15:43:41 -04:00
mhwang-stripe
9cea796671
Make langchain compatible with SQLAlchemy<1.4.0 (#11390)
<!-- 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>
```
2023-10-04 15:41:20 -04:00
Nuno Campos
4d66756d93
Improve output of Runnable.astream_log() (#11391)
- 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.
 -->
2023-10-04 20:16:37 +01:00
Lester Solbakken
a30f98f534
Add Vespa vector store (#11329)
Addition of Vespa vector store integration including notebook showing
its use.

Maintainer: @lesters 
Twitter handle: LesterSolbakken
2023-10-04 14:59:11 -04:00
Nuno Campos
58a88f3911
Add optional input_types to prompt template (#11385)
- 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.
 -->
2023-10-04 18:54:53 +01:00
Tomaz Bratanic
71290315cf
Add optional Cypher validation tool (#11078)
LLMs have trouble with consistently getting the relationship direction
accurately. That's why I organized a competition how to best and most
simple to fix it based on the existing schema as a post-processing step.
https://github.com/tomasonjo/cypher-direction-competition

I am adding the winner's code in this PR:
https://github.com/sakusaku-rich/cypher-direction-competition
2023-10-04 12:54:37 -04:00
Bagatur
dd514c2781
bump 308 (#11383) 2023-10-04 12:10:09 -04:00
Leonid Kuligin
4f4e0f38fc
a better error description when GCP project is not set (#11377)
- **Description:** a little bit better error description
  - **Issue:** #10879
2023-10-04 11:57:47 -04:00
Nuno Campos
0d80226c64
Add _type to json functions output parser (#11381)
<!-- 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.
 -->
2023-10-04 16:56:45 +01:00
Bagatur
106608bc89
add default async (#11141) 2023-10-04 11:40:35 -04:00
Nuno Campos
b0893c7c6a
Use an enum for configurable_alternatives to make the generated json schema nicer (#11350) 2023-10-04 11:32:41 -04:00
Bagatur
b499de2926
Anthropic system message fix (#11301)
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
2023-10-04 11:32:24 -04:00
Massimiliano Angelino
2f83350eac
Feat bedrock cohere support (#11230)
**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>
2023-10-04 11:12:19 -04:00
Daniel Butler
939bceccb0
GitHubIssuesLoader Custom API URL Support (#11378)
- **Description:** Adds support for custom API URL in the
GitHubIssuesLoader. This allows it to be used with Github enterprise
instances.
2023-10-04 10:17:46 -04:00
Bagatur
16a80779b9
bump 307 (#11380) 2023-10-04 10:03:17 -04:00
mziru
9e3c1d4463
add HTMLHeaderTextSplitter (#11039)
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>
2023-10-04 09:24:25 -04:00
Predrag Gruevski
289de601c8
Use parameterized queries to select SQL schemas. (#11356) 2023-10-04 05:43:30 +01:00
Nuno Campos
b0097f8908
In ProgressBarCallback update the progress counter also when runs fin… (#11332) 2023-10-04 05:04:59 +01:00
William FH
06f39be1c2
Wfh/eval max concurrency (#11368) 2023-10-03 20:18:14 -07:00
Aashish Saini
4adb2b399d
Fixed exception type in py files (#11322)
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.
2023-10-03 21:46:26 -04:00
니콜라스
c6d7124675
Add 'device' to GPT4All (#11216)
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>
2023-10-03 17:37:30 -07:00
Harrison Chase
6e848b879a
add default for async (#11367) 2023-10-03 17:28:14 -07:00
Fynn Flügge
0a4baca291
chore: add kotlin code splitter (#11364)
<!-- 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>
2023-10-03 18:35:36 -04:00
Ofer Mendelevitch
b93a08079e
Updates to Vectara Implementation (#11366)
Replace this entire comment with:
  - **Description:** updates to documentation and API headers
  - **Tag maintainer:** @baskarya
  - **Twitter handle:** @ofermend
2023-10-03 18:34:39 -04:00
Erick Friis
745e3e29da
add getattr case for llms.type_to_cls_dict (#11362)
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.
2023-10-03 14:34:30 -07:00
Vicente Reyes
f3e13e7e5a
Use term keyword according to the official python doc glossary (#11338)
- **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
2023-10-03 12:56:08 -07:00
Predrag Gruevski
5d6b83d9cf
Make a copy of external data instead of mutating another object's attributes. (#11349)
Fix for a bug surfaced as part of #11339. `mypy` caught this since the
types didn't match up.
2023-10-03 15:27:51 -04:00