Preventing error caused by attempting to move the model that was already
loaded on the GPU using the Accelerate module to the same or another
device. It is not possible to load model with Accelerate/PEFT to CPU for
now
Addresses:
[#10985](https://github.com/langchain-ai/langchain/issues/10985)
<!-- 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:** This is an update to OctoAI LLM provider that adds
support for llama2 endpoints hosted on OctoAI and updates MPT-7b url
with the current one.
@baskaryan
Thanks!
---------
Co-authored-by: ML Wiz <bassemgeorgi@gmail.com>
**Description:** I noticed the metadata returned by the url_selenium
loader was missing several values included by the web_base loader. (The
former returned `{source: ...}`, the latter returned `{source: ...,
title: ..., description: ..., language: ...}`.) This change fixes it so
both loaders return all 4 key value pairs.
Files have been properly formatted and all tests are passing. Note,
however, that I am not much of a python expert, so that whole "Adding
the imports inside the code so that tests pass" thing seems weird to me.
Please LMK if I did anything wrong.
- **Description:** Assigning the custom_llm_provider to the default
params function so that it will be passed to the litellm
- **Issue:** Even though the custom_llm_provider argument is being
defined it's not being assigned anywhere in the code and hence its not
being passed to litellm, therefore any litellm call which uses the
custom_llm_provider as required parameter is being failed. This
parameter is mainly used by litellm when we are doing inference via
Custom API server.
https://docs.litellm.ai/docs/providers/custom_openai_proxy
- **Dependencies:** No dependencies are required
@krrishdholakia , @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@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:** This PR introduces a new LLM and Retriever API to
https://arcee.ai for the python client
- **Issue:** implements the integrations as requested in #11578 ,
- **Dependencies:** no dependencies are required,
- **Tag maintainer:** @hwchase17
- **Twitter handle:** shwooobham
**✅ `make format`, `make lint` and `make test` runs locally.**
```shell
=========== 1245 passed, 277 skipped, 20 warnings in 16.26s ===========
./scripts/check_pydantic.sh .
./scripts/check_imports.sh
poetry run ruff .
[ "." = "" ] || poetry run black . --check
All done! ✨🍰✨
1818 files would be left unchanged.
[ "." = "" ] || poetry run mypy .
Success: no issues found in 1815 source files
[ "." = "" ] || poetry run black .
All done! ✨🍰✨
1818 files left unchanged.
[ "." = "" ] || poetry run ruff --select I --fix .
poetry run codespell --toml pyproject.toml
poetry run codespell --toml pyproject.toml -w
```
**Contributions**
1. Arcee (langchain/llms), ArceeRetriever (langchain/retrievers),
ArceeWrapper (langchain/utilities)
2. docs for Arcee (llms/arcee.py) and
ArceeRetriever(retrievers/arcee.py)
3.
cc: @jacobsolawetz @ben-epstein
---------
Co-authored-by: Shubham <shubham@sORo.local>
jinja2 templates are not sandboxed and are at risk for arbitrary code
execution. To mitigate this risk:
- We no longer support loading jinja2-formatted prompt template files.
- `PromptTemplate` with jinja2 may still be constructed manually, but
the class carries a security warning reminding the user to not pass
untrusted input into it.
Resolves#4394.
<!-- 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:** CohereRerank is missing `cohere_api_key` as a field and
since extras are forbidden, it is not possible to pass-in the key. The
only way is to use an env variable named `COHERE_API_KEY`.
For example, if trying to create a compressor like this:
```python
cohere_api_key = "......Cohere api key......"
compressor = CohereRerank(cohere_api_key=cohere_api_key)
```
you will get the following error:
```
File "/langchain/.venv/lib/python3.10/site-packages/pydantic/v1/main.py", line 341, in __init__
raise validation_error
pydantic.v1.error_wrappers.ValidationError: 1 validation error for CohereRerank
cohere_api_key
extra fields not permitted (type=value_error.extra)
```
- **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
The previous API of the `_execute()` function had a few rough edges that
this PR addresses:
- The `fetch` argument was type-hinted as being able to take any string,
but any string other than `"all"` or `"one"` would `raise ValueError`.
The new type hints explicitly declare that only those values are
supported.
- The return type was type-hinted as `Sequence` but using `fetch =
"one"` would actually return a single result item. This was incorrectly
suppressed using `# type: ignore`. We now always return a list.
- Using `fetch = "one"` would return a single item if data was found, or
an empty *list* if no data was found. This was confusing, and we now
always return a list to simplify.
- The return type was `Sequence[Any]` which was a bit difficult to use
since it wasn't clear what one could do with the returned rows. I'm
making the new type `Dict[str, Any]` that corresponds to the column
names and their values in the query.
I've updated the use of this method elsewhere in the file to match the
new behavior.
continuation of PR #8550
@hwchase17 please see and merge. And also close the PR #8550.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Instead of:
```
client = Client()
with collect_runs() as cb:
chain.invoke()
run = cb.traced_runs[0]
client.get_run_url(run)
```
it's
```
with tracing_v2_enabled() as cb:
chain.invoke()
cb.get_run_url()
```
<!-- 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/hwchase17/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. These live is docs/extras
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17, @rlancemartin.
-->
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Similarly to Vertex classes, PaLM classes weren't marked as
serialisable. Should be working fine with LangSmith.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
<!-- 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/hwchase17/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.
-->
This PR uses 2 dedicated LangChain warnings types for deprecations
(mirroring python's built in deprecation and pending deprecation
warnings).
These deprecation types are unslienced during initialization in
langchain achieving the same default behavior that we have with our
current warnings approach. However, because these warnings have a
dedicated type, users will be able to silence them selectively (I think
this is strictly better than our current handling of warnings).
The PR adds a deprecation warning to llm symbolic math.
---------
Co-authored-by: Predrag Gruevski <2348618+obi1kenobi@users.noreply.github.com>
- Also move RunnableBranch to its own file
<!-- 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
renamed several repository links from `hwchase17` to `langchain-ai`.
### Why
I discovered that the README file in the devcontainer contains an old
repository name, so I took the opportunity to rename the old repository
name in all files within the repository, excluding those that do not
require changes.
### Dependencies
none
### Tag maintainer
@baskaryan
### Twitter handle
[kzk_maeda](https://twitter.com/kzk_maeda)
**Description:** Adds streaming and many more sampling parameters to the
DeepSparse interface
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:** Fix a code injection vuln by adding one more keyword
into the filtering list
- **Issue:** N/A
- **Dependencies:** N/A
- **Tag maintainer:**
- **Twitter handle:**
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Passes through dict input and assigns additional keys
<!-- 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/hwchase17/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.
-->
<img width="1728" alt="Screenshot 2023-09-28 at 20 15 01"
src="https://github.com/langchain-ai/langchain/assets/56902/ed0644c3-6db7-41b9-9543-e34fce46d3e5">
<!-- 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/hwchase17/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.
-->
Suppress warnings in interactive environments that can arise from users
relying on tab completion (without even using deprecated modules).
jupyter seems to filter warnings by default (at least for me), but
ipython surfaces them all
- **Description:** A Document Loader for MongoDB
- **Issue:** n/a
- **Dependencies:** Motor, the async driver for MongoDB
- **Tag maintainer:** n/a
- **Twitter handle:** pigpenblue
Note that an initial mongodb document loader was created 4 months ago,
but the [PR ](https://github.com/langchain-ai/langchain/pull/4285)was
never pulled in. @leo-gan had commented on that PR, but given it is
extremely far behind the master branch and a ton has changed in
Langchain since then (including repo name and structure), I rewrote the
branch and issued a new PR with the expectation that the old one can be
closed.
Please reference that old PR for comments/context, but it can be closed
in favor of this one. Thanks!
---------
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/hwchase17/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.
-->
```
ChatPromptTemplate(messages=[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], template='You are a nice assistant.')), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['question'], template='{question}'))])
| RunnableLambda(lambda x: x)
| {
chat: FakeListChatModel(responses=["i'm a chatbot"]),
llm: FakeListLLM(responses=["i'm a textbot"])
}
```
<!-- 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/hwchase17/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:**
be able to use langchain with other version than tiktoken 0.3.3 i.e
0.5.1
- **Issue:**
cannot installed the conda-forge version since it applied all optional
dependency:
https://github.com/conda-forge/langchain-feedstock/pull/85
replace "^0.3.2" by "">=0.3.2,<0.6.0" and "^3.9" by python=">=3.9"
Tested with python 3.10, langchain=0.0.288 and tiktoken==0.5.0
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
## Description
As of now, when instantiating and during inference, `LlamaCppEmbeddings`
outputs (a lot of) verbose when controlled from Langchain binding - it
is a bit annoying when computing the embeddings of long documents, for
instance.
This PR adds `verbose` for `LlamaCppEmbeddings` objects to be able
**not** to print the verbose of the model to `stderr`. It is natively
supported by `llama-cpp-python` and directly passed to the library – the
PR is hence very small.
The value of `verbose` is `True` by default, following the way it is
defined in [`LlamaCpp` (`llamacpp.py`
#L136-L137)](c87e9fb2ce/libs/langchain/langchain/llms/llamacpp.py (L136-L137))
## Issue
_No issue linked_
## Dependencies
_No additional dependency needed_
## To see it in action
```python
from langchain.embeddings import LlamaCppEmbeddings
MODEL_PATH = "<path_to_gguf_file>"
if __name__ == "__main__":
llm_embeddings = LlamaCppEmbeddings(
model_path=MODEL_PATH,
n_gpu_layers=1,
n_batch=512,
n_ctx=2048,
f16_kv=True,
verbose=False,
)
```
Co-authored-by: Bagatur <baskaryan@gmail.com>
# Description
Adds logic for NotionDBLoader to correctly populate `last_edited_time`
and `created_time` fields from [page
properties](https://developers.notion.com/reference/page#property-value-object).
There are no relevant tests for this code to be updated.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Based on the customers' requests for native langchain integration,
SearchApi is ready to invest in AI and LLM space, especially in
open-source development.
- This is our initial PR and later we want to improve it based on
customers' and langchain users' feedback. Most likely changes will
affect how the final results string is being built.
- We are creating similar native integration in Python and JavaScript.
- The next plan is to integrate into Java, Ruby, Go, and others.
- Feel free to assign @SebastjanPrachovskij as a main reviewer for any
SearchApi-related searches. We will be glad to help and support
langchain development.
- **Description:**
- Make running integration test for opensearch easy
- Provide a way to use different text for embedding: refer to #11002 for
more of the use case and design decision.
- **Issue:** N/A
- **Dependencies:** None other than the existing ones.
Both black and mypy expect a list of files or directories as input.
As-is the Makefile computes a list files changed relative to the last
commit; these are passed to black and mypy in the `format_diff` and
`lint_diff` targets. This is done by way of the Makefile variable
`PYTHON_FILES`. This is to save time by skipping running mypy and black
over the whole source tree.
When no changes have been made, this variable is empty, so the call to
black (and mypy) lacks input files. The call exits with error causing
the Makefile target to error out with:
```bash
$ make format_diff
poetry run black
Usage: black [OPTIONS] SRC ...
One of 'SRC' or 'code' is required.
make: *** [format_diff] Error 1
```
This is unexpected and undesirable, as the naive caller (that's me! 😄 )
will think something else is wrong. This commit smooths over this by
short circuiting when `PYTHON_FILES` is empty.
- **Description:** The types of 'destination_chains' and 'default_chain'
in 'MultiPromptChain' were changed from 'LLMChain' to 'Chain'. and
removed variables declared overlapping with the parent class
- **Issue:** When a class that inherits only Chain and not LLMChain,
such as 'SequentialChain' or 'RetrievalQA', is entered in
'destination_chains' and 'default_chain', a pydantic validation error is
raised.
- - codes
```
retrieval_chain = ConversationalRetrievalChain(
retriever=doc_retriever,
combine_docs_chain=combine_docs_chain,
question_generator=question_gen_chain,
)
destination_chains = {
'retrieval': retrieval_chain,
}
main_chain = MultiPromptChain(
router_chain=router_chain,
destination_chains=destination_chains,
default_chain=default_chain,
verbose=True,
)
```
✅ `make format`, `make lint` and `make test`
## Description
Expanded the upper bound for `networkx` dependency to allow installation
of latest stable version. Tested the included sample notebook with
version 3.1, and all steps ran successfully.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Adds support for the `$vectorSearch` operator for
MongoDBAtlasVectorSearch, which was announced at .Local London
(September 26th, 2023). This change maintains breaks compatibility
support for the existing `$search` operator used by the original
integration (https://github.com/langchain-ai/langchain/pull/5338) due to
incompatibilities in the Atlas search implementations.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
We noticed that as we have been moving developers to the new
`ElasticsearchStore` implementation, we want to keep the
ElasticVectorSearch class still available as developers transition
slowly to the new store.
To speed up this process, I updated the blurb giving them a better
recommendation of why they should use ElasticsearchStore.
Description: Add "source" metadata to OutlookMessageLoader
This pull request adds the "source" metadata to the OutlookMessageLoader
class in the load method. The "source" metadata is required when
indexing with RecordManager in order to sync the index documents with a
source.
Issue: None
Dependencies: None
Twitter handle: @ATelders
Co-authored-by: Arthur Telders <arthur.telders@roquette.com>
- **Description:** Bedrock updated boto service name to
"bedrock-runtime" for the InvokeModel and InvokeModelWithResponseStream
APIs. This update also includes new model identifiers for Titan text,
embedding and Anthropic.
Co-authored-by: Mani Kumar Adari <maniadar@amazon.com>
The key of stopping strings used in text-generation-webui api is
[`stopping_strings`](https://github.com/oobabooga/text-generation-webui/blob/main/api-examples/api-example.py#L51),
not `stop`.
<!-- 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/hwchase17/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:** Changed data type from `text` to `json` in xata for
improved performance. Also corrected the `additionalKwargs` key in the
`messages()` function to `additional_kwargs` to adhere to `BaseMessage`
requirements.
- **Issue:** The Chathisroty.messages() will return {} of
`additional_kwargs`, as the name is wrong for `additionalKwargs` .
- **Dependencies:** N/A
- **Tag maintainer:** N/A
- **Twitter handle:** N/A
My PR is passing linting and testing before submitting.
This adds `input_schema` and `output_schema` properties to all
runnables, which are Pydantic models for the input and output types
respectively. These are inferred from the structure of the Runnable as
much as possible, the only manual typing needed is
- optionally add type hints to lambdas (which get translated to
input/output schemas)
- optionally add type hint to RunnablePassthrough
These schemas can then be used to create JSON Schema descriptions of
input and output types, see the tests
- [x] Ensure no InputType and OutputType in our classes use abstract
base classes (replace with union of subclasses)
- [x] Implement in BaseChain and LLMChain
- [x] Implement in RunnableBranch
- [x] Implement in RunnableBinding, RunnableMap, RunnablePassthrough,
RunnableEach, RunnableRouter
- [x] Implement in LLM, Prompt, Chat Model, Output Parser, Retriever
- [x] Implement in RunnableLambda from function signature
- [x] Implement in Tool
<!-- 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/hwchase17/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.
-->
Adds LangServe package
* Integrate Runnables with Fast API creating Server and a RemoteRunnable
client
* Support multiple runnables for a given server
* Support sync/async/batch/abatch/stream/astream/astream_log on the
client side (using async implementations on server)
* Adds validation using annotations (relying on pydantic under the hood)
-- this still has some rough edges -- e.g., open api docs do NOT
generate correctly at the moment
* Uses pydantic v1 namespace
Known issues: type translation code doesn't handle a lot of types (e.g.,
TypedDicts)
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
The current behaviour just calls the handler without awaiting the
coroutine, which results in exceptions/warnings, and obviously doesn't
actually execute whatever the callback handler does
<!-- 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/hwchase17/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:** Prompt wrapping requirements have been implemented on
the service side of AWS Bedrock for the Anthropic Claude models to
provide parity between Anthropic's offering and Bedrock's offering. This
overnight change broke most existing implementations of Claude, Bedrock
and Langchain. This PR just steals the the Anthropic LLM implementation
to enforce alias/role wrapping and implements it in the existing
mechanism for building the request body. This has also been tested to
fix the chat_model implementation as well. Happy to answer any further
questions or make changes where necessary to get things patched and up
to PyPi ASAP, TY.
- **Issue:** No issue opened at the moment, though will update when
these roll in.
- **Dependencies:** None
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Description:
NotionDB supports a number of common property types. I have found three
common types that are not included in notiondb loader. When programs
loaded them with notiondb, which will cause some metadata information
not to be passed to langchain. Therefore, I added three common types:
- date
- created_time
- last_edit_time.
### Issue:
no
### Dependencies:
No dependencies added :)
### Tag maintainer:
@rlancemartin, @eyurtsev
### Twitter handle:
@BJTUTC
Reverts langchain-ai/langchain#8610
this is actually an oversight - this merges all dfs into one df. we DO
NOT want to do this - the idea is we work and manipulate multiple dfs
This removes the use of the intermediate df list and directly
concatenates the dataframes if path is a list of strings. The pd.concat
function combines the dataframes efficiently, making it faster and more
memory-efficient compared to appending dataframes to a list.
<!-- Thank you for contributing to LangChain!
Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
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.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
