This PR adds support for the Azure Cosmos DB MongoDB vCore Vector Store
https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/vector-search
Summary:
- **Description:** added vector store integration for Azure Cosmos DB
MongoDB vCore Vector Store,
- **Issue:** the issue # it fixes#11627,
- **Dependencies:** pymongo dependency,
- **Tag maintainer:** @hwchase17,
- **Twitter handle:** @izzyacademy
---------
Co-authored-by: Israel Ekpo <israel.ekpo@gmail.com>
Co-authored-by: Israel Ekpo <44282278+izzyacademy@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
* Should use non chunked messages for Invoke/Batch
* After this PR, stream output type is not represented, do we want to
use the union?
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Adds standard `type` field for all messages that will be
serialized/validated by pydantic.
* The presence of `type` makes it easier for developers consuming
schemas to write client code to serialize/deserialize.
* In LangServe `type` will be used for both validation and will appear
in the generated openapi specs
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.
-->
There is some invalid link in open ai platform
[docs](https://python.langchain.com/docs/integrations/platforms/openai).
So i fixed it to valid links.
- `/docs/integrations/chat_models/openai` ->
`/docs/integrations/chat/openai`
- `/docs/integrations/chat_models/azure_openai` ->
`/docs/integrations/chat/azure_chat_openai`
Thanks! ☺️
- **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.
**Description**
This PR adds an additional Example to the Redis integration
documentation. [The
example](https://learn.microsoft.com/azure/azure-cache-for-redis/cache-tutorial-vector-similarity)
is a step-by-step walkthrough of using Azure Cache for Redis and Azure
OpenAI for vector similarity search, using LangChain extensively
throughout.
**Issue**
Nothing specific, just adding an additional example.
**Dependencies**
None.
**Tag Maintainer**
Tagging @hwchase17 :)
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 🙂
