Very simple change in relation to the issue
https://github.com/langchain-ai/langchain/issues/14550
@baskaryan, @eyurtsev, @hwchase17.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Added logic for re-calling the YandexGPT API in case of
an error
---------
Co-authored-by: Dmitry Tyumentsev <dmitry.tyumentsev@raftds.com>
Description: A new vector store Jaguar is being added. Class, test
scripts, and documentation is added.
Issue: None -- This is the first PR contributing to LangChain
Dependencies: This depends on "pip install -U jaguardb-http-client"
client http package
Tag maintainer: @baskaryan, @eyurtsev, @hwchase1
Twitter handle: @workbot
---------
Co-authored-by: JY <jyjy@jaguardb>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Addded missed docstrings. Fixed inconsistency in docstrings.
**Note** CC @efriis
There were PR errors on
`langchain_experimental/prompt_injection_identifier/hugging_face_identifier.py`
But, I didn't touch this file in this PR! Can it be some cache problems?
I fixed this error.
- **Description:** added support for chat_history for Google
GenerativeAI (to actually use the `chat` API) plus since Gemini
currently doesn't have a support for SystemMessage, added support for it
only if a user provides additional `convert_system_message_to_human`
flag during model initialization (in this case, SystemMessage would be
prepanded to the first HumanMessage)
- **Issue:** #14710
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** lkuligin
---------
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
- **Description:** This is addition to [my previous
PR](https://github.com/langchain-ai/langchain/pull/13930) with
improvements to flexibility allowing different models and notebook to
use ONNX runtime for faster speed. Since the last PR, [our
model](https://huggingface.co/laiyer/deberta-v3-base-prompt-injection)
got more than 660k downloads, and with the [public
benchmark](https://huggingface.co/spaces/laiyer/prompt-injection-benchmark)
showed much fewer false-positives than the previous one from deepset.
Additionally, on the ONNX runtime, it can be running 3x faster on the
CPU, which might be handy for builders using Langchain.
**Issue:** N/A
- **Dependencies:** N/A
- **Tag maintainer:** N/A
- **Twitter handle:** `@laiyer_ai`
Fixing issue - https://github.com/langchain-ai/langchain/issues/14494 to
avoid Kendra query ValidationException
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** Update kendra.py to avoid Kendra query
ValidationException,
- **Issue:** the issue
#https://github.com/langchain-ai/langchain/issues/14494,
- **Dependencies:** None,
- **Tag maintainer:** ,
- **Twitter handle:**
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:**
- Add a break case to `text_splitter.py::split_text_on_tokens()` to
avoid unwanted item at the end of result.
- Add a testcase to enforce the behavior.
- **Issue:**
- #14649
- #5897
- **Dependencies:** n/a,
---
**Quick illustration of change:**
```
text = "foo bar baz 123"
tokenizer = Tokenizer(
chunk_overlap=3,
tokens_per_chunk=7
)
output = split_text_on_tokens(text=text, tokenizer=tokenizer)
```
output before change: `["foo bar", "bar baz", "baz 123", "123"]`
output after change: `["foo bar", "bar baz", "baz 123"]`
This is technically a breaking change because it'll switch out default
models from `text-davinci-003` to `gpt-3.5-turbo-instruct`, but OpenAI
is shutting off those endpoints on 1/4 anyways.
Feels less disruptive to switch out the default instead.
Gpt-3.5 sometimes calls with empty string arguments instead of `{}`
I'd assume it's because the typescript representation on their backend
makes it a bit ambiguous.
- **Description:** VertexAIEmbeddings performance improvements
- **Twitter handle:** @vladkol
## Improvements
- Dynamic batch size, starting from 250, lowering down to 5. Batch size
varies across regions.
Some regions support larger batches, and it significantly improves
performance.
When running large batches of texts in `us-central1`, performance gain
can be up to 3.5x.
The dynamic batching also makes sure every batch is below 20K token
limit.
- New model parameter `embeddings_type` that translates to `task_type`
parameter of the API. Newer model versions support [different embeddings
task
types](https://cloud.google.com/vertex-ai/docs/generative-ai/embeddings/get-text-embeddings#api_changes_to_models_released_on_or_after_august_2023).
Now that it's supported again for OAI chat models .
Shame this wouldn't include it in the `.invoke()` output though (it's
not included in the message itself). Would need to do a follow-up for
that to be the case
Fixed:
- `_agenerate` return value in the YandexGPT Chat Model
- duplicate line in the documentation
Co-authored-by: Dmitry Tyumentsev <dmitry.tyumentsev@raftds.com>
Builds out a developer documentation section in the docs
- Links it from contributing.md
- Adds an initial guide on how to contribute an integration
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Adds the option for `similarity_score_threshold` when using
`MongoDBAtlasVectorSearch` as a vector store retriever.
Example use:
```
vector_search = MongoDBAtlasVectorSearch.from_documents(...)
qa_retriever = vector_search.as_retriever(
search_type="similarity_score_threshold",
search_kwargs={
"score_threshold": 0.5,
}
)
qa = RetrievalQA.from_chain_type(
llm=OpenAI(),
chain_type="stuff",
retriever=qa_retriever,
)
docs = qa({"query": "..."})
```
I've tested this feature locally, using a MongoDB Atlas Cluster with a
vector search index.
… (#14723)
- **Description:** Minor updates per marketing requests. Namely, name
decisions (AI Foundation Models / AI Playground)
- **Tag maintainer:** @hinthornw
Do want to pass around the PR for a bit and ask a few more marketing
questions before merge, but just want to make sure I'm not working in a
vacuum. No major changes to code functionality intended; the PR should
be for documentation and only minor tweaks.
Note: QA model is a bit borked across staging/prod right now. Relevant
teams have been informed and are looking into it, and I'm placeholdered
the response to that of a working version in the notebook.
Co-authored-by: Vadim Kudlay <32310964+VKudlay@users.noreply.github.com>
Replace this entire comment with:
- **Description:** added support for new Google GenerativeAI models
- **Twitter handle:** lkuligin
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Description: Added NVIDIA AI Playground Initial support for a selection of models (Llama models, Mistral, etc.)
Dependencies: These models do depend on the AI Playground services in NVIDIA NGC. API keys with a significant amount of trial compute are available (10K queries as of the time of writing).
H/t to @VKudlay
<!-- 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.
-->
Co-authored-by: fangkeke <3339698829@qq.com>
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.
-->
Add a new ChatGoogleGenerativeAI class in a `langchain-google-genai`
package.
Still todo: add a deprecation warning in PALM
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Leonid Kuligin <lkuligin@yandex.ru>
Co-authored-by: Bagatur <baskaryan@gmail.com>
h/t to @lkuligin
- **Description:** added new models on VertexAI
- **Twitter handle:** @lkuligin
---------
Co-authored-by: Leonid Kuligin <lkuligin@yandex.ru>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This PR adds an example notebook for the Databricks Vector Search vector
store. It also adds an introduction to the Databricks Vector Search
product on the Databricks's provider page.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
When using local Chatglm2-6B by changing OPENAI_BASE_URL to localhost,
the token_usage in ChatOpenAI becomes None. This leads to an
AttributeError when trying to access token_usage.items().
This commit adds a check to ensure token_usage is not None before
accessing its items. This change prevents the AttributeError and allows
ChatOpenAI to work seamlessly with a local Chatglm2-6B model, aligning
with the way it operates with the OpenAI API.
<!-- 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.
-->
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
**Description:** This PR fixes `HuggingFaceHubEmbeddings` by making the
API token optional (as in the client beneath). Most models don't require
one. I also updated the notebook for TEI (text-embeddings-inference)
accordingly as requested here #14288. In addition, I fixed a mistake in
the POST call parameters.
**Tag maintainers:** @baskaryan
## Description
New YAML output parser as a drop-in replacement for the Pydantic output
parser. Yaml is a much more token-efficient format than JSON, proving to
be **~35% faster and using the same percentage fewer completion
tokens**.
☑️ Formatted
☑️ Linted
☑️ Tested (analogous to the existing`test_pydantic_parser.py`)
The YAML parser excels in situations where a list of objects is
required, where the root object needs no key:
```python
class Products(BaseModel):
__root__: list[Product]
```
I ran the prompt `Generate 10 healthy, organic products` 10 times on one
chain using the `PydanticOutputParser`, the other one using
the`YamlOutputParser` with `Products` (see below) being the targeted
model to be created.
LLMs used were Fireworks' `lama-v2-34b-code-instruct` and OpenAI
`gpt-3.5-turbo`. All runs succeeded without validation errors.
```python
class Nutrition(BaseModel):
sugar: int = Field(description="Sugar in grams")
fat: float = Field(description="% of daily fat intake")
class Product(BaseModel):
name: str = Field(description="Product name")
stats: Nutrition
class Products(BaseModel):
"""A list of products"""
products: list[Product] # Used `__root__` for the yaml chain
```
Stats after 10 runs reach were as follows:
### JSON
ø time: 7.75s
ø tokens: 380.8
### YAML
ø time: 5.12s
ø tokens: 242.2
Looking forward to feedback, tips and contributions!
- **Description:** There is a bug in RedisNum filter that filter towards
value 0 will be parsed as "*". This is a fix to it.
- **Issue:** NA
- **Dependencies:** NA
- **Tag maintainer:** NA
- **Twitter handle:** NA
This PR updates RunnableWithMessage history to support user specific
configuration for the factory.
It extends support to passing multiple named arguments into the factory
if the factory takes more than a single argument.
TIL `**` globstar doesn't work in make
Makefile changes fix that.
`__getattr__` changes allow import of all files, but raise error when
accessing anything from the module.
file deletions were corresponding libs change from #14559
<!-- 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**
The `SmartLLMChain` was was fixed to output key "resolution".
Unfortunately, this prevents the ability to use multiple `SmartLLMChain`
in a `SequentialChain` because of colliding output keys. This change
simply gives the option the customize the output key to allow for
sequential chaining. The default behavior is the same as the current
behavior.
Now, it's possible to do the following:
```
from langchain.chat_models import ChatOpenAI
from langchain.prompts import PromptTemplate
from langchain_experimental.smart_llm import SmartLLMChain
from langchain.chains import SequentialChain
joke_prompt = PromptTemplate(
input_variables=["content"],
template="Tell me a joke about {content}.",
)
review_prompt = PromptTemplate(
input_variables=["scale", "joke"],
template="Rate the following joke from 1 to {scale}: {joke}"
)
llm = ChatOpenAI(temperature=0.9, model_name="gpt-4-32k")
joke_chain = SmartLLMChain(llm=llm, prompt=joke_prompt, output_key="joke")
review_chain = SmartLLMChain(llm=llm, prompt=review_prompt, output_key="review")
chain = SequentialChain(
chains=[joke_chain, review_chain],
input_variables=["content", "scale"],
output_variables=["review"],
verbose=True
)
response = chain.run({"content": "chickens", "scale": "10"})
print(response)
```
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
