This bugfix PR adds kwargs support to Baseten model invocations so that
e.g. the following script works properly:
```python
chatgpt_chain = LLMChain(
llm=Baseten(model="MODEL_ID"),
prompt=prompt,
verbose=False,
memory=ConversationBufferWindowMemory(k=2),
llm_kwargs={"max_length": 4096}
)
```
Unexpectedly changed at
6792a3557d
<!-- 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
-->
I guess `allowed_search_types` is unexpectedly changed in
6792a3557d,
so that we cannot specify `similarity_score_threshold` here.
```python
class VectorStoreRetriever(BaseRetriever):
...
allowed_search_types: ClassVar[Collection[str]] = (
"similarity",
"similarityatscore_threshold",
"mmr",
)
@root_validator()
def validate_search_type(cls, values: Dict) -> Dict:
"""Validate search type."""
search_type = values["search_type"]
if search_type not in cls.allowed_search_types:
raise ValueError(...)
if search_type == "similarity_score_threshold":
... # UNREACHABLE CODE
```
VectorStores Maintainers: @rlancemartin @eyurtsev
- Description: Get SQL Cmd directly generated by SQL-Database Chain
without executing it in the DB engine.
- Issue: #4853
- Tag maintainer: @hinthornw,@baskaryan
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
New HTML loader that asynchronously loader a list of urls.
New transformer using [HTML2Text](https://github.com/Alir3z4/html2text/)
for HTML to clean, easy-to-read plain ASCII text (valid Markdown).
In certain 0-shot scenarios, the existing stateful language model can
unintentionally send/accumulate the .history.
This commit adds the "with_history" option to chatglm, allowing users to
control the behavior of .history and prevent unintended accumulation.
Possible reviewers @hwchase17 @baskaryan @mlot
Refer to discussion over this thread:
https://twitter.com/wey_gu/status/1681996149543276545?s=20
The `sql_database.py` is unnecessarily placed in the root code folder.
A similar code is usually placed in the `utilities/`.
As a byproduct of this placement, the sql_database is [placed on the top
level of classes in the API
Reference](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.sql_database)
which is confusing and not correct.
- moved the `sql_database.py` from the root code folder to the
`utilities/`
@baskaryan
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Fixed the bug causing: `TypeError: generate() got multiple values for
keyword argument 'stop_sequences'`
```python
res = await self.async_client.generate(
prompt,
**self._default_params,
stop_sequences=stop,
**kwargs,
)
```
The above throws an error because stop_sequences is in also in the
self._default_params.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
I've extended the support of async API to local Qdrant mode. It is faked
but allows prototyping without spinning a container. The tests are
improved to test the in-memory case as well.
@baskaryan @rlancemartin @eyurtsev @agola11
Redis cache currently stores model outputs as strings. Chat generations
have Messages which contain more information than just a string. Until
Redis cache supports fully storing messages, cache should not interact
with chat generations.
Streaming support is useful if you are doing long-running completions or
need interactivity e.g. for chat... adding it to replicate, using a
similar pattern to other LLMs that support streaming.
Housekeeping: I ran `make format` and `make lint`, no issues reported in
the files I touched.
I did update the replicate integration test but ran into some issues,
specifically:
1. The original test was failing for me due to the model argument not
being specified... perhaps this test is not regularly run? I fixed it by
adding a call to the lightweight hello world model which should not be
burdensome for replicate infra.
2. I couldn't get the `make integration_tests` command to pass... a lot
of failures in other integration tests due to missing dependencies...
however I did make sure the particluar test file I updated does pass, by
running `poetry run pytest
tests/integration_tests/llms/test_replicate.py`
Finally, I am @tjaffri https://twitter.com/tjaffri for feature
announcement tweets... or if you could please tag @docugami
https://twitter.com/docugami we would really appreciate that :-)
Tagging model maintainers @hwchase17 @baskaryan
Thank for all the awesome work you folks are doing.
---------
Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
## Description
This PR adds a graph class and an openCypher QA chain to work with the
Amazon Neptune database.
## Dependencies
`requests` which is included in the LangChain dependencies.
## Maintainers for Review
@krlawrence
@baskaryan
### Twitter handle
pjain7
`math_utils.py` is in the root code folder. This creates the
`langchain.math_utils: Math Utils` group on the API Reference navigation
ToC, on the same level with `Chains` and `Agents` which is not correct.
Refactoring:
- created the `utils/` folder
- moved `math_utils.py` to `utils/math.py`
- moved `utils.py` to `utils/utils.py`
- split `utils.py` into `utils.py, env.py, strings.py`
- added module description
@baskaryan
- Description: fix to avoid rdflib warnings when concatenating URIs and
strings to create the text snippet for the knowledge graph's schema.
@marioscrock pointed this out in a comment related to #7165
- Issue: None, but the problem was mentioned as a comment in #7165
- Dependencies: None
- Tag maintainer: Related to memory -> @hwchase17, maybe @baskaryan as
it is a fix
Integrating Portkey, which adds production features like caching,
tracing, tagging, retries, etc. to langchain apps.
- Dependencies: None
- Twitter handle: https://twitter.com/portkeyai
- test_portkey.py added for tests
- example notebook added in new utilities folder in modules
Also fixed a bug with OpenAIEmbeddings where headers weren't passing.
cc @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
