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>
- Description: this change will add the google place ID of the found
location to the response of the GooglePlacesTool
- Issue: Not applicable
- Dependencies: no dependencies
- Tag maintainer: @hinthornw
- Twitter handle: Not applicable
<!-- 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: Jiří Moravčík <jiri.moravcik@gmail.com>
Co-authored-by: Jan Čurn <jan.curn@gmail.com>
- Description: Added the ability to define the open AI model.
- Issue: Currently the Doctran instance uses gpt-4 by default, this does
not work if the user has no access to gpt -4.
- rlancemartin, @eyurtsev, @baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
BedrockEmbeddings does not have endpoint_url so that switching to custom
endpoint is not possible. I have access to Bedrock custom endpoint and
cannot use BedrockEmbeddings
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Added a parameter in VectorStoreRetrieverMemory which
filters the input given by the key when constructing the buffering the
document for Vector. This feature is helpful if you have certain inputs
apart from the VectorMemory's own memory_key that needs to be ignored
e.g when using combined memory, we might need to filter the memory_key
of the other memory, Please see the issue.
- Issue: #7695
- Tag maintainer: @rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Golden Query is a wrapper on top of the [Golden Query
API](https://docs.golden.com/reference/query-api) which enables
programmatic access to query results on entities across Golden's
Knowledge Base. For more information about Golden API, please see the
[Golden API Getting
Started](https://docs.golden.com/reference/getting-started) page.
**Issue:** None
**Dependencies:** requests(already present in project)
**Tag maintainer:** @hinthornw
Signed-off-by: Constantin Musca <constantin.musca@gmail.com>
- Description: Adding code to set pandas dataframe to display all the
columns. Otherwise, some data get truncated (it puts a "..." in the
middle and just shows the first 4 and last 4 columns) and the LLM
doesn't realize it isn't getting the full data. Default value is 8, so
this helps Dataframes larger than that.
- Issue: none
- Dependencies: none
- Tag maintainer: @hinthornw
- Twitter handle: none
