# Astra DB Vector store integration
- **Description:** This PR adds a `VectorStore` implementation for
DataStax Astra DB using its HTTP API
- **Issue:** (no related issue)
- **Dependencies:** A new required dependency is `astrapy` (`>=0.5.3`)
which was added to pyptoject.toml, optional, as per guidelines
- **Tag maintainer:** I recently mentioned to @baskaryan this
integration was coming
- **Twitter handle:** `@rsprrs` if you want to mention me
This PR introduces the `AstraDB` vector store class, extensive
integration test coverage, a reworking of the documentation which
conflates Cassandra and Astra DB on a single "provider" page and a new,
completely reworked vector-store example notebook (common to the
Cassandra store, since parts of the flow is shared by the two APIs). I
also took care in ensuring docs (and redirects therein) are behaving
correctly.
All style, linting, typechecks and tests pass as far as the `AstraDB`
integration is concerned.
I could build the documentation and check it all right (but ran into
trouble with the `api_docs_build` makefile target which I could not
verify: `Error: Unable to import module
'plan_and_execute.agent_executor' with error: No module named
'langchain_experimental'` was the first of many similar errors)
Thank you for a review!
Stefano
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Cohere released the new embedding API (Embed v3:
https://txt.cohere.com/introducing-embed-v3/) that treats document and
query embeddings differently. This PR updated the `CohereEmbeddings` to
use them appropriately. It also works with the old models.
Description: This PR masks API key secrets for the Nebula model from
Symbl.ai
Issue: #12165
Maintainer: @eyurtsev
---------
Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>
* ChatAnyscale was missing coercion to SecretStr for anyscale api key
* The model inherits from ChatOpenAI so it should not force the openai
api key to be secret str until openai model has the same changes
https://github.com/langchain-ai/langchain/issues/12841
Qdrant was incorrectly calculating the cosine similarity and returning
`0.0` for the best match, instead of `1.0`. Internally Qdrant returns a
cosine score from `-1.0` (worst match) to `1.0` (best match), and the
current formula reflects it.
Possibility to pass on_artifacts to a conversation. It can be then
achieved by adding this way:
```python
result = agent.run(
input=message.text,
metadata={
"on_artifact": CALLBACK_FUNCTION
},
)
```
Calls uvicorn directly from cli:
Reload works if you define app by import string instead of object.
(was doing subprocess in order to get reloading)
Version bump to 0.0.14
Remove the need for [serve] for simplicity.
Readmes are updated in #12847 to avoid cluttering this PR
Previously we treated trace_on_chain_group as a command to always start
tracing. This is unintuitive (makes the function do 2 things), and makes
it harder to toggle tracing
When you use a MultiQuery it might be useful to use the original query
as well as the newly generated ones to maximise the changes to retriever
the correct document. I haven't created an issue, it seems a very small
and easy thing.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Correct number of elements in config list in
`batch()` and `abatch()` of `BaseLLM` in case `max_concurrency` is not
None.
- **Issue:** #12643
- **Twitter handle:** @akionux
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Zep now has the ability to search over chat history summaries. This PR
adds support for doing so. More here: https://blog.getzep.com/zep-v0-17/
@baskaryan @eyurtsev
…s present
<!-- 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.
-->
### Enabling `device_map` in HuggingFacePipeline
For multi-gpu settings with large models, the
[accelerate](https://huggingface.co/docs/accelerate/usage_guides/big_modeling#using--accelerate)
library provides the `device_map` parameter to automatically distribute
the model across GPUs / disk.
The [Transformers
pipeline](3520e37e86/src/transformers/pipelines/__init__.py (L543))
enables users to specify `device` (or) `device_map`, and handles cases
(with warnings) when both are specified.
However, Langchain's HuggingFacePipeline only supports specifying
`device` when calling transformers which limits large models and
multi-gpu use-cases.
Additionally, the [default
value](8bd3ce59cd/libs/langchain/langchain/llms/huggingface_pipeline.py (L72))
of `device` is initialized to `-1` , which is incompatible with the
transformers pipeline when `device_map` is specified.
This PR addresses the addition of `device_map` as a parameter , and
solves the incompatibility of `device = -1` when `device_map` is also
specified.
An additional test has been added for this feature.
Additionally, some existing tests no longer work since
1. `max_new_tokens` has to be specified under `pipeline_kwargs` and not
`model_kwargs`
2. The GPT2 tokenizer raises a `ValueError: Pipeline with tokenizer
without pad_token cannot do batching`, since the `tokenizer.pad_token`
is `None` ([related
issue](https://github.com/huggingface/transformers/issues/19853) on the
transformers repo).
This PR handles fixing these tests as well.
Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>
[The python
spec](https://docs.python.org/3/reference/datamodel.html#object.__getattr__)
requires that `__getattr__` throw `AttributeError` for missing
attributes but there are several places throwing `ImportError` in the
current code base. This causes a specific problem with `hasattr` since
it calls `__getattr__` then looks only for `AttributeError` exceptions.
At present, calling `hasattr` on any of these modules will raise an
unexpected exception that most code will not handle as `hasattr`
throwing exceptions is not expected.
In our case this is triggered by an exception tracker (Airbrake) that
attempts to collect the version of all installed modules with code that
looks like: `if hasattr(mod, "__version__"):`. With `HEAD` this is
causing our exception tracker to fail on all exceptions.
I only changed instances of unknown attributes raising `ImportError` and
left instances of known attributes raising `ImportError`. It feels a
little weird but doesn't seem to break anything.
- **Description:** Use all Google search results data in SerpApi.com
wrapper instead of the first one only
- **Tag maintainer:** @hwchase17
_P.S. `libs/langchain/tests/integration_tests/utilities/test_serpapi.py`
are not executed during the `make test`._
