In some cases, the OpenAI response is missing the `finish_reason`
attribute. It seems to happen when using Ada or Babbage and
`stream=true`, but I can't always reproduce it. This change just
gracefully handles the missing key.
Introduction of newest function calling feature doesn't work properly
with PromptLayerChatOpenAI model since on the `_generate` method,
functions argument are not even getting passed to the `ChatOpenAI` base
class which results in empty `ai_message.additional_kwargs`
Fixes #6365
updated `tutorials.mdx`:
- added a link to new `Deeplearning AI` course on LangChain
- added links to other tutorial videos
- fixed format
@baskaryan, @hwchase17
#### Description
refactor BedrockEmbeddings class to clean code as below:
1. inline content type and accept
2. rewrite input_body as a dictionary literal
3. no need to declare embeddings variable, so remove it
- Description: Adding to Chroma integration the option to run a
similarity search by a vector with relevance scores. Fixing two minor
typos.
- Issue: The "lambda_mult" typo is related to #4861
- Maintainer: @rlancemartin, @eyurtsev
Based on user feedback, we have improved the Alibaba Cloud OpenSearch
vector store documentation.
Co-authored-by: zhaoshengbo <shengbo.zsb@alibaba-inc.com>
<!-- 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!
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
-->
Several updates for the PowerBI tools:
- Handle 0 records returned by requesting redo with different filtering
- Handle too large results by optionally tokenizing the result and
comparing against a max (change in signature, non-breaking)
- Implemented LLMChain with Chat for chat models for the tools.
- Updates to the main prompt including tables
- Update to Tool prompt with TOPN function
- Split the tool prompt to allow the LLMChain with ChatPromptTemplate
Smaller fixes for stability.
For visibility: @hinthornw
Replace this comment with:
- Description: added documentation for a template repo that helps
dockerizing and deploying a LangChain using a Cloud Build CI/CD pipeline
to Google Cloud build serverless
- Issue: None,
- Dependencies: None,
- Tag maintainer: @baskaryan,
- Twitter handle: EdenEmarco177
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.
- Description:
- When `keep_separator` is `True` the `_split_text_with_regex()` method
in `text_splitter` uses regex to split, but when `keep_separator` is
`False` it uses `str.split()`. This causes problems when the separator
is a special regex character like `.` or `*`. This PR fixes that by
using `re.split()` in both cases.
- Issue: #7262
- Tag maintainer: @baskaryan
**Description**
In the following page, "Wikipedia" tool is explained.
https://python.langchain.com/docs/modules/agents/tools/integrations/wikipedia
However, the WikipediaAPIWrapper being used is not a tool. This PR
updated the documentation to use a tool WikipediaQueryRun.
**Issue**
None
**Tag maintainer**
Agents / Tools / Toolkits: @hinthornw
- Description: This is a chat model equivalent of HumanInputLLM. An
example notebook is also added.
- Tag maintainer: @hwchase17, @baskaryan
- Twitter handle: N/A
- Description: I have added a `show_progress_bar` parameter (defaults.to
`False`) to the `OpenAIEmbeddings`. If the user sets `show_progress_bar`
to `True`, a progress bar will be displayed.
- Issue: #7246
- Dependencies: N/A
- Tag maintainer: @hwchase17, @baskaryan
- Twitter handle: N/A
Description: `flan-t5-xl` hangs, updated to `flan-t5-xxl`. Tested all
stabilityai LLMs- all hang so removed from tutorial. Temperature > 0 to
prevent unintended determinism.
Issue: #3275
Tag maintainer: @baskaryan
Fix for bug in SitemapLoader
`aiohttp` `get` does not accept `verify` argument, and currently throws
error, so SitemapLoader is not working
This PR fixes it by removing `verify` param for `get` function call
Fixes#6107
#### Who can review?
Tag maintainers/contributors who might be interested:
@eyurtsev
---------
Co-authored-by: techcenary <127699216+techcenary@users.noreply.github.com>
Add an "eval" tag to traced evaluation runs
Most of this PR is actually
https://github.com/hwchase17/langchain/pull/7207 but I can't diff off
two separate PRs
---------
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
### Description
This pull request introduces the "Cube Semantic Layer" document loader,
which demonstrates the retrieval of Cube's data model metadata in a
format suitable for passing to LLMs as embeddings. This enhancement aims
to provide contextual information and improve the understanding of data.
Twitter handle:
@the_cube_dev
---------
Co-authored-by: rlm <pexpresss31@gmail.com>
This PR brings in a vectorstore interface for
[Marqo](https://www.marqo.ai/).
The Marqo vectorstore exposes some of Marqo's functionality in addition
the the VectorStore base class. The Marqo vectorstore also makes the
embedding parameter optional because inference for embeddings is an
inherent part of Marqo.
Docs, notebook examples and integration tests included.
Related PR:
https://github.com/hwchase17/langchain/pull/2807
---------
Co-authored-by: Tom Hamer <tom@marqo.ai>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Description:
Updating the docstrings for Milvus and Zilliz so that they appear
correctly on https://integrations.langchain.com/vectorstores. No changes
done to code.
Maintainer:
@baskaryan
Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
### Summary
Updates the docstrings for the unstructured base loaders so more useful
information appears on the integrations page. If these look good, will
add similar docstrings to the other loaders.
### Reviewers
- @rlancemartin
- @eyurtsev
- @hwchase17
- Description: Allow `InMemoryDocstore` to be created without passing a
dict to the constructor; the constructor can create a dict at runtime if
one isn't provided.
- Tag maintainer: @dev2049
- Description: At the moment, inserting new embeddings to pgvector is
querying all embeddings every time as the defined `embeddings`
relationship is using the default params, which sets `lazy="select"`.
This change drastically improves the performance and adds a few
additional cleanups:
* remove `collection.embeddings.append` as it was querying all
embeddings on insert, replace with `collection_id` param
* centralize storing logic in add_embeddings function to reduce
duplication
* remove boilerplate
- Issue: No issue was opened.
- Dependencies: None.
- Tag maintainer: this is a vectorstore update, so I think
@rlancemartin, @eyurtsev
- Twitter handle: @falmannaa
Hi, there
This pull request contains two commit:
**1. Implement delete interface with optional ids parameter on
AnalyticDB.**
**2. Allow customization of database connection behavior by exposing
engine_args parameter in interfaces.**
- This commit adds the `engine_args` parameter to the interfaces,
allowing users to customize the behavior of the database connection. The
`engine_args` parameter accepts a dictionary of additional arguments
that will be passed to the create_engine function. Users can now modify
various aspects of the database connection, such as connection pool size
and recycle time. This enhancement provides more flexibility and control
to users when interacting with the database through the exposed
interfaces.
This commit is related to VectorStores @rlancemartin @eyurtsev
Thank you for your attention and consideration.
