- Description: Bug Fix - Added a step variable to keep track of prompts
- Issue: Bug from internal Arize testing - The prompts and responses
that are ingested were not mapped correctly
- Dependencies: N/A
fix the Chinese characters in the solution content will be converted to
ascii encoding, resulting in an abnormally long number of tokens
Co-authored-by: qixin <qixin@fintec.ai>
allows for where filtering on collection via get
- Description: aligns langchain chroma vectorstore get with underlying
[chromadb collection
get](https://github.com/chroma-core/chroma/blob/main/chromadb/api/models/Collection.py#L103)
allowing for where filtering, etc.
- Issue: NA
- Dependencies: none
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @pappanaka
#### Background
With the development of [structured
tools](https://blog.langchain.dev/structured-tools/), the LangChain team
expanded the platform's functionality to meet the needs of new
applications. The GMail tool, empowered by structured tools, now
supports multiple arguments and powerful search capabilities,
demonstrating LangChain's ability to interact with dynamic data sources
like email servers.
#### Challenge
The current GMail tool only supports GMail, while users often utilize
other email services like Outlook in Office365. Additionally, the
proposed calendar tool in PR
https://github.com/hwchase17/langchain/pull/652 only works with Google
Calendar, not Outlook.
#### Changes
This PR implements an Office365 integration for LangChain, enabling
seamless email and calendar functionality with a single authentication
process.
#### Future Work
With the core Office365 integration complete, future work could include
integrating other Office365 tools such as Tasks and Address Book.
#### Who can review?
@hwchase17 or @vowelparrot can review this PR
#### Appendix
@janscas, I utilized your [O365](https://github.com/O365/python-o365)
library extensively. Given the rising popularity of LangChain and
similar AI frameworks, the convergence of libraries like O365 and tools
like this one is likely. So, I wanted to keep you updated on our
progress.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
When the tool requires no input, the LLM often gives something like
this:
```json
{
"action": "just_do_it"
}
```
I have attempted to enhance the prompt, but it doesn't appear to be
functioning effectively. Therefore, I believe we should consider easing
the check a little bit.
Signed-off-by: Xiaochao Dong (@damnever) <the.xcdong@gmail.com>
Adding Confluence to Jira tool. Can create a page in Confluence with
this PR. If accepted, will extend functionality to Bitbucket and
additional Confluence features.
---------
Co-authored-by: Ethan Bowen <ethan.bowen@slalom.com>
Since this model name is not there in the list MODEL_COST_PER_1K_TOKENS,
when we use get_openai_callback(), for gpt 3.5 model in Azure AI, we do
not get the cost of the tokens. This will fix this issue
#### Who can review?
@hwchase17
@agola11
Co-authored-by: rajib76 <rajib76@yahoo.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
- Fixed an issue where some caching types check the wrong types, hence
not allowing caching to work
Maintainer responsibilities:
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
MHTML is a very interesting format since it's used both for emails but
also for archived webpages. Some scraping projects want to store pages
in disk to process them later, mhtml is perfect for that use case.
This is heavily inspired from the beautifulsoup html loader, but
extracting the html part from the mhtml file.
---------
Co-authored-by: rlm <pexpresss31@gmail.com>
# beautifulsoup get_text kwargs in WebBaseLoader
- Description: this PR introduces an optional `bs_get_text_kwargs`
parameter to `WebBaseLoader` constructor. It can be used to pass kwargs
to the downstream BeautifulSoup.get_text call. The most common usage
might be to pass a custom text separator, as seen also in
`BSHTMLLoader`.
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: jtolgyesi
- Description: Adds a simple progress bar with tqdm when using
UnstructuredURLLoader. Exposes new paramater `show_progress_bar`. Very
simple PR.
- Issue: N/A
- Dependencies: N/A
- Tag maintainer: @rlancemartin @eyurtsev
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
- Description: Updated regex to support a new format that was observed
when whatsapp chat was exported.
- Issue: #6654
- Dependencies: No new dependencies
- Tag maintainer: @rlancemartin, @eyurtsev
<!-- 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: @dev2049
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @dev2049
- Memory: @hwchase17
- Agents / Tools / Toolkits: @vowelparrot
- 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
-->
- Description: Fix Typo in LangChain MyScale Integration Doc
@hwchase17
# Add caching to BaseChatModel
Fixes#1644
(Sidenote: While testing, I noticed we have multiple implementations of
Fake LLMs, used for testing. I consolidated them.)
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
Models
- @hwchase17
- @agola11
Twitter: [@UmerHAdil](https://twitter.com/@UmerHAdil) | Discord:
RicChilligerDude#7589
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Motorhead Memory module didn't support deletion of a session. Added a
method to enable deletion.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
This PR adds a new LLM class for the Amazon API Gateway hosted LLM. The
PR also includes example notebooks for using the LLM class in an Agent
chain.
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
### Just corrected a small inconsistency on a doc page (not exactly a
typo, per se)
- Description: There was inconsistency due to the use of single quotes
at one place on the [Squential
Chains](https://python.langchain.com/docs/modules/chains/foundational/sequential_chains)
page of the docs,
- Issue: NA,
- Dependencies: NA,
- Tag maintainer: @dev2049,
- Twitter handle: kambleakash0
This PR targets the `API Reference` documentation.
- Several classes and functions missed `docstrings`. These docstrings
were created.
- In several places this
```
except ImportError:
raise ValueError(
```
was replaced to
```
except ImportError:
raise ImportError(
```
# Description
It adds a new initialization param in `WikipediaLoader` so we can
override the `doc_content_chars_max` param used in `WikipediaAPIWrapper`
under the hood, e.g:
```python
from langchain.document_loaders import WikipediaLoader
# doc_content_chars_max is the new init param
loader = WikipediaLoader(query="python", doc_content_chars_max=90000)
```
## Decisions
`doc_content_chars_max` default value will be 4000, because it's the
current value
I have added pycode comments
# Issue
#6639
# Dependencies
None
# Twitter handle
[@elafo](https://twitter.com/elafo)
