Implements
[#12115](https://github.com/langchain-ai/langchain/issues/12115)
Who can review?
@baskaryan , @eyurtsev , @hwchase17
Integrated Stack Exchange API into Langchain, enabling access to diverse
communities within the platform. This addition enhances Langchain's
capabilities by allowing users to query Stack Exchange for specialized
information and engage in discussions. The integration provides seamless
interaction with Stack Exchange content, offering content from varied
knowledge repositories.
A notebook example and test cases were included to demonstrate the
functionality and reliability of this integration.
- Add StackExchange as a tool.
- Add unit test for the StackExchange wrapper and tool.
- Add documentation for the StackExchange wrapper and tool.
If you have time, could you please review the code and provide any
feedback as necessary! My team is welcome to any suggestions.
---------
Co-authored-by: Yuval Kamani <yuvalkamani@gmail.com>
Co-authored-by: Aryan Thakur <aryanthakur@Aryans-MacBook-Pro.local>
Co-authored-by: Manas1818 <79381912+manas1818@users.noreply.github.com>
Co-authored-by: aryan-thakur <61063777+aryan-thakur@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
<!-- 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.
-->
Small fix to _summarization_ example, `reduce_template` should use
`{docs}` variable.
Bug likely introduced as following code suggests using
`hub.pull("rlm/map-prompt")` instead of defined prompt.
### Description:
Hey 👋🏽 this is a small docs example fix. Hoping it helps future developers who are working with Langchain.
### Problem:
Take a look at the original example code. You were not able to get the `dialogue_turn[0]` while it was a tuple.
Original code:
```python
def _format_chat_history(chat_history: List[Tuple]) -> str:
buffer = ""
for dialogue_turn in chat_history:
human = "Human: " + dialogue_turn[0]
ai = "Assistant: " + dialogue_turn[1]
buffer += "\n" + "\n".join([human, ai])
return buffer
```
In the original code you were getting this error:
```bash
human = "Human: " + dialogue_turn[0].content
~~~~~~~~~~~~~^^^
TypeError: 'HumanMessage' object is not subscriptable
```
### Solution:
The fix is to just for loop over the chat history and look to see if its a human or ai message and add it to the buffer.
The `integrations/vectorstores/matchingengine.ipynb` example has the
"Google Vertex AI Vector Search" title. This place this Title in the
wrong order in the ToC (it is sorted by the file name).
- Renamed `integrations/vectorstores/matchingengine.ipynb` into
`integrations/vectorstores/google_vertex_ai_vector_search.ipynb`.
- Updated a correspondent comment in docstring
- Rerouted old URL to a new URL
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Addressed this issue with the top menu: It allocates too much space. If the screen is small, then the top menu items are split into two lines and look unreadable.
Another issue is with several top menu items: "Chat our docs" and "Also by LangChain". They are compound of several words which also hurts readability. The top menu items should be 1-word size.
Updates:
- "Chat our docs" -> "Chat" (the meaning is clean after clicking/opening the item)
- "Also by LangChain" -> "🦜️🔗"
- "🦜️🔗" moved before "Chat" item. This new item is partially copied from the first left item, the "🦜️🔗 LangChain". This design (with two 🦜️🔗 elements, visually splits the top menu into two parts. The first item in each part holds the 🦜️🔗 symbols and, when we click the second 🦜️🔗 item, it opens the drop-down menu. So, we've got two visually similar parts, which visually split the top menu on the right side: the LangChain Docs (and Doc-related items) and the lift side: other LangChain.ai (company) products/docs.
There are the following main changes in this PR:
1. Rewrite of the DocugamiLoader to not do any XML parsing of the DGML
format internally, and instead use the `dgml-utils` library we are
separately working on. This is a very lightweight dependency.
2. Added MMR search type as an option to multi-vector retriever, similar
to other retrievers. MMR is especially useful when using Docugami for
RAG since we deal with large sets of documents within which a few might
be duplicates and straight similarity based search doesn't give great
results in many cases.
We are @docugami on twitter, and I am @tjaffri
---------
Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
- **Description:** Adds a retriever implementation for [Knowledge Bases
for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/), a
new service announced at AWS re:Invent, shortly before this PR was
opened. This depends on the `bedrock-agent-runtime` service, which will
be included in a future version of `boto3` and of `botocore`. We will
open a follow-up PR documenting the minimum required versions of `boto3`
and `botocore` after that information is available.
- **Issue:** N/A
- **Dependencies:** `boto3>=1.33.2, botocore>=1.33.2`
- **Tag maintainer:** @baskaryan
- **Twitter handles:** `@pjain7` `@dead_letter_q`
This PR includes a documentation notebook under
`docs/docs/integrations/retrievers`, which I (@dlqqq) have verified
independently.
EDIT: `bedrock-agent-runtime` service is now included in
`boto3>=1.33.2`:
5cf793f493
---------
Co-authored-by: Piyush Jain <piyushjain@duck.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** dead link replacement
- **Issue:** no open issue
**Note:**
Hi langchain team,
Sorry to open a PR for this concern but we realized that one of the
links present in the documentation booklet was broken 😄
- **Description:** Reduce image asset file size used in documentation by
running them via lossless image optimization
([tinypng](https://www.npmjs.com/package/tinypng-cli) was used in this
case). Images wider than 1916px (the maximum width of an image displayed
in documentation) where downsized.
- **Issue:** No issue is created for this, but the large image file
assets caused slow documentation load times
- **Dependencies:** No dependencies affected
- **Description:** Existing model used for Prompt Injection is quite
outdated but we fine-tuned and open-source a new model based on the same
model deberta-v3-base from Microsoft -
[laiyer/deberta-v3-base-prompt-injection](https://huggingface.co/laiyer/deberta-v3-base-prompt-injection).
It supports more up-to-date injections and less prone to
false-positives.
- **Dependencies:** No
- **Tag maintainer:** -
- **Twitter handle:** @alex_yaremchuk
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Current docs for adapters are in the `Guides/Adapters which is not a
good place.
- moved Adapters into `Integratons/Components/Adapters/
- simplified the OpenAI adapter notebook
- rerouted the old OpenAI adapter page URL to a new one.
**Description:**
This PR adds Databricks Vector Search as a new vector store in
LangChain.
- [x] Add `DatabricksVectorSearch` in `langchain/vectorstores/`
- [x] Unit tests
- [x] Add
[`databricks-vectorsearch`](https://pypi.org/project/databricks-vectorsearch/)
as a new optional dependency
We ran the following checks:
- `make format` passed ✅
- `make lint` failed but the failures were caused by other files
+ Files touched by this PR passed the linter ✅
- `make test` passed ✅
- `make coverage` failed but the failures were caused by other files.
Tests added by or related to this PR all passed
+ langchain/vectorstores/databricks_vector_search.py test coverage 94% ✅
- `make spell_check` passed ✅
The example notebook and updates to the [provider's documentation
page](https://github.com/langchain-ai/langchain/blob/master/docs/docs/integrations/providers/databricks.md)
will be added later in a separate PR.
**Dependencies:**
Optional dependency:
[`databricks-vectorsearch`](https://pypi.org/project/databricks-vectorsearch/)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Added a retriever for the Outline API to ask
questions on knowledge base
- **Issue:** resolves#11814
- **Dependencies:** None
- **Tag maintainer:** @baskaryan
- **Description:**
I encountered an issue while running the existing sample code on the
page https://python.langchain.com/docs/modules/agents/how_to/agent_iter
in an environment with Pydantic 2.0 installed. The following error was
triggered:
```python
ValidationError Traceback (most recent call last)
<ipython-input-12-2ffff2c87e76> in <cell line: 43>()
41
42 tools = [
---> 43 Tool(
44 name="GetPrime",
45 func=get_prime,
2 frames
/usr/local/lib/python3.10/dist-packages/pydantic/v1/main.py in __init__(__pydantic_self__, **data)
339 values, fields_set, validation_error = validate_model(__pydantic_self__.__class__, data)
340 if validation_error:
--> 341 raise validation_error
342 try:
343 object_setattr(__pydantic_self__, '__dict__', values)
ValidationError: 1 validation error for Tool
args_schema
subclass of BaseModel expected (type=type_error.subclass; expected_class=BaseModel)
```
I have made modifications to the example code to ensure it functions
correctly in environments with Pydantic 2.0.
This PR provides idiomatic implementations for the exact-match and the
semantic LLM caches using Astra DB as backend through the database's
HTTP JSON API. These caches require the `astrapy` library as dependency.
Comes with integration tests and example usage in the `llm_cache.ipynb`
in the docs.
@baskaryan this is the Astra DB counterpart for the Cassandra classes
you merged some time ago, tagging you for your familiarity with the
topic. Thank you!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR adds a chat message history component that uses Astra DB for
persistence through the JSON API.
The `astrapy` package is required for this class to work.
I have added tests and a small notebook, and updated the relevant
references in the other docs pages.
(@rlancemartin this is the counterpart of the Cassandra equivalent class
you so helpfully reviewed back at the end of June)
Thank you!
- **Description:** Fix typo in MongoDB memory docs
- **Tag maintainer:** @eyurtsev
<!-- Thank you for contributing to LangChain!
- **Description:** Fix typo in MongoDB memory docs
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** @baskaryan
- **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.
-->
- **Description:** This change adds an agent to the Azure Cognitive
Services toolkit for identifying healthcare entities
- **Dependencies:** azure-ai-textanalytics (Optional)
---------
Co-authored-by: James Beck <James.Beck@sa.gov.au>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:**
This commit adds embedchain retriever along with tests and docs.
Embedchain is a RAG framework to create data pipelines.
**Twitter handle:**
- [Taranjeet's twitter](https://twitter.com/taranjeetio) and
[Embedchain's twitter](https://twitter.com/embedchain)
**Reviewer**
@hwchase17
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:**
Enhance the functionality of YoutubeLoader to enable the translation of
available transcripts by refining the existing logic.
**Issue:**
Encountering a problem with YoutubeLoader (#13523) where the translation
feature is not functioning as expected.
Tag maintainers/contributors who might be interested:
@eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
## Update 2023-09-08
This PR now supports further models in addition to Lllama-2 chat models.
See [this comment](#issuecomment-1668988543) for further details. The
title of this PR has been updated accordingly.
## Original PR description
This PR adds a generic `Llama2Chat` model, a wrapper for LLMs able to
serve Llama-2 chat models (like `LlamaCPP`,
`HuggingFaceTextGenInference`, ...). It implements `BaseChatModel`,
converts a list of chat messages into the [required Llama-2 chat prompt
format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2) and
forwards the formatted prompt as `str` to the wrapped `LLM`. Usage
example:
```python
# uses a locally hosted Llama2 chat model
llm = HuggingFaceTextGenInference(
inference_server_url="http://127.0.0.1:8080/",
max_new_tokens=512,
top_k=50,
temperature=0.1,
repetition_penalty=1.03,
)
# Wrap llm to support Llama2 chat prompt format.
# Resulting model is a chat model
model = Llama2Chat(llm=llm)
messages = [
SystemMessage(content="You are a helpful assistant."),
MessagesPlaceholder(variable_name="chat_history"),
HumanMessagePromptTemplate.from_template("{text}"),
]
prompt = ChatPromptTemplate.from_messages(messages)
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
chain = LLMChain(llm=model, prompt=prompt, memory=memory)
# use chat model in a conversation
# ...
```
Also part of this PR are tests and a demo notebook.
- Tag maintainer: @hwchase17
- Twitter handle: `@mrt1nz`
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
The original notebook has the `faiss` title which is duplicated in
the`faiss.jpynb`. As a result, we have two `faiss` items in the
vectorstore ToC. And the first item breaks the searching order (it is
placed between `A...` items).
- I updated title to `Asynchronous Faiss`.
- Fixed titles for two notebooks. They were inconsistent with other
titles and clogged ToC.
- Added `Upstash` description and link
- Moved the authentication text up in the `Elasticsearch` nb, right
after package installation. It was on the end of the page which was a
wrong place.
This PR brings a few minor improvements to the docs, namely class/method
docstrings and the demo notebook.
- A note on how to control concurrency levels to tune performance in
bulk inserts, both in the class docstring and the demo notebook;
- Slightly increased concurrency defaults after careful experimentation
(still on the conservative side even for clients running on
less-than-typical network/hardware specs)
- renamed the DB token variable to the standardized
`ASTRA_DB_APPLICATION_TOKEN` name (used elsewhere, e.g. in the Astra DB
docs)
- added a note and a reference (add_text docstring, demo notebook) on
allowed metadata field names.
Thank you!
The current `integrations/document_loaders/` sidebar has the
`example_data` item, which is a menu with a single item: "Notebook".
It is happening because the `integrations/document_loaders/` folder has
the `example_data/notebook.md` file that is used to autogenerate the
above menu item.
- removed an example_data/notebook.md file. Docusaurus doesn't have
simple ways to fix this problem (to exclude folders/files from an
autogenerated sidebar). Removing this file didn't break any existing
examples, so this fix is safe.
Updated several notebooks:
- fixed titles which are inconsistent or break the ToC sorting order.
- added missed soruce descriptions and links
- fixed formatting
- the `SemaDB` notebook was placed in additional subfolder which breaks
the vectorstore ToC. I moved file up, removed this unnecessary
subfolder; updated the `vercel.json` with rerouting for the new URL
- Added SemaDB description and link
- improved text consistency
- Fixed the title of the notebook. It created an ugly ToC element as
`Activeloop DeepLake's DeepMemory + LangChain + ragas or how to get +27%
on RAG recall.`
- Added Activeloop description
- improved consistency in text
- fixed ToC (it was using HTML tagas that break left-side in-page ToC).
Now in-page ToC works
- Fixed headers (was more then 1 Titles)
- Removed security token value. It was OK to have it, because it is
temporary token, but the automatic security swippers raise warnings on
that.
- Added `ClickUp` service description and link.
The `Integrations` site is hidden now.
I've added it into the `More` menu.
The name is `Integration Cards` otherwise, it is confused with the
`Integrations` menu.
---------
Co-authored-by: Erick Friis <erickfriis@gmail.com>
The new ruff version fixed the blocking bugs, and I was able to fairly
easily us to a passing state: ruff fixed some issues on its own, I fixed
a handful by hand, and I added a list of narrowly-targeted exclusions
for files that are currently failing ruff rules that we probably should
look into eventually.
I went pretty lenient on the docs / cookbooks rules, allowing dead code
and such things. Perhaps in the future we may want to tighten the rules
further, but this is already a good set of checks that found real issues
and will prevent them going forward.
Hey @rlancemartin, @eyurtsev ,
I did some minimal changes to the `ElasticVectorSearch` client so that
it plays better with existing ES indices.
Main changes are as follows:
1. You can pass the dense vector field name into `_default_script_query`
2. You can pass a custom script query implementation and the respective
parameters to `similarity_search_with_score`
3. You can pass functions for building page content and metadata for the
resulting `Document`
<!-- 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,
4. 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:** Refine Weaviate tutorial and add an example for
Retrieval-Augmented Generation (RAG)
- **Issue:** (not applicable),
- **Dependencies:** none
- **Tag maintainer:** @baskaryan <!--
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- **Twitter handle:** @helloiamleonie
Co-authored-by: Leonie <leonie@Leonies-MBP-2.fritz.box>
On the [Defining Custom
Tools](https://python.langchain.com/docs/modules/agents/tools/custom_tools)
page, there's a 'Subclassing the BaseTool class' paragraph under the
'Completely New Tools - String Input and Output' header. Also there's
another 'Subclassing the BaseTool' paragraph under no header, which I
think may belong to the 'Custom Structured Tools' header.
Another thing is, there's a 'Using the tool decorator' and a 'Using the
decorator' paragraph, I think should belong to 'Completely New Tools -
String Input and Output' and 'Custom Structured Tools' separately.
This PR moves those paragraphs to corresponding headers.
- **Description:** Changed the fleet_context documentation to use
`context.download_embeddings()` from the latest release from our
package. More details here:
https://github.com/fleet-ai/context/tree/main#api
- **Issue:** n/a
- **Dependencies:** n/a
- **Tag maintainer:** @baskaryan
- **Twitter handle:** @andrewthezhou
Added a Docusaurus Loader
Issue: #6353
I had to implement this for working with the Ionic documentation, and
wanted to open this up as a draft to get some guidance on building this
out further. I wasn't sure if having it be a light extension of the
SitemapLoader was in the spirit of a proper feature for the library --
but I'm grateful for the opportunities Langchain has given me and I'd
love to build this out properly for the sake of the community.
Any feedback welcome!
