Since the refactoring into sub-projects `libs/langchain` and
`libs/experimental`, the `make` targets `format_diff` and `lint_diff` do
not work anymore when running `make` from these subdirectories. Reason
is that
```
PYTHON_FILES=$(shell git diff --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
```
generates paths from the project's root directory instead of the
corresponding subdirectories. This PR fixes this by adding a
`--relative` command line option.
- Tag maintainer: @baskaryan
# [WIP] Tree of Thought introducing a new ToTChain.
This PR adds a new chain called ToTChain that implements the ["Large
Language Model Guided
Tree-of-Though"](https://arxiv.org/pdf/2305.08291.pdf) paper.
There's a notebook example `docs/modules/chains/examples/tot.ipynb` that
shows how to use it.
Implements #4975
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
- @hwchase17
- @vowelparrot
---------
Co-authored-by: Vadim Gubergrits <vgubergrits@outbox.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Optimizing important numerical code and making it run faster.
Performance went up by 1.48x (148%). Runtime went down from 138715us to
56020us
Optimization explanation:
The `cosine_similarity_top_k` function is where we made the most
significant optimizations.
Instead of sorting the entire score_array which needs considering all
elements, `np.argpartition` is utilized to find the top_k largest scores
indices, this operation has a time complexity of O(n), higher
performance than sorting. Remember, `np.argpartition` doesn't guarantee
the order of the values. So we need to use argsort() to get the indices
that would sort our top-k values after partitioning, which is much more
efficient because it only sorts the top-K elements, not the entire
array. Then to get the row and column indices of sorted top_k scores in
the original score array, we use `np.unravel_index`. This operation is
more efficient and cleaner than a list comprehension.
The code has been tested for correctness by running the following
snippet on both the original function and the optimized function and
averaged over 5 times.
```
def test_cosine_similarity_top_k_large_matrices():
X = np.random.rand(1000, 1000)
Y = np.random.rand(1000, 1000)
top_k = 100
score_threshold = 0.5
gc.disable()
counter = time.perf_counter_ns()
return_value = cosine_similarity_top_k(X, Y, top_k, score_threshold)
duration = time.perf_counter_ns() - counter
gc.enable()
```
@hwaking @hwchase17 @jerwelborn
Unit tests pass, I also generated more regression tests which all
passed.
Description: Adding support for custom index and scoring profile support
in Azure Cognitive Search
@hwchase17
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR introduces async API support for Cohere, both LLM and
embeddings. It requires updating `cohere` package to `^4`.
Tagging @hwchase17, @baskaryan, @agola11
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
# Description:
**Add the possibility to keep text as Markdown in the ConfluenceLoader**
Add a bool variable that allows to keep the Markdown format of the
Confluence pages.
It is useful because it allows to use MarkdownHeaderTextSplitter as a
DataSplitter.
If this variable in set to True in the load() method, the pages are
extracted using the markdownify library.
# Issue:
[4407](https://github.com/langchain-ai/langchain/issues/4407)
# Dependencies:
Add the markdownify library
# Tag maintainer:
@rlancemartin, @eyurtsev
# Twitter handle:
FloBastinHeyI - https://twitter.com/FloBastinHeyI
---------
Co-authored-by: Florian Bastin <florian.bastin@octo.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Objects implementing Runnable: BasePromptTemplate, LLM, ChatModel,
Chain, Retriever, OutputParser
- [x] Implement Runnable in base Retriever
- [x] Raise TypeError in operator methods for unsupported things
- [x] Implement dict which calls values in parallel and outputs dict
with results
- [x] Merge in `+` for prompts
- [x] Confirm precedence order for operators, ideal would be `+` `|`,
https://docs.python.org/3/reference/expressions.html#operator-precedence
- [x] Add support for openai functions, ie. Chat Models must return
messages
- [x] Implement BaseMessageChunk return type for BaseChatModel, a
subclass of BaseMessage which implements __add__ to return
BaseMessageChunk, concatenating all str args
- [x] Update implementation of stream/astream for llm and chat models to
use new `_stream`, `_astream` optional methods, with default
implementation in base class `raise NotImplementedError` use
https://stackoverflow.com/a/59762827 to see if it is implemented in base
class
- [x] Delete the IteratorCallbackHandler (leave the async one because
people using)
- [x] Make BaseLLMOutputParser implement Runnable, accepting either str
or BaseMessage
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
ElasticsearchVectorStore.as_retriever() method is returning
`RecursionError: maximum recursion depth exceeded`
because of incorrect field reference in
`embeddings()` method
- Description: Fix RecursionError because of a typo
- Issue: the issue #8310
- Dependencies: None,
- Tag maintainer: @eyurtsev
- Twitter handle: bpatel
Description:
I wanted to use the DuckDuckGoSearch tool in an agent to let him get the
latest news for a topic. DuckDuckGoSearch has already an implemented
function for retrieving news articles. But there wasn't a tool to use
it. I simply adapted the SearchResult class with an extra argument
"backend". You can set it to "news" to only get news articles.
Furthermore, I added an example to the DuckDuckGo Notebook on how to
further customize the results by using the DuckDuckGoSearchAPIWrapper.
Dependencies: no new dependencies
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: in the .devcontainer, docker-compose build is currently
failing due to the src paths in the COPY command. This change adds the
full path to the pyproject.toml and poetry.toml to allow the build to
run.
Issue:
You can see the issue if you try to build the dev docker image with:
```
cd .devcontainer
docker-compose build
```
Dependencies: none
Twitter handle: byronsalty
- Description: During streaming, the first chunk may only contain the
name of an OpenAI function and not any arguments. In this case, the
current code presumes there is a streaming response and tries to append
to it, but gets a KeyError. This fixes that case by checking if the
arguments key exists, and if not, creates a new entry instead of
appending.
- Issue: Related to #6462
Sample Code:
```python
llm = AzureChatOpenAI(
deployment_name=deployment_name,
model_name=model_name,
streaming=True
)
tools = [PythonREPLTool()]
callbacks = [StreamingStdOutCallbackHandler()]
agent = initialize_agent(
tools=tools,
llm=llm,
agent=AgentType.OPENAI_FUNCTIONS,
callbacks=callbacks
)
agent('Run some python code to test your interpreter')
```
Previous Result:
```
File ...langchain/chat_models/openai.py:344, in ChatOpenAI._generate(self, messages, stop, run_manager, **kwargs)
342 function_call = _function_call
343 else:
--> 344 function_call["arguments"] += _function_call["arguments"]
345 if run_manager:
346 run_manager.on_llm_new_token(token)
KeyError: 'arguments'
```
New Result:
```python
{'input': 'Run some python code to test your interpreter',
'output': "The Python code `print('Hello, World!')` has been executed successfully, and the output `Hello, World!` has been printed."}
```
Co-authored-by: jswe <jswe@polencapital.com>
- Description: Fix mangling issue affecting a couple of VectorStore
classes including Redis.
- Issue: https://github.com/langchain-ai/langchain/issues/8185
- @rlancemartin
This is a simple issue but I lack of some context in the original
implementation.
My changes perhaps are not the definitive fix but to start a quick
discussion.
@hinthornw Tagging you since one of your changes introduced this
[here.](c38965fcba)
I have some Prompt subclasses in my project that I'd like to be able to
deserialize in callbacks. Right now `loads()`/`load()` will bail when it
encounters my object, but I know I can trust the objects because they're
in my own projects.
<!-- 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
-->
### Description
This PR includes the following changes:
- Adds AOSS (Amazon OpenSearch Service Serverless) support to
OpenSearch. Please refer to the documentation on how to use it.
- While creating an index, AOSS only supports Approximate Search with
`nmslib` and `faiss` engines. During Search, only Approximate Search and
Script Scoring (on doc values) are supported.
- This PR also adds support to `efficient_filter` which can be used with
`faiss` and `lucene` engines.
- The `lucene_filter` is deprecated. Instead please use the
`efficient_filter` for the lucene engine.
Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
Given a user question, this will -
* Use LLM to generate a set of queries.
* Query for each.
* The URLs from search results are stored in self.urls.
* A check is performed for any new URLs that haven't been processed yet
(not in self.url_database).
* Only these new URLs are loaded, transformed, and added to the
vectorstore.
* The vectorstore is queried for relevant documents based on the
questions generated by the LLM.
* Only unique documents are returned as the final result.
This code will avoid reprocessing of URLs across multiple runs of
similar queries, which should improve the performance of the retriever.
It also keeps track of all URLs that have been processed, which could be
useful for debugging or understanding the retriever's behavior.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Added a quick check to make integration easier with Databricks; another
option would be to make a new class, but this seemed more
straightfoward.
cc: @liangz1 Can this be done in a more straightfoward way?
This PR removes operator overloading for base message.
Removing the `+` operating from base message will help make sure that:
1) There's no need to re-define `+` for message chunks
2) That there's no unexpected behavior in terms of types changing
(adding two messages yields a ChatPromptTemplate which is not a message)
- Description: Small change to fix broken Azure streaming. More complete
migration probably still necessary once the new API behavior is
finalized.
- Issue: Implements fix by @rock-you in #6462
- Dependencies: N/A
There don't seem to be any tests specifically for this, and I was having
some trouble adding some. This is just a small temporary fix to allow
for the new API changes that OpenAI are releasing without breaking any
other code.
---------
Co-authored-by: Jacob Swe <jswe@polencapital.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
# What
- This is to add test for faiss vector store with score threshold
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: This is to add test for faiss vector store with score
threshold
- Issue: None
- Dependencies: None
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @MlopsJ
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
-->
# What
- Use `logger` instead of using logging directly.
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: Use `logger` instead of using logging directly.
- Issue: None
- Dependencies: None
- Tag maintainer: @baskaryan
- Twitter handle: @MlopsJ
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
-->
Refactored `requests.py`. The same as
https://github.com/langchain-ai/langchain/pull/7961#8098#8099
requests.py is in the root code folder. This creates the
`langchain.requests: Requests` group on the API Reference navigation
ToC, on the same level as Chains and Agents which is incorrect.
Refactoring:
- copied requests.py content into utils/requests.py
- I added the backwards compatibility ref in the original requests.py.
- updated imports to requests objects
@hwchase17, @baskaryan
Addresses #7578. `run()` can return dictionaries, Pydantic objects or
strings, so the type hints should reflect that. See the chain from
`create_structured_output_chain` for an example of a non-string return
type from `run()`.
I've updated the BaseLLMChain return type hint from `str` to `Any`.
Although, the differences between `run()` and `__call__()` seem less
clear now.
CC: @baskaryan
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Until now, hybrid search was limited to modules requiring external
services, such as Weaviate/Pinecone Hybrid Search. However, I have
developed a hybrid retriever that can merge a list of retrievers using
the [Reciprocal Rank
Fusion](https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf)
algorithm. This new approach, similar to Weaviate hybrid search, does
not require the initialization of any external service.
- Dependencies: No - Twitter handle: dayuanjian21687
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Changed "SELECT" and "UPDTAE" intent check from "=" to
"in",
- Issue: Based on my own testing, most of the LLM (StarCoder, NeoGPT3,
etc..) doesn't return a single word response ("SELECT" / "UPDATE")
through this modification, we can accomplish the same output without
curated prompt engineering.
- Dependencies: None
- Tag maintainer: @baskaryan
- Twitter handle: @aditya_0290
Thank you for maintaining this library, Keep up the good efforts.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Stop sequences are useful if you are doing long-running completions and
need to early-out rather than running for the full max_length... not
only does this save inference cost on Replicate, it is also much faster
if you are going to truncate the output later anyway.
Other LLMs support stop sequences natively (e.g. OpenAI) but I didn't
see this for Replicate so adding this via their prediction cancel
method.
Housekeeping: I ran `make format` and `make lint`, no issues reported in
the files I touched.
I did update the replicate integration test and ran `poetry run pytest
tests/integration_tests/llms/test_replicate.py` successfully.
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 :-)
Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
@rlancemartin
The modification includes:
* etherscanLoader
* test_etherscan
* document ipynb
I have run the test, lint, format, and spell check. I do encounter a
linting error on ipynb, I am not sure how to address that.
```
docs/extras/modules/data_connection/document_loaders/integrations/Etherscan.ipynb:55: error: Name "null" is not defined [name-defined]
docs/extras/modules/data_connection/document_loaders/integrations/Etherscan.ipynb:76: error: Name "null" is not defined [name-defined]
Found 2 errors in 1 file (checked 1 source file)
```
- Description: The Etherscan loader uses etherscan api to load
transaction histories under specific accounts on Ethereum Mainnet.
- No dependency is introduced by this PR.
- Twitter handle: glazecl
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
ChatGLM LLM integration will by default accumulate conversation
history(with_history=True) to ChatGLM backend api, which is not expected
in most cases. This PR set with_history=False by default, user should
explicitly set llm.with_history=True to turn this feature on. Related
PR: #8048#7774
---------
Co-authored-by: mlot <limpo2000@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
My team recently faced an issue while using MSSQL and passing a schema
name.
We noticed that "SET search_path TO {self.schema}" is being called for
us, which is not a valid ms-sql query, and is specific to postgresql
dialect.
We were able to run it locally after this fix.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Refactored `example_generator.py`. The same as #7961
`example_generator.py` is in the root code folder. This creates the
`langchain.example_generator: Example Generator ` group on the API
Reference navigation ToC, on the same level as `Chains` and `Agents`
which is not correct.
Refactoring:
- moved `example_generator.py` content into
`chains/example_generator.py` (not in `utils` because the
`example_generator` has dependencies on other LangChain classes. It also
doesn't work for moving into `utilities/`)
- added the backwards compatibility ref in the original
`example_generator.py`
@hwchase17
Refactored `input.py`. The same as
https://github.com/langchain-ai/langchain/pull/7961#8098#8099
input.py is in the root code folder. This creates the `langchain.input:
Input` group on the API Reference navigation ToC, on the same level as
Chains and Agents which is incorrect.
Refactoring:
- copied input.py file into utils/input.py
- I added the backwards compatibility ref in the original input.py.
- changed several imports to a new ref
@hwchase17, @baskaryan
Description:
This PR adds embeddings for LocalAI (
https://github.com/go-skynet/LocalAI ), a self-hosted OpenAI drop-in
replacement. As LocalAI can re-use OpenAI clients it is mostly following
the lines of the OpenAI embeddings, however when embedding documents, it
just uses string instead of sending tokens as sending tokens is
best-effort depending on the model being used in LocalAI. Sending tokens
is also tricky as token id's can mismatch with the model - so it's safer
to just send strings in this case.
Partly related to: https://github.com/hwchase17/langchain/issues/5256
Dependencies: No new dependencies
Twitter: @mudler_it
---------
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**PR Description:**
This pull request introduces several enhancements and new features to
the `CubeSemanticLoader`. The changes include the following:
1. Added imports for the `json` and `time` modules.
2. Added new constructor parameters: `load_dimension_values`,
`dimension_values_limit`, `dimension_values_max_retries`, and
`dimension_values_retry_delay`.
3. Updated the class documentation with descriptions for the new
constructor parameters.
4. Added a new private method `_get_dimension_values()` to retrieve
dimension values from Cube's REST API.
5. Modified the `load()` method to load dimension values for string
dimensions if `load_dimension_values` is set to `True`.
6. Updated the API endpoint in the `load()` method from the base URL to
the metadata endpoint.
7. Refactored the code to retrieve metadata from the response JSON.
8. Added the `column_member_type` field to the metadata dictionary to
indicate if a column is a measure or a dimension.
9. Added the `column_values` field to the metadata dictionary to store
the dimension values retrieved from Cube's API.
10. Modified the `page_content` construction to include the column title
and description instead of the table name, column name, data type,
title, and description.
These changes improve the functionality and flexibility of the
`CubeSemanticLoader` class by allowing the loading of dimension values
and providing more detailed metadata for each document.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Refactored `formatting.py`. The same as
https://github.com/langchain-ai/langchain/pull/7961#8098#8099
formatting.py is in the root code folder. This creates the
`langchain.formatting: Formatting` group on the API Reference navigation
ToC, on the same level as Chains and Agents which is incorrect.
Refactoring:
- moved formatting.py content into utils/formatting.py
- I did not add the backwards compatibility ref in the original
formatting.py. It seems unnecessary.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: In the llms/__init__.py, the key name is wrong for
mlflowaigateway. It should be mlflow-ai-gateway
- Issue: NA
- Dependencies: NA
- Tag maintainer: @hwchase17, @baskaryan
- Twitter handle: na
Without this fix, when we run the code for mlflowaigateway, we will get
error as below
ValueError: Loading mlflow-ai-gateway LLM not supported
---------
Co-authored-by: rajib76 <rajib76@yahoo.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Fixes an issue with the github tool where the API returned special
objects but the tool was expecting dictionaries.
Also added proper docstrings to the GitHubAPIWraper methods and a (very
basic) integration test.
Maintainer responsibilities:
- Agents / Tools / Toolkits: @hinthornw
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
# What
- Add faiss vector search test for score threshold
- Fix failing faiss vector search test; filtering with list value is
wrong.
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: Add faiss vector search test for score threshold; Fix
failing faiss vector search test; filtering with list value is wrong.
- Issue: None
- Dependencies: None
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: @MlopsJ
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
-->
Codespaces and devcontainer was broken by the [repo
restructure](https://github.com/langchain-ai/langchain/discussions/8043).
- Description: Add libs/langchain to container so it can be built
without error.
- Issue: -
- Dependencies: -
- Tag maintainer: @hwchase17 @baskaryan
- Twitter handle: @finnless
The failed build log says:
```
#10 [langchain-dev-dependencies 2/2] RUN poetry install --no-interaction --no-ansi --with dev,test,docs
#10 sha256:e850ee99fc966158bfd2d85e82b7c57244f47ecbb1462e75bd83b981a56a1929
2023-07-23 23:30:33.692Z: #10 0.827
#10 0.827 Directory libs/langchain does not exist
2023-07-23 23:30:33.738Z: #10 ERROR: executor failed running [/bin/sh -c poetry install --no-interaction --no-ansi --with dev,test,docs]: exit code: 1
```
The new pyproject.toml imports from libs/langchain:
77bf75c236/pyproject.toml (L14-L16)
But libs/langchain is never added to the dev.Dockerfile:
77bf75c236/libs/langchain/dev.Dockerfile (L37-L39)
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}
)
```
