Moving to the latest non-preview Azure OpenAI API version=2023-05-15.
The previous 2023-03-15-preview doesn't have support, SLA etc. For
instance, OpenAI SDK has moved to this version
https://github.com/openai/openai-python/releases/tag/v0.27.7
@baskaryan
Description:
Currently, Zilliz only support dedicated clusters using a pair of
username and password for connection. Regarding serverless clusters,
they can connect to them by using API keys( [ see official note
detail](https://docs.zilliz.com/docs/manage-cluster-credentials)), so I
add API key(token) description in Zilliz docs to make it more obvious
and convenient for this group of users to better utilize Zilliz. No
changes done to code.
---------
Co-authored-by: Robin.Wang <3Jg$94sbQ@q1>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Azure GPT-4 models can't be accessed via LLM model. It's easy to miss
that and a lot of discussions about that are on the Internet. Therefore
I added a comment in Azure LLM docs that mentions that and points to
Azure Chat OpenAI docs.
@baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: This PR adds the option to retrieve scores and explanations
in the WeaviateHybridSearchRetriever. This feature improves the
usability of the retriever by allowing users to understand the scoring
logic behind the search results and further refine their search queries.
Issue: This PR is a solution to the issue #7855
Dependencies: This PR does not introduce any new dependencies.
Tag maintainer: @rlancemartin, @eyurtsev
I have included a unit test for the added feature, ensuring that it
retrieves scores and explanations correctly. I have also included an
example notebook demonstrating its use.
Here I am adding documentation for the `PromptLayerCallbackHandler`.
When we created the initial PR for the callback handler the docs were
causing issues, so we merged without the docs.
Motivation, it seems that when dealing with a long context and "big"
number of relevant documents we must avoid using out of the box score
ordering from vector stores.
See: https://arxiv.org/pdf/2306.01150.pdf
So, I added an additional parameter that allows you to reorder the
retrieved documents so we can work around this performance degradation.
The relevance respect the original search score but accommodates the
lest relevant document in the middle of the context.
Extract from the paper (one image speaks 1000 tokens):
This seems to be common to all diff arquitectures. SO I think we need a
good generic way to implement this reordering and run some test in our
already running retrievers.
It could be that my approach is not the best one from the architecture
point of view, happy to have a discussion about that.
For me this was the best place to introduce the change and start
retesting diff implementations.
@rlancemartin, @eyurtsev
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Still don't have good "how to's", and the guides / examples section
could be further pruned and improved, but this PR adds a couple examples
for each of the common evaluator interfaces.
- [x] Example docs for each implemented evaluator
- [x] "how to make a custom evalutor" notebook for each low level APIs
(comparison, string, agent)
- [x] Move docs to modules area
- [x] Link to reference docs for more information
- [X] Still need to finish the evaluation index page
- ~[ ] Don't have good data generation section~
- ~[ ] Don't have good how to section for other common scenarios / FAQs
like regression testing, testing over similar inputs to measure
sensitivity, etc.~
- Description: Add a BM25 Retriever that do not need Elastic search
- Dependencies: rank_bm25(if it is not installed it will be install by
using pip, just like TFIDFRetriever do)
- Tag maintainer: @rlancemartin, @eyurtsev
- Twitter handle: DayuanJian21687
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description:
Add LLM for ChatGLM-6B & ChatGLM2-6B API
Related Issue:
Will the langchain support ChatGLM? #4766
Add support for selfhost models like ChatGLM or transformer models #1780
Dependencies:
No extra library install required.
It wraps api call to a ChatGLM(2)-6B server(start with api.py), so api
endpoint is required to run.
Tag maintainer: @mlot
Any comments on this PR would be appreciated.
---------
Co-authored-by: mlot <limpo2000@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
# Support Redis Sentinel database connections
This PR adds the support to connect not only to Redis standalone servers
but High Availability Replication sets too
(https://redis.io/docs/management/sentinel/)
Redis Replica Sets have on Master allowing to write data and 2+ replicas
with read-only access to the data. The additional Redis Sentinel
instances monitor all server and reconfigure the RW-Master on the fly if
it comes unavailable.
Therefore all connections must be made through the Sentinels the query
the current master for a read-write connection. This PR adds basic
support to also allow a redis connection url specifying a Sentinel as
Redis connection.
Redis documentation and Jupyter notebook with Redis examples are updated
to mention how to connect to a redis Replica Set with Sentinels
-
Remark - i did not found test cases for Redis server connections to add
new cases here. Therefor i tests the new utility class locally with
different kind of setups to make sure different connection urls are
working as expected. But no test case here as part of this PR.
- [Xorbits](https://doc.xorbits.io/en/latest/) is an open-source
computing framework that makes it easy to scale data science and machine
learning workloads in parallel. Xorbits can leverage multi cores or GPUs
to accelerate computation on a single machine, or scale out up to
thousands of machines to support processing terabytes of data.
- This PR added support for the Xorbits agent, which allows langchain to
interact with Xorbits Pandas dataframe and Xorbits Numpy array.
- Dependencies: This change requires the Xorbits library to be installed
in order to be used.
`pip install xorbits`
- Request for review: @hinthornw
- Twitter handle: https://twitter.com/Xorbitsio
<!-- 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
-->
Integrate [Rockset](https://rockset.com/docs/) as a document loader.
Issue: None
Dependencies: Nothing new (rockset's dependency was already added
[here](https://github.com/hwchase17/langchain/pull/6216))
Tag maintainer: @rlancemartin
I have added a test for the integration and an example notebook showing
its use. I ran `make lint` and everything looks good.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This pull request adds a ElasticsearchDatabaseChain chain for
interacting with analytics database, in the manner of the
SQLDatabaseChain.
Maintainer: @samber
Twitter handler: samuelberthe
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Add langchain.llms.Tonyi for text completion, in examples into the
Tonyi Text API,
- Add system tests.
Note async completion for the Text API is not yet supported and will be
included in a future PR.
Dependencies: dashscope. It will be installed manually cause it is not
need by everyone.
Happy for feedback on any aspect of this PR @hwchase17 @baskaryan.
Multiple people have asked in #5081 for a way to limit the documents
returned from an AzureCognitiveSearchRetriever. This PR adds the `top_n`
parameter to allow that.
Twitter handle:
[@UmerHAdil](twitter.com/umerHAdil)
# Browserless
Added support for Browserless' `/content` endpoint as a document loader.
### About Browserless
Browserless is a cloud service that provides access to headless Chrome
browsers via a REST API. It allows developers to automate Chromium in a
serverless fashion without having to configure and maintain their own
Chrome infrastructure.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Lance Martin <lance@langchain.dev>
This PR is aimed at enhancing the clarity of the documentation in the
langchain project.
**Description**:
In the graphql.ipynb file, I have removed the unnecessary 'llm' argument
from the initialization process of the GraphQL tool (of type
_EXTRA_OPTIONAL_TOOLS). The 'llm' argument is not required for this
process. Its presence could potentially confuse users. This modification
simplifies the understanding of tool initialization and minimizes
potential confusion.
**Issue**: Not applicable, as this is a documentation improvement.
**Dependencies**: None.
**I kindly request a review from the following maintainer**: @hinthornw,
who is responsible for Agents / Tools / Toolkits.
No new integration is being added in this PR, hence no need for a test
or an example notebook.
Please see the changes for more detail and let me know if any further
modification is necessary.
Added fix to avoid irrelevant attributes being returned plus an example
of extracting unrelated entities and an exampe of using an 'extra_info'
attribute to extract unstructured data for an entity.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Add two new document transformers that translates
documents into different languages and converts documents into q&a
format to improve vector search results. Uses OpenAI function calling
via the [doctran](https://github.com/psychic-api/doctran/tree/main)
library.
- Issue: N/A
- Dependencies: `doctran = "^0.0.5"`
- Tag maintainer: @rlancemartin @eyurtsev @hwchase17
- Twitter handle: @psychicapi or @jfan001
Notes
- Adheres to the `DocumentTransformer` abstraction set by @dev2049 in
#3182
- refactored `EmbeddingsRedundantFilter` to put it in a file under a new
`document_transformers` module
- Added basic docs for `DocumentInterrogator`, `DocumentTransformer` as
well as the existing `EmbeddingsRedundantFilter`
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Probably the most boring PR to review ;)
Individual commits might be easier to digest
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
- Description: Adds a new chain that acts as a wrapper around Sympy to
give LLMs the ability to do some symbolic math.
- Dependencies: SymPy
---------
Co-authored-by: sreiswig <sreiswig@github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: add wrapper that lets you use KoboldAI api in langchain
- Issue: n/a
- Dependencies: none extra, just what exists in lanchain
- Tag maintainer: @baskaryan
- Twitter handle: @zanzibased
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description: a description of the change**
Fixed `make docs_build` and related scripts which caused errors. There
are several changes.
First, I made the build of the documentation and the API Reference into
two separate commands. This is because it takes less time to build. The
commands for documents are `make docs_build`, `make docs_clean`, and
`make docs_linkcheck`. The commands for API Reference are `make
api_docs_build`, `api_docs_clean`, and `api_docs_linkcheck`.
It looked like `docs/.local_build.sh` could be used to build the
documentation, so I used that. Since `.local_build.sh` was also building
API Rerefence internally, I removed that process. `.local_build.sh` also
added some Bash options to stop in error or so. Futher more added `cd
"${SCRIPT_DIR}"` at the beginning so that the script will work no matter
which directory it is executed in.
`docs/api_reference/api_reference.rst` is removed, because which is
generated by `docs/api_reference/create_api_rst.py`, and added it to
.gitignore.
Finally, the description of CONTRIBUTING.md was modified.
**Issue: the issue # it fixes (if applicable)**
https://github.com/hwchase17/langchain/issues/6413
**Dependencies: any dependencies required for this change**
`nbdoc` was missing in group docs so it was added. I installed it with
the `poetry add --group docs nbdoc` command. I am concerned if any
modifications are needed to poetry.lock. I would greatly appreciate it
if you could pay close attention to this file during the review.
**Tag maintainer**
- General / Misc / if you don't know who to tag: @baskaryan
If this PR needs any additional changes, I'll be happy to make them!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: I added an example of how to reference the OpenAI API
Organization ID, because I couldn't find it before. In the example, it
is mentioned how to achieve this using environment variables as well as
parameters for the OpenAI()-class
Issue: -
Dependencies: -
Twitter @schop-rob
This PR changes the behavior of `Qdrant.from_texts` so the collection is
reused if not requested to recreate it. Previously, calling
`Qdrant.from_texts` or `Qdrant.from_documents` resulted in removing the
old data which was confusing for many.
- Description: Added notebook to LangChain docs that explains how to use
Lemon AI NLP Workflow Automation tool with Langchain
- Issue: not applicable
- Dependencies: not applicable
- Tag maintainer: @agola11
- Twitter handle: felixbrockm
# Causal program-aided language (CPAL) chain
## Motivation
This builds on the recent [PAL](https://arxiv.org/abs/2211.10435) to
stop LLM hallucination. The problem with the
[PAL](https://arxiv.org/abs/2211.10435) approach is that it hallucinates
on a math problem with a nested chain of dependence. The innovation here
is that this new CPAL approach includes causal structure to fix
hallucination.
For example, using the below word problem, PAL answers with 5, and CPAL
answers with 13.
"Tim buys the same number of pets as Cindy and Boris."
"Cindy buys the same number of pets as Bill plus Bob."
"Boris buys the same number of pets as Ben plus Beth."
"Bill buys the same number of pets as Obama."
"Bob buys the same number of pets as Obama."
"Ben buys the same number of pets as Obama."
"Beth buys the same number of pets as Obama."
"If Obama buys one pet, how many pets total does everyone buy?"
The CPAL chain represents the causal structure of the above narrative as
a causal graph or DAG, which it can also plot, as shown below.
.
The two major sections below are:
1. Technical overview
2. Future application
Also see [this jupyter
notebook](https://github.com/borisdev/langchain/blob/master/docs/extras/modules/chains/additional/cpal.ipynb)
doc.
## 1. Technical overview
### CPAL versus PAL
Like [PAL](https://arxiv.org/abs/2211.10435), CPAL intends to reduce
large language model (LLM) hallucination.
The CPAL chain is different from the PAL chain for a couple of reasons.
* CPAL adds a causal structure (or DAG) to link entity actions (or math
expressions).
* The CPAL math expressions are modeling a chain of cause and effect
relations, which can be intervened upon, whereas for the PAL chain math
expressions are projected math identities.
PAL's generated python code is wrong. It hallucinates when complexity
increases.
```python
def solution():
"""Tim buys the same number of pets as Cindy and Boris.Cindy buys the same number of pets as Bill plus Bob.Boris buys the same number of pets as Ben plus Beth.Bill buys the same number of pets as Obama.Bob buys the same number of pets as Obama.Ben buys the same number of pets as Obama.Beth buys the same number of pets as Obama.If Obama buys one pet, how many pets total does everyone buy?"""
obama_pets = 1
tim_pets = obama_pets
cindy_pets = obama_pets + obama_pets
boris_pets = obama_pets + obama_pets
total_pets = tim_pets + cindy_pets + boris_pets
result = total_pets
return result # math result is 5
```
CPAL's generated python code is correct.
```python
story outcome data
name code value depends_on
0 obama pass 1.0 []
1 bill bill.value = obama.value 1.0 [obama]
2 bob bob.value = obama.value 1.0 [obama]
3 ben ben.value = obama.value 1.0 [obama]
4 beth beth.value = obama.value 1.0 [obama]
5 cindy cindy.value = bill.value + bob.value 2.0 [bill, bob]
6 boris boris.value = ben.value + beth.value 2.0 [ben, beth]
7 tim tim.value = cindy.value + boris.value 4.0 [cindy, boris]
query data
{
"question": "how many pets total does everyone buy?",
"expression": "SELECT SUM(value) FROM df",
"llm_error_msg": ""
}
# query result is 13
```
Based on the comments below, CPAL's intended location in the library is
`experimental/chains/cpal` and PAL's location is`chains/pal`.
### CPAL vs Graph QA
Both the CPAL chain and the Graph QA chain extract entity-action-entity
relations into a DAG.
The CPAL chain is different from the Graph QA chain for a few reasons.
* Graph QA does not connect entities to math expressions
* Graph QA does not associate actions in a sequence of dependence.
* Graph QA does not decompose the narrative into these three parts:
1. Story plot or causal model
4. Hypothetical question
5. Hypothetical condition
### Evaluation
Preliminary evaluation on simple math word problems shows that this CPAL
chain generates less hallucination than the PAL chain on answering
questions about a causal narrative. Two examples are in [this jupyter
notebook](https://github.com/borisdev/langchain/blob/master/docs/extras/modules/chains/additional/cpal.ipynb)
doc.
## 2. Future application
### "Describe as Narrative, Test as Code"
The thesis here is that the Describe as Narrative, Test as Code approach
allows you to represent a causal mental model both as code and as a
narrative, giving you the best of both worlds.
#### Why describe a causal mental mode as a narrative?
The narrative form is quick. At a consensus building meeting, people use
narratives to persuade others of their causal mental model, aka. plan.
You can share, version control and index a narrative.
#### Why test a causal mental model as a code?
Code is testable, complex narratives are not. Though fast, narratives
are problematic as their complexity increases. The problem is LLMs and
humans are prone to hallucination when predicting the outcomes of a
narrative. The cost of building a consensus around the validity of a
narrative outcome grows as its narrative complexity increases. Code does
not require tribal knowledge or social power to validate.
Code is composable, complex narratives are not. The answer of one CPAL
chain can be the hypothetical conditions of another CPAL Chain. For
stochastic simulations, a composable plan can be integrated with the
[DoWhy library](https://github.com/py-why/dowhy). Lastly, for the
futuristic folk, a composable plan as code allows ordinary community
folk to design a plan that can be integrated with a blockchain for
funding.
An explanation of a dependency planning application is
[here.](https://github.com/borisdev/cpal-llm-chain-demo)
---
Twitter handle: @boris_dev
---------
Co-authored-by: Boris Dev <borisdev@Boriss-MacBook-Air.local>
This PR proposes an implementation to support `generate` as an
`early_stopping_method` for the new `OpenAIFunctionsAgent` class.
The motivation behind is to facilitate the user to set a maximum number
of actions the agent can take with `max_iterations` and force a final
response with this new agent (as with the `Agent` class).
The following changes were made:
- The `OpenAIFunctionsAgent.return_stopped_response` method was
overwritten to support `generate` as an `early_stopping_method`
- A boolean `with_functions` parameter was added to the
`OpenAIFunctionsAgent.plan` method
This way the `OpenAIFunctionsAgent.return_stopped_response` method can
call the `OpenAIFunctionsAgent.plan` method with `with_function=False`
when the `early_stopping_method` is set to `generate`, making a call to
the LLM with no functions and forcing a final response from the
`"assistant"`.
- Relevant maintainer: @hinthornw
- Twitter handle: @aledelunap
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
