- 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>
## Summary
This PR corrects the checks for credentials_profile_name, and
region_name attributes. This was causing validation exceptions when
either of these values were missing during creation of the retriever
class.
Fixes#7571
#### Requested reviewers:
@baskaryan
Updates to the WhyLabsCallbackHandler and example notebook
- Update dependency to langkit 0.0.6 which defines new helper methods
for callback integrations
- Update WhyLabsCallbackHandler to use the new `get_callback_instance`
so that the callback is mostly defined in langkit
- Remove much of the implementation of the WhyLabsCallbackHandler here
in favor of the callback instance
This does not change the behavior of the whylabs callback handler
implementation but is a reorganization that moves some of the
implementation externally to our optional dependency package, and should
make future updates easier.
@agola11
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
This PR adds model architecture to the `WandbTracer` from the Serialized
Run kwargs. This allows visualization of the calling parameters of an
Agent, LLM and Tool in Weights & Biases.
1. Safely serialize the run objects to WBTraceTree model_dict
2. Refactors the run processing logic to be more organized.
- Twitter handle: @parambharat
---------
Co-authored-by: Bharat Ramanathan <ramanathan.parameshwaran@gohuddl.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: I wanted to be able to redirect debug output to a function,
but it wasn't very easy. I figured it would make sense to implement a
`FunctionCallbackHandler`, and reimplement `ConsoleCallbackHandler` as a
subclass that calls the `print` function. Now I can create a simple
subclass in my project that calls `logging.info` or whatever I need.
Tag maintainer: @agola11
Twitter handle: `@andandaraalex`
Added an _endpoint_url_ attribute to Bedrock(LLM) class - I have access
to Bedrock only via us-west-2 endpoint and needed to change the endpoint
url, this could be useful to other users
This change makes the ecosystem integrations cnosdb documentation more
realistic and easy to understand.
- change examples of question and table
- modify typo and format
When using callbacks, there are times when callbacks can be added
redundantly: for instance sometimes you might need to create an llm with
specific callbacks, but then also create and agent that uses a chain
that has those callbacks already set. This means that "callbacks" might
get passed down again to the llm at predict() time, resulting in
duplicate calls to the `on_llm_start` callback.
For the sake of simplicity, I made it so that langchain never adds an
exact handler/callbacks object in `add_handler`, thus avoiding the
duplicate handler issue.
Tagging @hwchase17 for callback review
---------
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**: Current implementation assumes that the length of
`texts` and `ids` should be same but if the passed `ids` length is not
equal to the passed length of `texts`, current code
`dict(zip(index_to_id.values(), documents))` is not failing or giving
any warning and silently creating docstores only for the passed `ids`
i.e. if `ids = ['A']` and `texts=["I love Open Source","I love
langchain"]` then only one `docstore` will be created. But either two
docstores should be created assuming same id value for all the elements
of `texts` or an error should be raised.
- **Issue**: My change fixes this by using dictionary comprehension
instead of `zip`. This was if lengths of `ids` and `texts` mismatches an
explicit `IndexError` will be raised.
@rlancemartin, @eyurtsev
fix#7569
add following properties for Notion DB document loader's metadata
- `unique_id`
- `status`
- `people`
@rlancemartin, @eyurtsev (Since this is a change related to
`DataLoaders`)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Currently `ChatOutputParser` extracts actions by splitting the text on
"```", and then load the second part as a json string.
But sometimes the LLM will wrap the action in markdown code block like:
````markdown
```json
{
"action": "foo",
"action_input": "bar"
}
```
````
Splitting text on "```" will cause `OutputParserException` in such case.
This PR changes the behaviour to extract the `$JSON_BLOB` by regex, so
that it can handle both ` ``` ``` ` and ` ```json ``` `
@hinthornw
---------
Co-authored-by: Junlin Zhou <jlzhou@zjuici.com>
**Description: a description of the change**
Fixed `make docs_build` and related scripts which caused errors. There
are several changes.
First, I made the build of the documentation and the API Reference into
two separate commands. This is because it takes less time to build. The
commands for documents are `make docs_build`, `make docs_clean`, and
`make docs_linkcheck`. The commands for API Reference are `make
api_docs_build`, `api_docs_clean`, and `api_docs_linkcheck`.
It looked like `docs/.local_build.sh` could be used to build the
documentation, so I used that. Since `.local_build.sh` was also building
API Rerefence internally, I removed that process. `.local_build.sh` also
added some Bash options to stop in error or so. Futher more added `cd
"${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: Refactor the upsert method in the Pinecone class to allow
for additional keyword arguments. This change adds flexibility and
extensibility to the method, allowing for future modifications or
enhancements. The upsert method now accepts the `**kwargs` parameter,
which can be used to pass any additional arguments to the Pinecone
index. This change has been made in both the `upsert` method in the
`Pinecone` class and the `upsert` method in the
`similarity_search_with_score` class method. Falls in line with the
usage of the upsert method in
[Pinecone-Python-Client](4640c4cf27/pinecone/index.py (L73))
Issue: [This feature request in Pinecone
Repo](https://github.com/pinecone-io/pinecone-python-client/issues/184)
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- Memory: @hwchase17
---------
Co-authored-by: kwesi <22204443+yankskwesi@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Lance Martin <122662504+rlancemartin@users.noreply.github.com>
### Description:
This PR introduces a new option format_diff to the existing Makefile.
This option allows us to apply the formatting tools (Black and isort)
only to the changed Python and ipynb files since the last commit. This
will make our development process more efficient as we only format the
codes that we modify. Along with this change, comments were added to
make the Makefile more understandable and maintainable.
### Issue:
N/A
### Dependencies:
Add dependency to black.
### Tag maintainer:
@baskaryan
### Twitter handle:
[kzk_maeda](https://twitter.com/kzk_maeda)
---------
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 simply awaits `AsyncRunManager`'s method call in `MulitRouteChain`.
Noticed this while playing around with Langchain's implementation of
`MultiPromptChain`. @baskaryan
cheers
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: ChatOpenAI model does not return finish_reason in
generation_info.
Issue: #2702
Dependencies: None
Tag maintainer: @baskaryan
Thank you
---------
Co-authored-by: Bagatur <baskaryan@gmail.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
-->
Currently there are 4 tools in SQL agent-toolkits, and 2 of them have
reference to the other 2.
This PR change the reference from hard coded string to `{tool.name}`
Co-authored-by: Junlin Zhou <jlzhou@zjuici.com>
Small fix to a link from the Marqo page in the ecosystem.
The link was not updated correctly when the documentation structure
changed to html pages instead of links to notebooks.
I found it unclear, where to get the API keys for JinaChat. Mentioning
this in the docstring should be helpful.
#7490
Twitter handle: benji1a
@delgermurun
@svlandeg gave me a tip for how to improve a bit on
https://github.com/hwchase17/langchain/pull/7442 for some extra speed
and memory gains. The tagger isn't needed for sentencization, so can be
disabled too.
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>
Description: Current `_call` function in the
`langchain.llms.HuggingFaceEndpoint` class truncates response when
`task=text-generation`. Same error discussed a few days ago on Hugging
Face: https://huggingface.co/tiiuae/falcon-40b-instruct/discussions/51
Issue: Fixes#7353
Tag maintainer: @hwchase17 @baskaryan @hinthornw
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: This pull request aims to support generating the correct
generic relevancy scores for different vector stores by refactoring the
relevance score functions and their selection in the base class and
subclasses of VectorStore. This is especially relevant with VectorStores
that require a distance metric upon initialization. Note many of the
current implenetations of `_similarity_search_with_relevance_scores` are
not technically correct, as they just return
`self.similarity_search_with_score(query, k, **kwargs)` without applying
the relevant score function
Also includes changes associated with:
https://github.com/hwchase17/langchain/pull/6564 and
https://github.com/hwchase17/langchain/pull/6494
See more indepth discussion in thread in #6494
Issue:
https://github.com/hwchase17/langchain/issues/6526https://github.com/hwchase17/langchain/issues/6481https://github.com/hwchase17/langchain/issues/6346
Dependencies: None
The changes include:
- Properly handling score thresholding in FAISS
`similarity_search_with_score_by_vector` for the corresponding distance
metric.
- Refactoring the `_similarity_search_with_relevance_scores` method in
the base class and removing it from the subclasses for incorrectly
implemented subclasses.
- Adding a `_select_relevance_score_fn` method in the base class and
implementing it in the subclasses to select the appropriate relevance
score function based on the distance strategy.
- Updating the `__init__` methods of the subclasses to set the
`relevance_score_fn` attribute.
- Removing the `_default_relevance_score_fn` function from the FAISS
class and using the base class's `_euclidean_relevance_score_fn`
instead.
- Adding the `DistanceStrategy` enum to the `utils.py` file and updating
the imports in the vector store classes.
- Updating the tests to import the `DistanceStrategy` enum from the
`utils.py` file.
---------
Co-authored-by: Hanit <37485638+hanit-com@users.noreply.github.com>
Improve documentation for a central use-case, qa / chat over documents.
This will be merged as an update to `index.mdx`
[here](https://python.langchain.com/docs/use_cases/question_answering/).
Testing w/ local Docusaurus server:
```
From `docs` directory:
mkdir _dist
cp -r {docs_skeleton,snippets} _dist
cp -r extras/* _dist/docs_skeleton/docs
cd _dist/docs_skeleton
yarn install
yarn start
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
