### Description
This PR adds a wrapper which adds support for the OpenSearch vector
database. Using opensearch-py client we are ingesting the embeddings of
given text into opensearch cluster using Bulk API. We can perform the
`similarity_search` on the index using the 3 popular searching methods
of OpenSearch k-NN plugin:
- `Approximate k-NN Search` use approximate nearest neighbor (ANN)
algorithms from the [nmslib](https://github.com/nmslib/nmslib),
[faiss](https://github.com/facebookresearch/faiss), and
[Lucene](https://lucene.apache.org/) libraries to power k-NN search.
- `Script Scoring` extends OpenSearch’s script scoring functionality to
execute a brute force, exact k-NN search.
- `Painless Scripting` adds the distance functions as painless
extensions that can be used in more complex combinations. Also, supports
brute force, exact k-NN search like Script Scoring.
### Issues Resolved
https://github.com/hwchase17/langchain/issues/1054
---------
Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
Follow-up of @hinthornw's PR:
- Migrate the Tool abstraction to a separate file (`BaseTool`).
- `Tool` implementation of `BaseTool` takes in function and coroutine to
more easily maintain backwards compatibility
- Add a Toolkit abstraction that can own the generation of tools around
a shared concept or state
---------
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com>
Co-authored-by: cragwolfe <cragcw@gmail.com>
Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com>
Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com>
Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net>
Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
This approach has several advantages:
* it improves the readability of the code
* removes incompatibilities between SQL dialects
* fixes a bug with `datetime` values in rows and `ast.literal_eval`
Huge thanks and credits to @jzluo for finding the weaknesses in the
current approach and for the thoughtful discussion on the best way to
implement this.
---------
Co-authored-by: Francisco Ingham <>
Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>
Pydantic validation breaks tests for example (`test_qdrant.py`) because
fake embeddings contain an integer.
This PR casts the embeddings array to all floats.
Now the `qdrant` test passes, `poetry run pytest
tests/integration_tests/vectorstores/test_qdrant.py`
Fix KeyError 'items' when no result found.
## Problem
When no result found for a query, google search crashed with `KeyError
'items'`.
## Solution
I added a check for an empty response before accessing the 'items' key.
It will handle the case correctly.
## Other
my twitter: yakigac
(I don't mind even if you don't mention me for this PR. But just because
last time my real name was shout out :) )
Alternate implementation to PR #960 Again - only FAISS is implemented.
If accepted can add this to other vectorstores or leave as
NotImplemented? Suggestions welcome...
Adds Google Search integration with [Serper](https://serper.dev) a
low-cost alternative to SerpAPI (10x cheaper + generous free tier).
Includes documentation, tests and examples. Hopefully I am not missing
anything.
Developers can sign up for a free account at
[serper.dev](https://serper.dev) and obtain an api key.
## Usage
```python
from langchain.utilities import GoogleSerperAPIWrapper
from langchain.llms.openai import OpenAI
from langchain.agents import initialize_agent, Tool
import os
os.environ["SERPER_API_KEY"] = ""
os.environ['OPENAI_API_KEY'] = ""
llm = OpenAI(temperature=0)
search = GoogleSerperAPIWrapper()
tools = [
Tool(
name="Intermediate Answer",
func=search.run
)
]
self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
```
### Output
```
Entering new AgentExecutor chain...
Yes.
Follow up: Who is the reigning men's U.S. Open champion?
Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion.
Follow up: Where is Carlos Alcaraz from?
Intermediate answer: El Palmar, Spain
So the final answer is: El Palmar, Spain
> Finished chain.
'El Palmar, Spain'
```
Currently the chain is getting the column names and types on the one
side and the example rows on the other. It is easier for the llm to read
the table information if the column name and examples are shown together
so that it can easily understand to which columns do the examples refer
to. For an instantiation of this, please refer to the changes in the
`sqlite.ipynb` notebook.
Also changed `eval` for `ast.literal_eval` when interpreting the results
from the sample row query since it is a better practice.
---------
Co-authored-by: Francisco Ingham <>
---------
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
This PR adds persistence to the Chroma vector store.
Users can supply a `persist_directory` with any of the `Chroma` creation
methods. If supplied, the store will be automatically persisted at that
directory.
If a user creates a new `Chroma` instance with the same persistence
directory, it will get loaded up automatically. If they use `from_texts`
or `from_documents` in this way, the documents will be loaded into the
existing store.
There is the chance of some funky behavior if the user passes a
different embedding function from the one used to create the collection
- we will make this easier in future updates. For now, we log a warning.
Chroma is a simple to use, open-source, zero-config, zero setup
vectorstore.
Simply `pip install chromadb`, and you're good to go.
Out-of-the-box Chroma is suitable for most LangChain workloads, but is
highly flexible. I tested to 1M embs on my M1 mac, with out issues and
reasonably fast query times.
Look out for future releases as we integrate more Chroma features with
LangChain!
Co-authored-by: Andrew White <white.d.andrew@gmail.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
Co-authored-by: Peng Qu <82029664+pengqu123@users.noreply.github.com>
Supporting asyncio in langchain primitives allows for users to run them
concurrently and creates more seamless integration with
asyncio-supported frameworks (FastAPI, etc.)
Summary of changes:
**LLM**
* Add `agenerate` and `_agenerate`
* Implement in OpenAI by leveraging `client.Completions.acreate`
**Chain**
* Add `arun`, `acall`, `_acall`
* Implement them in `LLMChain` and `LLMMathChain` for now
**Agent**
* Refactor and leverage async chain and llm methods
* Add ability for `Tools` to contain async coroutine
* Implement async SerpaPI `arun`
Create demo notebook.
Open questions:
* Should all the async stuff go in separate classes? I've seen both
patterns (keeping the same class and having async and sync methods vs.
having class separation)
This allows the LLM to correct its previous command by looking at the
error message output to the shell.
Additionally, this uses subprocess.run because that is now recommended
over subprocess.check_output:
https://docs.python.org/3/library/subprocess.html#using-the-subprocess-module
Co-authored-by: Amos Ng <me@amos.ng>
Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
Signed-off-by: Frank Liu <frank.liu@zilliz.com>
Co-authored-by: Filip Haltmayer <81822489+filip-halt@users.noreply.github.com>
Co-authored-by: Frank Liu <frank@frankzliu.com>
This does not involve a separator, and will naively chunk input text at
the appropriate boundaries in token space.
This is helpful if we have strict token length limits that we need to
strictly follow the specified chunk size, and we can't use aggressive
separators like spaces to guarantee the absence of long strings.
CharacterTextSplitter will let these strings through without splitting
them, which could cause overflow errors downstream.
Splitting at arbitrary token boundaries is not ideal but is hopefully
mitigated by having a decent overlap quantity. Also this results in
chunks which has exact number of tokens desired, instead of sometimes
overcounting if we concatenate shorter strings.
Potentially also helps with #528.
# Problem
I noticed that in order to change the prefix of the prompt in the
`zero-shot-react-description` agent
we had to dig around to subset strings deep into the agent's attributes.
It requires the user to inspect a long chain of attributes and classes.
`initialize_agent -> AgentExecutor -> Agent -> LLMChain -> Prompt from
Agent.create_prompt`
``` python
agent = initialize_agent(
tools=tools,
llm=fake_llm,
agent="zero-shot-react-description"
)
prompt_str = agent.agent.llm_chain.prompt.template
new_prompt_str = change_prefix(prompt_str)
agent.agent.llm_chain.prompt.template = new_prompt_str
```
# Implemented Solution
`initialize_agent` accepts `**kwargs` but passes it to `AgentExecutor`
but not `ZeroShotAgent`, by simply giving the kwargs to the agent class
methods we can support changing the prefix and suffix for one agent
while allowing future agents to take advantage of `initialize_agent`.
```
agent = initialize_agent(
tools=tools,
llm=fake_llm,
agent="zero-shot-react-description",
agent_kwargs={"prefix": prefix, "suffix": suffix}
)
```
To be fair, this was before finding docs around custom agents here:
https://langchain.readthedocs.io/en/latest/modules/agents/examples/custom_agent.html?highlight=custom%20#custom-llmchain
but i find that my use case just needed to change the prefix a little.
# Changes
* Pass kwargs to Agent class method
* Added a test to check suffix and prefix
---------
Co-authored-by: Jason Liu <jason@jxnl.coA>
It's generally considered to be a good practice to pin dependencies to
prevent surprise breakages when a new version of a dependency is
released. This commit adds the ability to pin dependencies when loading
from LangChainHub.
Centralizing this logic and using urllib fixes an issue identified by
some windows users highlighted in this video -
https://youtu.be/aJ6IQUh8MLQ?t=537
The agents usually benefit from understanding what the data looks like
to be able to filter effectively. Sending just one row in the table info
allows the agent to understand the data before querying and get better
results.
---------
Co-authored-by: Francisco Ingham <>
---------
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
* add implementations of `BaseCallbackHandler` to support tracing:
`SharedTracer` which is thread-safe and `Tracer` which is not and is
meant to be used locally.
* Tracers persist runs to locally running `langchain-server`
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- This uses the faiss built-in `write_index` and `load_index` to save
and load faiss indexes locally
- Also fixes#674
- The save/load functions also use the faiss library, so I refactored
the dependency into a function
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
https://github.com/hwchase17/langchain/issues/354
Add support for running your own HF pipeline locally. This would allow
you to get a lot more dynamic with what HF features and models you
support since you wouldn't be beholden to what is hosted in HF hub. You
could also do stuff with HF Optimum to quantize your models and stuff to
get pretty fast inference even running on a laptop.
This PR has two contributions:
1. Add test for when stop token is found in middle of text
2. Add code coverage tooling and instructions
- Add pytest-cov via poetry
- Add necessary config files
- Add new make instruction for `coverage`
- Update README with coverage guidance
- Update minor README formatting/spelling
Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
Love the project, a ton of fun!
I think the PR is pretty self-explanatory, happy to make any changes! I
am working on using it in an `LLMBashChain` and may update as that
progresses.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Add support for calling HuggingFace embedding models
using the HuggingFaceHub Inference API. New class mirrors
the existing HuggingFaceHub LLM implementation. Currently
only supports 'sentence-transformers' models.
Closes#86
Add MemoryChain and ConversationChain as chains that take a docstore in
addition to the prompt, and use the docstore to stuff context into the
prompt. This can be used to have an ongoing conversation with a chatbot.
Probably needs a bit of refactoring for code quality
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Also updated docs, and noticed an issue with the add_texts method on
VectorStores that I had missed before -- the metadatas arg should be
required to match the classmethod which initializes the VectorStores
(the add_example methods break otherwise in the ExampleSelectors)
this will break atm but wanted to get thoughts on implementation.
1. should add() be on docstore interface?
2. should InMemoryDocstore change to take a list of documents as init?
(makes this slightly easier to implement in FAISS -- if we think it is
less clean then could expose a method to get the number of documents
currently in the dict, and perform the logic of creating the necessary
dictionary in the FAISS.add_texts method.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
`SQLDatabase` now accepts two `init` arguments:
1. `ignore_tables` to pass in a list of tables to not search over
2. `include_tables` to restrict to a list of tables to consider
This is a simple proof of concept of using external files as templates.
I'm still feeling my way around the codebase.
As a user, I want to use files as prompts, so it will be easier to
manage and test prompts.
The future direction is to use a template engine, most likely Mako.
This fixes Issue #104
The tests for HF Embeddings is skipped because of the segfault issue
mentioned there. Perhaps, a new issue should be created for that?
lots of kwargs! generation docs here:
https://docs.nlpcloud.com/#generation
This somewhat breaks the paradigm introduced in LLM base class as the
stop sequence isn't a list, and should rightfully be introduced at the
time of initialization of the class, along with the other kwargs that
depend on its presence (e.g. remove_end_sequence, etc.) curious if you'd
want to refactor LLM base class to take out stop as a specific named
kwarg?
Add support for huggingface hub
I could not find a good way to enforce stop tokens over the huggingface
hub api - that needs to hopefully be cleaned up in the future
