Commit Graph

445 Commits

Author SHA1 Message Date
Francisco Ingham
3f29742adc
Sql alchemy commands used in table info (#1135)
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>
2023-02-18 10:58:29 -08:00
Noah Gundotra
8c5fbab72d
[Integration Tests] Cast fake embeddings to ALL float values (#1102)
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`
2023-02-17 15:18:09 -08:00
yakigac
1ed708391e
Fix a bug that shows "KeyError 'items'" (#1118)
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 :) )
2023-02-17 13:04:02 -08:00
Harrison Chase
5e10e19bfe
Harrison/align table (#1081)
Co-authored-by: Francisco Ingham <fpingham@gmail.com>
2023-02-15 23:53:37 -08:00
Hasegawa Yuya
e08961ab25
Fixed openai embeddings to be safe by batching them based on token size calculation. (#991)
I modified the logic of the batch calculation for embedding according to
this cookbook

https://github.com/openai/openai-cookbook/blob/main/examples/Embedding_long_inputs.ipynb
2023-02-15 23:02:32 -08:00
seanaedmiston
f0a258555b
Support similarity search by vector (in FAISS) (#961)
Alternate implementation to PR #960 Again - only FAISS is implemented.
If accepted can add this to other vectorstores or leave as
NotImplemented? Suggestions welcome...
2023-02-15 22:50:00 -08:00
rogerserper
e46cd3b7db
Google Search API integration with serper.dev (wrapper, tests, docs, … (#909)
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'
```
2023-02-15 22:47:17 -08:00
Ankush Gola
caa8e4742e
Enable streaming for OpenAI LLM (#986)
* Support a callback `on_llm_new_token` that users can implement when
`OpenAI.streaming` is set to `True`
2023-02-14 15:06:14 -08:00
Harrison Chase
88bebb4caa
Harrison/llm integrations (#1039)
Co-authored-by: jped <jonathanped@gmail.com>
Co-authored-by: Justin Torre <justintorre75@gmail.com>
Co-authored-by: Ivan Vendrov <ivan@anthropic.com>
2023-02-13 22:06:25 -08:00
Harrison Chase
ec727bf166
Align table info (#999) (#1034)
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>
2023-02-13 21:48:41 -08:00
Enrico Shippole
f30dcc6359
Add GooseAI, CerebriumAI, Petals, ForefrontAI (#981)
Add GooseAI, CerebriumAI, Petals, ForefrontAI
2023-02-13 21:20:19 -08:00
Anton Troynikov
d43d430d86
Chroma persistence (#1028)
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.
2023-02-13 21:09:06 -08:00
Anton Troynikov
78abd277ff
Chroma in LangChain (#1010)
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!
2023-02-12 17:43:48 -08:00
Shahriar Tajbakhsh
b7747017d7
Import of declarative_base when SQLAlchemy <1.4 (#883)
In
[pyproject.toml](https://github.com/hwchase17/langchain/blob/master/pyproject.toml),
the expectation is `SQLAlchemy = "^1"`. But, the way `declarative_base`
is imported in
[cache.py](https://github.com/hwchase17/langchain/blob/master/langchain/cache.py)
will only work with SQLAlchemy >=1.4. This PR makes sure Langchain can
be run in environments with SQLAlchemy <1.4
2023-02-10 18:33:47 -08:00
Harrison Chase
c64f98e2bb
Harrison/format agent instructions (#973)
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>
2023-02-10 10:07:26 -08:00
Harrison Chase
91c6cea227
Harrison/batch embeds (#972)
Co-authored-by: John Dagdelen <jdagdelen@users.noreply.github.com>
Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>
2023-02-10 06:59:50 -08:00
Ankush Gola
bc7e56e8df
Add asyncio support for LLM (OpenAI), Chain (LLMChain, LLMMathChain), and Agent (#841)
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)
2023-02-07 21:21:57 -08:00
Harrison Chase
bc53c928fc
Harrison/athropic (#921)
Co-authored-by: Mike Lambert <mlambert@gmail.com>
Co-authored-by: mrbean <sam@you.com>
Co-authored-by: mrbean <43734688+sam-h-bean@users.noreply.github.com>
Co-authored-by: Ivan Vendrov <ivendrov@gmail.com>
2023-02-06 22:29:25 -08:00
Harrison Chase
1e56879d38
Harrison/save faiss (#916)
Co-authored-by: Shrey Joshi <shreyjoshi2004@gmail.com>
2023-02-06 21:44:50 -08:00
Harrison Chase
e2b834e427
Harrison/prompt template prefix (#888)
Co-authored-by: Gabriel Simmons <simmons.gabe@gmail.com>
2023-02-06 19:09:28 -08:00
Harrison Chase
f95cedc443
Harrison/sql rows (#915)
Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>
2023-02-06 18:56:18 -08:00
Harrison Chase
ba5a2f06b9
Harrison/inference endpoint (#861)
Co-authored-by: Eno Reyes <enoreyes@gmail.com>
2023-02-06 18:14:25 -08:00
Kevin Huo
31b054f69d
Add pinecone integration test (#911)
Basic integration test for pinecone
2023-02-06 18:13:35 -08:00
Harrison Chase
93a091cfb8
Optionally return shell output on incorrect command (#894) (#899)
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>
2023-02-06 12:46:16 -08:00
Harrison Chase
a2b699dcd2
prompt template from string (#884) 2023-02-04 17:04:58 -08:00
Harrison Chase
8df6b68093
fix length based example selector (#862) 2023-02-02 22:06:56 -08:00
Harrison Chase
3f48eed5bd
Harrison/milvus (#856)
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>
2023-02-02 22:05:47 -08:00
kahkeng
4a8f5cdf4b
Add alternative token-based text splitter (#816)
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.
2023-02-02 19:55:13 -08:00
Harrison Chase
23d5f64bda
Harrison/ngram example (#846)
Co-authored-by: Sean Spriggens <ssprigge@syr.edu>
2023-02-02 09:44:42 -08:00
Harrison Chase
d564308e0f
rfc: instruct embeddings (#811)
Co-authored-by: seanaedmiston <seane999@gmail.com>
2023-02-02 08:44:02 -08:00
Harrison Chase
7b4882a2f4
Harrison/tf embeddings (#817)
Co-authored-by: Ryohei Kuroki <10434946+yakigac@users.noreply.github.com>
2023-01-31 00:00:08 -08:00
Jason Liu
54f9e4287f
Pass kwargs from initialize_agent into agent classmethod (#799)
# 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>
2023-01-30 14:54:09 -08:00
Roy Williams
6086292252
Centralize logic for loading from LangChainHub, add ability to pin dependencies (#805)
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
2023-01-30 14:52:17 -08:00
Harrison Chase
1ad7973cc6
Harrison/tool decorator (#790)
Co-authored-by: Jason Liu <jxnl@users.noreply.github.com>
Co-authored-by: Jason Liu <jason@jxnl.coA>
2023-01-28 18:26:24 -08:00
Harrison Chase
248c297f1b
Sample row in table info for SQLDatabase (#769) (#782)
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>
2023-01-28 13:37:07 -08:00
Amos Ng
6ad360bdef
Suggestions for better debugging (#765)
Please feel free to disregard any changes you disagree with
2023-01-28 08:05:20 -08:00
Ankush Gola
57609845df
add tracing support to langchain (#741)
* 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>
2023-01-26 17:38:13 -08:00
Amos Ng
fa6826e417
Fix sqlalchemy warnings when running tests (#733)
This has been bugging me when running my own tests that call langchain
methods :P
2023-01-25 07:14:07 -08:00
scadEfUr
e3df8ab6dc
move hyde into chains (#728)
Co-authored-by: scadEfUr <>
2023-01-24 22:23:32 -08:00
Harrison Chase
0ffeabd14f
Harrison/serialize llm chain (#671) 2023-01-24 21:36:19 -08:00
Harrison Chase
cbc146720b
verbose flag (#683) 2023-01-22 12:44:14 -08:00
dham
e04b063ff4
add faiss local saving/loading (#676)
- 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
2023-01-21 16:08:14 -08:00
Harrison Chase
a2eeaf3d43
strip whitespace (#680) 2023-01-21 16:03:48 -08:00
Harrison Chase
0b204d8c21
Harrison/quadrant (#665)
Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com>
2023-01-20 09:45:01 -08:00
Harrison Chase
54d7f1c933
fix caching (#658) 2023-01-19 15:33:45 -08:00
Harrison Chase
4d4cff0530
Harrison/cohere experimental (#638)
Co-authored-by: inyourhead <44607279+xettrisomeman@users.noreply.github.com>
2023-01-17 22:28:55 -08:00
Harrison Chase
1ac3319e45
simplify parsing of the final answer (#621) 2023-01-15 16:39:27 -08:00
Harrison Chase
ffc7e04d44
Harrison/wolfram alpha (#579)
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
2023-01-11 05:52:19 -08:00
Harrison Chase
1511606799
Harrison/fix splitting (#563)
fix issue where text splitting could possibly create empty docs
2023-01-08 19:19:32 -08:00
Harrison Chase
1192cc0767
smart text splitter (#530)
smart text splitter that iteratively tries different separators until it
works!
2023-01-08 15:11:10 -08:00
Harrison Chase
9833fcfe32
fix caching (#555) 2023-01-06 07:30:10 -08:00
Harrison Chase
330a5b42d4
fix map reduce chain (#550) 2023-01-06 07:15:57 -08:00
Harrison Chase
4974f49bb7
add return_direct flag to tool (#537)
adds a return_direct flag to tools, which just returns the tool output
as the final output
2023-01-06 06:40:32 -08:00
Harrison Chase
1631981f84
Harrison/fix and test caching (#538) 2023-01-04 18:39:06 -08:00
Harrison Chase
9e04c34e20
Add BaseCallbackHandler and CallbackManager (#478)
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
2023-01-04 07:54:25 -08:00
Harrison Chase
0db05b6725
Harrison/add human prefix (#520)
Co-authored-by: Andrew Huang <jhuang16888@gmail.com>
2023-01-03 08:03:50 -08:00
Harrison Chase
985496f4be
Docs refactor (#480)
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>
2023-01-02 08:24:09 -08:00
Harrison Chase
0072686aab
Harrison/new search engine (#477)
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
2022-12-30 08:06:57 -05:00
Harrison Chase
d0f194de73
add logic for agent stopping (#420) 2022-12-29 08:21:11 -05:00
Harrison Chase
95157d0aad
Add schema property to sql database utility class (#448) (#462)
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>
2022-12-28 17:37:53 -05:00
Harrison Chase
0c5d3fd894
version 0.0.49 (#436) 2022-12-27 09:17:01 -05:00
Harrison Chase
f8b605293f
Harrison/improve memory (#432)
add AI prefix

add new type of memory

Co-authored-by: Jason <chisanch@usc.edu>
2022-12-27 08:23:51 -05:00
Harrison Chase
ee3b8e89b3
better parsing of agent output (#418) 2022-12-25 09:53:36 -05:00
Harrison Chase
20959d8c36
check memory variables (#411)
can have multiple input keys, if some come from memory
2022-12-24 08:35:46 -05:00
Harrison Chase
6b60c509ac
(WIP) add HyDE (#393)
Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>
2022-12-21 20:46:41 -05:00
Harrison Chase
c104d507bf
Harrison/improve data augmented generation docs (#390)
Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>
2022-12-20 22:24:08 -05:00
Harrison Chase
cf98f219f9
Harrison/tools exp (#372) 2022-12-18 21:51:23 -05:00
Harrison Chase
e7b625fe03
fix text splitter (#375) 2022-12-18 20:21:43 -05:00
Harrison Chase
3474f39e21
Harrison/improve cache (#368)
make it so everything goes through generate, which removes the need for
two types of caches
2022-12-18 16:22:42 -05:00
Ankush Gola
8d0869c6d3
change run to use args and kwargs (#367)
Before, `run` was not able to be called with multiple arguments. This
expands the functionality.
2022-12-18 15:54:56 -05:00
Harrison Chase
a7084ad6e4
Harrison/version 0040 (#366) 2022-12-17 07:53:22 -08:00
mrbean
50257fce59
Support Streaming Tokens from OpenAI (#364)
https://github.com/hwchase17/langchain/issues/363

@hwchase17 how much does this make you want to cry?
2022-12-17 07:02:58 -08:00
mrbean
fe6695b9e7
Add HuggingFacePipeline LLM (#353)
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.
2022-12-17 07:00:04 -08:00
Harrison Chase
c1b50b7b13
Harrison/map reduce merge (#344)
Co-authored-by: John Nay <JohnNay@users.noreply.github.com>
2022-12-15 17:49:14 -08:00
Harrison Chase
78b31e5966
Harrison/cache (#343) 2022-12-15 07:53:32 -08:00
Harrison Chase
8cf62ce06e
Harrison/single input (#347)
allow passing of single input into chain

Co-authored-by: thepok <richterthepok@yahoo.de>
2022-12-15 07:52:51 -08:00
Harrison Chase
9bb7195085
Harrison/llm saving (#331)
Co-authored-by: Akash Samant <70665700+asamant21@users.noreply.github.com>
2022-12-13 06:46:01 -08:00
Hunter Gerlach
482611f426
unit test / code coverage improvements (#322)
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>
2022-12-13 05:48:53 -08:00
Shobith Alva
19a9fa16a9
Add clear() method for Memory (#305)
a simple helper to clear the buffer in `Conversation*Memory` classes
2022-12-11 07:09:06 -08:00
Harrison Chase
e02d6b2288
beta: logger (#307) 2022-12-10 23:17:19 -08:00
andersenchen
5267ebce2d
Add LLMCheckerChain (#281)
Implementation of https://github.com/jagilley/fact-checker. Works pretty
well.

<img width="993" alt="Screenshot 2022-12-07 at 4 41 47 PM"
src="https://user-images.githubusercontent.com/101075607/206302751-356a19ff-d000-4798-9aee-9c38b7f532b9.png">

Verifying this manually:
1. "Only two kinds of egg-laying mammals are left on the planet
today—the duck-billed platypus and the echidna, or spiny anteater."
https://www.scientificamerican.com/article/extreme-monotremes/
2. "An [Echidna] egg weighs 1.5 to 2 grams (0.05 to 0.07
oz)[[19]](https://en.wikipedia.org/wiki/Echidna#cite_note-19) and is
about 1.4 centimetres (0.55 in) long."
https://en.wikipedia.org/wiki/Echidna#:~:text=sleep%20is%20suppressed.-,Reproduction,a%20reptile%2Dlike%20egg%20tooth.
3. "A [platypus] lays one to three (usually two) small, leathery eggs
(similar to those of reptiles), about 11 mm (7⁄16 in) in diameter and
slightly rounder than bird eggs."
https://en.wikipedia.org/wiki/Platypus#:~:text=It%20lays%20one%20to%20three,slightly%20rounder%20than%20bird%20eggs.
4. Therefore, an Echidna is the mammal that lays the biggest eggs.


cc @hwchase17
2022-12-09 12:49:05 -08:00
Harrison Chase
3c1c7ba672
update branch name in gha (#274) 2022-12-06 22:28:50 -08:00
Akash Samant
48b093823e
Add a Transformation Chain (#257)
Arbitrary transformation chains that can be used to add dictionary
extractions from llms/other chains
2022-12-06 21:58:16 -08:00
coyotespike
b7bef36ee1
BashChain (#260)
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>
2022-12-06 21:57:50 -08:00
Harrison Chase
28be37f470
LLMRequestsChain (#267) 2022-12-06 21:55:02 -08:00
John McDonnell
68666d6a22
Gracefully degrade when model asks for nonexistent tool (#268)
Not yet tested, but very simple change, assumption is that we're cool
with just producing a generic output when tool is not found
2022-12-06 21:52:48 -08:00
Harrison Chase
f5c665a544
combine python files (#256) 2022-12-04 15:57:36 -08:00
Harrison Chase
db58032973
introduce output parser (#250) 2022-12-03 13:28:07 -08:00
Harrison Chase
a9ce04201f
Harrison/improve usability of api chain (#247)
improve usability of api chain
2022-12-02 15:44:10 -08:00
Harrison Chase
c897bd6cbd
api chain (#246)
Co-authored-by: Subhash Ramesh <33400216+thecooltechguy@users.noreply.github.com>
2022-12-02 13:39:36 -08:00
Xupeng (Tony) Tong
bb4bf9d6d0
chore: minor clean up / formatting (#233)
to get familiarize with the project
2022-12-01 10:50:36 -08:00
Harrison Chase
3ca2c8d6c5
allow passing of stop params into openai (#232) 2022-11-30 22:20:13 -08:00
Harrison Chase
ca2394028f
move search to not be a chain (#226) 2022-11-29 20:07:44 -08:00
Andrew Gleave
ea67c049f0
Support SQL statements that return no results (#222)
Adds support for statements such as insert, update etc which do not
return any rows.

`engine.execute` is deprecated and so execution has been updated to use
`connection.exec_driver_sql` as-per:


https://docs.sqlalchemy.org/en/14/core/connections.html#sqlalchemy.engine.Engine.execute
2022-11-29 08:28:45 -08:00
Akash Samant
d368c43648
Bug Fix (#221)
Quick bug fix for semantic similarity vector injection
2022-11-29 07:03:40 -08:00
Harrison Chase
1b9b8efbc9
pal chain (#207)
from https://arxiv.org/pdf/2211.10435.pdf
2022-11-28 21:38:34 -08:00
Harrison Chase
b94244eb12
nits (#210)
use json.dump

move test to integration tests (since it requires huggingface_hub)
2022-11-27 13:03:09 -08:00
Akash Samant
ae72cf84b8
Save Prompts (#194) 2022-11-27 09:10:35 -08:00
Bagatur
b90e25f786
Add HuggingFace Hub Embeddings (#125)
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
2022-11-27 00:24:59 -08:00
Harrison Chase
6eab5254e5
add docs for custom agents (#196) 2022-11-26 06:03:08 -08:00
Harrison Chase
08deed9002
Harrison/memory docs (#195)
update memory docs and change variables
2022-11-26 05:58:54 -08:00
Harrison Chase
b913df3774
make attrs public (#187)
since they are used outside of the class, should be public
2022-11-24 20:11:29 -08:00
Harrison Chase
ae9c6257fe
Harrison/arbitrary params (#186) 2022-11-24 20:01:20 -08:00
Samantha Whitmore
a408ed3ea3
Samantha/add conversation chain (#166)
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>
2022-11-23 16:35:38 -08:00
Harrison Chase
4334ffa6f9
Harrison/clean up language (#179)
dynamic prompts are no longer a thing
2022-11-23 16:58:41 -05:00
Samantha Whitmore
09f301cd38
Add add_example method to all ExampleSelector classes, with tests (#178)
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)
2022-11-23 13:12:47 -08:00
Harrison Chase
d3a7429f61
(WIP) agents (#171) 2022-11-22 06:16:26 -08:00
Harrison Chase
4a4dfbfbed
Harrison/sequential chains (#168)
add support for basic sequential chains
2022-11-21 13:08:53 -08:00
Samantha Whitmore
315b0c09c6
wip: add method for both docstore and embeddings (#119)
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>
2022-11-20 16:23:58 -08:00
Harrison Chase
c02eb199b6
add few shot example (#148) 2022-11-19 20:32:45 -08:00
Nicholas Larus-Stone
0c3ae78ec1
chore: update ascii colors to work with dark mode (#152) 2022-11-16 22:05:28 -08:00
Nicholas Larus-Stone
ca4b10bb74
feat: add option to ignore or restrict to SQL tables (#151)
`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
2022-11-16 22:04:50 -08:00
Harrison Chase
1835e8a681
prompt nit (#141)
doing some cleanup, and i think this just simplifies things...
2022-11-14 21:30:33 -08:00
Harrison Chase
bbb405a492
update colors (#140) 2022-11-14 20:27:36 -08:00
Harrison Chase
9f223e6ccc
Harrison/fix lint (#138) 2022-11-14 08:55:59 -08:00
Delip Rao
76cecf8165
A fix for Jupyter environment variable issue (#135)
- fixes the Jupyter environment variable issues mentioned in issue #134 
- fixes format/lint issues in some unrelated files (from make
format/lint)


![image](https://user-images.githubusercontent.com/347398/201599322-090af858-362d-4d69-bf59-208aea65419a.png)
2022-11-14 08:34:01 -08:00
Harrison Chase
f23b3ceb49
consolidate run functions (#126)
consolidating logic for when a chain is able to run with single input
text, single output text

open to feedback on naming, logic, usefulness
2022-11-13 18:14:35 -08:00
Edmar Ferreira
8a5ec894e7
Prompt from file proof of concept using plain text (#127)
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.
2022-11-13 13:15:30 -08:00
Harrison Chase
d87e73ddb1
huggingface tokenizer (#75) 2022-11-13 09:37:44 -08:00
Harrison Chase
e43534d41c
add integration with manifest (#62) 2022-11-10 11:24:11 -08:00
tomeras91
d8734ce5ad
Add AI21 LLMs (#99)
Integrate AI21 /complete API into langchain, to allow access to Jurassic
models.
2022-11-10 08:12:28 -08:00
Samantha Whitmore
a0780cc930
OptimizedPrompt -- k-shot example choice backed by semantic search (#91) 2022-11-09 21:15:42 -08:00
Delip Rao
3ee6e332dd
Implements NLTK and Spacy-based TextSplitters (#103)
This PR is for Issue #88 

- [x] `make format`
- [x] `make lint`
- [x] `make tests`
2022-11-09 20:45:30 -08:00
issam9
28282ad099
Issam9/cohere embeddings (#105)
Add support for cohere embeddings
2022-11-09 13:44:27 -08:00
Delip Rao
95dd2f140e
Make Integration Tests "work" again (#106)
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?
2022-11-09 13:26:58 -08:00
Harrison Chase
db37bd089f
model laboratory (#95) 2022-11-08 22:17:10 -08:00
Harrison Chase
b9f61390e9
add text2text generation (#93)
fixes issue #90
2022-11-08 18:08:46 -08:00
Samantha Whitmore
efbc03bda8
NLPCloud client integration (#81)
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?
2022-11-08 06:24:23 -08:00
issam9
990cd821cc
Issam/hf embeddings (#68)
Add support of HuggingFace embedding models
2022-11-07 05:46:44 -08:00
Harrison Chase
eb36317f9a
Harrison/fix imports (#72)
fix imports and add section to notebook
2022-11-06 16:06:40 -08:00
Samantha Whitmore
a5b61d59e1
Refactor prompts into module, add example generation utils (#64) 2022-11-06 15:40:33 -08:00
Harrison Chase
2456a547de
mrkl (#42) 2022-11-05 14:41:53 -07:00
Samantha Whitmore
c636488fe5
DynamicPrompt class creation (#49)
Checking that this structure looks generally ok -- going to sub in logic
where the TODO comment is then add a test.
2022-11-05 12:43:21 -07:00
Harrison Chase
4cc18d6c2a
Harrison/pretty print (#57)
make stuff look nice
2022-11-03 00:41:07 -07:00
Harrison Chase
76aff023d7
FAISS and embedding support (#48)
also adds embeddings and an in memory docstore
2022-11-01 21:29:39 -07:00
Harrison Chase
e982cf4b2e
Harrison/update docstore (#47)
change docstore interface
2022-10-31 21:18:52 -07:00
Harrison Chase
160af4ba6b
Harrison/map reduce (#36) 2022-10-31 20:17:22 -07:00
Harrison Chase
fba30e07d1
factor out mock python repl (#43) 2022-10-30 18:09:04 -07:00
Harrison Chase
7b0d02ac51
prompt templating (#41)
Co-authored-by: Samantha Whitmore <whitmore.samantha@gmail.com>
2022-10-30 09:45:27 -07:00
Harrison Chase
af81e9ca9c
add sql database (#35) 2022-10-27 23:21:47 -07:00
Harrison Chase
ce7b14b843
Harrison/add react chain (#24)
from https://arxiv.org/abs/2210.03629

still need to think if docstore abstraction makes sense
2022-10-26 21:02:23 -07:00
Harrison Chase
020c42dcae
Harrison/add huggingface hub (#23)
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
2022-10-25 22:00:33 -07:00
Harrison Chase
d2fdcba29d
fix test name (#22) 2022-10-25 20:22:16 -07:00
Harrison Chase
1ef3ab4d0e
Harrison/add natbot (#18) 2022-10-24 19:56:26 -07:00
Harrison Chase
18aeb72012 initial commit 2022-10-24 14:51:15 -07:00