Commit Graph

1467 Commits

Author SHA1 Message Date
Harrison Chase
1271c00ff0
Harrison/openapi planner (#2692)
Co-authored-by: Adam McCabe <adam.r.mccabe@gmail.com>
2023-04-10 21:22:42 -07:00
Harrison Chase
e0a13e9355
Harrison/postgres (#2691)
Co-authored-by: Ankit Jain <ankneo@users.noreply.github.com>
2023-04-10 21:15:42 -07:00
Guohao Li
bb5118f4c9
Add notebook example for camel role playing (#2689)
This PR adds a LangChain implementation of CAMEL role-playing example:
https://github.com/lightaime/camel.

I am sorry that I am not that familiar with LangChain. So I only
implement it in a naive way. There may be a better way to implement it.
2023-04-10 21:12:45 -07:00
Harrison Chase
d3f779d61d
baby agi agent (#2648)
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>
2023-04-10 21:03:30 -07:00
Naveen Tatikonda
4364d3316e
Add custom vector fields and text fields for OpenSearch (#2652)
**Description**
Add custom vector field name and text field name while indexing and
querying for OpenSearch

**Issues**
https://github.com/hwchase17/langchain/issues/2500

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-04-10 21:02:02 -07:00
Pavel Shibanov
023de9a70b
Add OpenAIEmbeddings special token params for tiktoken (#2682)
#2681 

Original type hints
```python
allowed_special: Union[Literal["all"], AbstractSet[str]] = set(),  # noqa: B006
disallowed_special: Union[Literal["all"], Collection[str]] = "all",
```
from

46287bfa49/tiktoken/core.py (L79-L80)
are not compatible with pydantic

<img width="718" alt="image"
src="https://user-images.githubusercontent.com/5096640/230993236-c744940e-85fb-4baa-b9da-8b00fb60a2a8.png">

I think we could use
```python
allowed_special: Union[Literal["all"], Set[str]] = set()
disallowed_special: Union[Literal["all"], Set[str], Tuple[()]] = "all"
```

Please let me know if you would like to implement it differently.
2023-04-10 21:00:55 -07:00
Nikita Zavgorodnii
1c979e320d
docs: update tokenizer notice in llms/getting_started (#2641)
A tiny update in docs which is spotted here:
https://github.com/hwchase17/langchain/issues/2439
2023-04-10 20:55:45 -07:00
Yasin Tatar
9d20fd5135
add: conda installation instructions (#2678)
Hi, 

just wanted to mention that I added `langchain` to
[conda-forge](https://github.com/conda-forge/langchain-feedstock), so
that it can be installed with `conda`/`mamba` etc.
This makes it available to some corporate users with custom
conda-servers and people who like to manage their python envs with
conda.
2023-04-10 20:54:13 -07:00
vr140
28bef6f87d
Clean up OpenAI Embeddings to fix method name and comments (#2687)
**Problem:**

OpenAI Embeddings has a few minor issues: method name and comment for
_completion_with_retry seems to be a copypasta error and a few comments
around usage of embedding_ctx_length seem to be incorrect.

**Solution:**

Clean up issues.

---------

Co-authored-by: Vijay Rajaram <vrajaram3@gatech.edu>
2023-04-10 20:53:56 -07:00
Harrison Chase
ad3c5dd186
Harrison/databerry (#2688)
Co-authored-by: Georges Petrov <georgesm.petrov@gmail.com>
2023-04-10 18:49:47 -07:00
Filip Haltmayer
b286d0e63f
Adding milvus/zilliz into docs (#2686)
Adding Milvus and Zilliz to integrations.md and creating an ecosystems
doc for Zilliz.

Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
2023-04-10 18:08:41 -07:00
Sean Sheng
90d5328eda
docs: Update deployments.md to include a BentoML example (#2661)
Add a new deployment example with BentoML, see more
https://github.com/ssheng/BentoChain.
2023-04-10 14:57:32 -07:00
Tommertom
bd9f095ed2
Doc - Update google_search.ipynb - more explicit reference to places where to create API keys (#2670)
Took me a bit to find the proper places to get the API keys. The link
earlier provided to setup search is still good, but why not provide
direct link to the Google cloud tools that give you ability to create
keys?
2023-04-10 12:36:52 -07:00
Ankush Gola
e23a596a18
SqlDatabaseToolkit should have custom llm for QueryChecke… (#2676)
…rTool (#2655)

---------

Co-authored-by: Rushabh Agarwal <26388764+rushout09@users.noreply.github.com>
2023-04-10 11:43:24 -07:00
Ankush Gola
8d3b059332
Add docs for callbacks (#2643)
Basically copy what's in the ts docs:
https://js.langchain.com/docs/production/callbacks


Discovered a bug wrt not awaiting callbacks in `LLMMathChain` so fixed
that
2023-04-10 10:23:11 -07:00
Dmitri Melikyan
1931d4495e
Update Graphsignal ecosystem page (#2662)
Added/updated information due to new automatic data recording feature.
2023-04-10 08:00:26 -07:00
Harrison Chase
e63f9a846b
Harrison/docs agents (#2647) 2023-04-09 22:34:34 -07:00
Ankush Gola
b82cbd1be0
Use run and arun in place of combine_docs and acombine_docs (#2635)
`combine_docs` does not go through the standard chain call path which
means that chain callbacks won't be triggered, meaning QA chains won't
be traced properly, this fixes that.

Also fix several errors in the chat_vector_db notebook
2023-04-09 18:47:59 -07:00
Chetanya Rastogi
50c511d75f
Add new loader to load pdf as html content (#2607)
Adds a new pdf loader using the existing dependency on PDFMiner. 

The new loader can be helpful for chunking texts semantically into
sections as the output html content can be parsed via `BeautifulSoup` to
get more structured and rich information about font size, page numbers,
pdf headers/footers, etc. which may not be available otherwise with
other pdf loaders
2023-04-09 17:57:25 -07:00
Ankush Gola
61f7bd7a3a
fix question answering nb (#2637)
Was throwing exception bc `VectorIndexWrapper` did not have
`similarity_search` -- changed to just use retriever
2023-04-09 17:56:49 -07:00
William FH
10ff1fda8e
Add Streaming for GPT4All (#2642)
- Adds  support for callback handlers in GPT4All models
- Updates notebook and docs
2023-04-09 17:54:26 -07:00
Ankush Gola
c51753250d
Add async call to APIChain. (#2583) (#2644)
Co-authored-by: Yan <32036413+Yan-Zero@users.noreply.github.com>
2023-04-09 16:28:16 -07:00
William FH
e56673c7f9
BabyAGI Notebook Example (#2559)
Create a notebook implementing
[BabyAGI](https://github.com/yoheinakajima/babyagi/tree/main) by [Yohei
Nakajima](https://twitter.com/yoheinakajima) as LLM Chains.
2023-04-09 13:54:23 -07:00
Harrison Chase
7c1dd3057f cr 2023-04-09 13:10:46 -07:00
Harrison Chase
412397ad55
bump version to 136 (#2634) 2023-04-09 13:08:05 -07:00
Harrison Chase
7aba18ea77
Harrison/docs cleanup (#2633) 2023-04-09 12:55:22 -07:00
Jan
e57f0e38c1
Fix small typo in SemanticSimilarityExampleSelector (#2629) 2023-04-09 12:53:02 -07:00
Nick Gibb
63175eb696
Fix typo in docs (#2601)
Minor typo in the docs ("reccomended" -> "recommended")

Co-authored-by: Nick Gibb <nick.gibb@bluedot.global>
2023-04-09 12:52:35 -07:00
54b1645d13
fix: ReadTheDocs loader main content filter (#2609)
It seems the main element wrapper changed in ReadTheDocs website or for
some reason it's different for me ?

This adds an extra filter for the main content wrapper if the first one
returns no text.


![2023-04-09-043315_1178x873_scrot](https://user-images.githubusercontent.com/210457/230751369-24b69cb9-1601-4540-b5f3-d115165f55f6.jpg)

Co-authored-by: blob42 <spike@w530>
2023-04-09 12:51:56 -07:00
Davit Buniatyan
aaac7071a3
Deep Lake retriever example analyzing Twitter the-algorithm source code (#2602)
Improvements to Deep Lake Vector Store
- much faster view loading of embeddings after filters with
`fetch_chunks=True`
- 2x faster ingestion
- use np.float32 for embeddings to save 2x storage, LZ4 compression for
text and metadata storage (saves up to 4x storage for text data)
- user defined functions as filters

Docs
- Added retriever full example for analyzing twitter the-algorithm
source code with GPT4
- Added a use case for code analysis (please let us know your thoughts
how we can improve it)

---------

Co-authored-by: Davit Buniatyan <d@activeloop.ai>
2023-04-09 12:29:47 -07:00
William FH
5c0c5fafb2
Multi-Hop / Multi-Spec LLM Chain (#2549)
Add a notebook showing how to make a chain that composes multiple
OpenAPI Endpoint operations to accomplish tasks.
2023-04-09 12:29:16 -07:00
Jan
d2f8ddab10
Fix typo in PromptTemplate from_examples (#2628) 2023-04-09 12:28:50 -07:00
ecneladis
9a49f5763d
Add missing comma in async_agent.ipynb (#2614) 2023-04-09 12:28:28 -07:00
Jan
166624d005
Fix typo in error message (#2622) 2023-04-09 12:25:49 -07:00
Girish Sharma
9aed565f13
Fix missing import in AzureOpenAI embeddings example (#2625)
## Why this PR?

Fixes #2624
There's a missing import statement in AzureOpenAI embeddings example.

## What's new in this PR?

- Import `OpenAIEmbeddings` before creating it's object.

## How it's tested?
- By running notebook and creating embedding object.

Signed-off-by: letmerecall <girishsharma001@gmail.com>
2023-04-09 12:25:31 -07:00
Tommertom
0f5d3b3390
Typo docs - Update data_augmented_question_answering.ipynb propriterary-> proprietary (#2626)
Minor typo propritary -> proprietary
2023-04-09 12:24:53 -07:00
Nuno Campos
5376799a23
Allow recovering from JSONDecoder errors in StructuredOutputParser (#2616) 2023-04-09 07:32:49 -07:00
Nuno Campos
6f39e88a2c
Add AsyncIteratorCallbackHandler (#2329) 2023-04-08 14:34:55 -07:00
Harrison Chase
6e4e7d2637
bump version to 135 (#2600) 2023-04-08 13:46:35 -07:00
rkeshwani
5e57496225
#2595 ChromaDB: Add ability to adjust metadata for indexes upon creating co… (#2597)
Referencing #2595
Added optional default parameter to adjust index metadata upon
collection creation per chroma code

ce0bc89777/chromadb/api/local.py (L74)

Allowing for user to have the ability to adjust distance calculation
functions.
2023-04-08 13:31:17 -07:00
Harrison Chase
b9e5b27a99
Harrison/motorhead (#2599)
Co-authored-by: James O'Dwyer <100361543+softboyjimbo@users.noreply.github.com>
2023-04-08 13:27:20 -07:00
Johnny Lim
79a44c8225
Remove unnecessary question mark in link in README (#2589)
This PR removes an unnecessary question mark in link in the `README.md`
file.
2023-04-08 12:41:25 -07:00
Harrison Chase
2f49c96532
Harrison/redis (#2588)
Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>
2023-04-08 10:55:52 -07:00
Yuchu Luo
40469eef7f
fix temperature parameter not used in chat models (#2558) 2023-04-08 08:47:50 -07:00
Will Henchy
125afb51d7
Add shared Google Drive folder support (#2562)
closes #1634

Adds support for loading files from a shared Google Drive folder to
`GoogleDriveLoader`. Shared drives are commonly used by businesses on
their Google Workspace accounts (this is my particular use case).
2023-04-08 08:46:55 -07:00
Alex Rad
7bf5b0ccd3
RWKV: do not propagate model_state between calls (#2565)
RWKV is an RNN with a hidden state that is part of its inference.
However, the model state should not be carried across uses and it's a
bug to do so.

This resets the state for multiple invocations
2023-04-08 08:36:16 -07:00
Venky
7a4e1b72a8
Fix docs links (#2572)
Fix broken links in documentation.
2023-04-08 08:33:28 -07:00
Roy Xue
f5afb60116
doc: change comment with correct name (#2580)
In this comment, it should be **ConversationalRetrievalChain** instead
of **ChatVectorDBChain**
2023-04-08 08:31:33 -07:00
Shishin Mo
f7f118e021
use openai_organization as argument (#2566)
Added support for passing the openai_organization as an argument, as it
was only supported by the environment variable but openai_api_key was
supported by both environment variables and arguments.

`ChatOpenAI(temperature=0, model_name="gpt-4", openai_api_key="sk-****",
openai_organization="org-****")`
2023-04-07 22:02:02 -07:00
akmhmgc
544cc7f395
Modified doc (#2568)
# description
Remove unnecessary codes and made the output easier to check in docs :)
2023-04-07 22:01:53 -07:00