Commit Graph

113 Commits

Author SHA1 Message Date
Bagatur
7fa82900cb
guides docs nits (#10005) 2023-08-30 11:07:42 -07:00
Bagatur
98cce7dcd3
update moderation docs (#10002) 2023-08-30 10:34:25 -07:00
Bagatur
f7cc125cac
docs: memory types menu (#9949)
The [Memory
Types](https://python.langchain.com/docs/modules/memory/types/) menu is
clogged with unnecessary wording.
I've made it more concise by simplifying titles of the example
notebooks.
As results, menu is shorter and better for comprehend.
2023-08-29 15:05:23 -07:00
Bagatur
ede45f535e
fix intro docs (#9950) 2023-08-29 11:50:07 -07:00
leo-gan
7c7ae34eeb updated .mdx titles and text. 2023-08-29 11:33:30 -07:00
Piyush Jain
fe1b9ee6b8
Updated notebook for comprehend moderation (#9875)
### Description
Updated the notebook for comprehend moderation.

cc @baskaryan
2023-08-28 16:01:43 -07:00
Monami Sharma
12a373810c
Fixing broken links to Moderation and Constitutional chain (#9768)
- Description: Fixing broken links for Moderation and Constitutional
chain
  - Issue: N/A
  - Twitter handle: MonamiSharma
2023-08-25 15:19:32 -07:00
nikhilkjha
d57d08fd01
Initial commit for comprehend moderator (#9665)
This PR implements a custom chain that wraps Amazon Comprehend API
calls. The custom chain is aimed to be used with LLM chains to provide
moderation capability that let’s you detect and redact PII, Toxic and
Intent content in the LLM prompt, or the LLM response. The
implementation accepts a configuration object to control what checks
will be performed on a LLM prompt and can be used in a variety of setups
using the LangChain expression language to not only detect the
configured info in chains, but also other constructs such as a
retriever.
The included sample notebook goes over the different configuration
options and how to use it with other chains.

###  Usage sample
```python
from langchain_experimental.comprehend_moderation import BaseModerationActions, BaseModerationFilters

moderation_config = { 
        "filters":[ 
                BaseModerationFilters.PII, 
                BaseModerationFilters.TOXICITY,
                BaseModerationFilters.INTENT
        ],
        "pii":{ 
                "action": BaseModerationActions.ALLOW, 
                "threshold":0.5, 
                "labels":["SSN"],
                "mask_character": "X"
        },
        "toxicity":{ 
                "action": BaseModerationActions.STOP, 
                "threshold":0.5
        },
        "intent":{ 
                "action": BaseModerationActions.STOP, 
                "threshold":0.5
        }
}

comp_moderation_with_config = AmazonComprehendModerationChain(
    moderation_config=moderation_config, #specify the configuration
    client=comprehend_client,            #optionally pass the Boto3 Client
    verbose=True
)

template = """Question: {question}

Answer:"""

prompt = PromptTemplate(template=template, input_variables=["question"])

responses = [
    "Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.", 
    "Final Answer: This is a really shitty way of constructing a birdhouse. This is fucking insane to think that any birds would actually create their motherfucking nests here."
]
llm = FakeListLLM(responses=responses)

llm_chain = LLMChain(prompt=prompt, llm=llm)

chain = ( 
    prompt 
    | comp_moderation_with_config 
    | {llm_chain.input_keys[0]: lambda x: x['output'] }  
    | llm_chain 
    | { "input": lambda x: x['text'] } 
    | comp_moderation_with_config 
)

response = chain.invoke({"question": "A sample SSN number looks like this 123-456-7890. Can you give me some more samples?"})

print(response['output'])


```
### Output
```
> Entering new AmazonComprehendModerationChain chain...
Running AmazonComprehendModerationChain...
Running pii validation...
Found PII content..stopping..
The prompt contains PII entities and cannot be processed
```

---------

Co-authored-by: Piyush Jain <piyushjain@duck.com>
Co-authored-by: Anjan Biswas <anjanavb@amazon.com>
Co-authored-by: Jha <nikjha@amazon.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-25 15:11:27 -07:00
Lance Martin
2ab04a4e32
Update agent docs, move to use-case sub-directory (#9344)
Re-structure and add new agent page
2023-08-25 11:28:55 -07:00
Leonid Ganeline
cf792891f1
📖 docs: compact api reference (#8651)
Updated design of the "API Reference" text
Here is an example of the current format:

![image](https://github.com/langchain-ai/langchain/assets/2256422/8727f2ba-1b69-497f-aa07-07f939b6da3b)

It changed to
`langchain.retrievers.ElasticSearchBM25Retriever` format. The same
format as it is in the API Reference Toc.

It also resembles code: 
`from langchain.retrievers import ElasticSearchBM25Retriever` (namespace
THEN class_name)

Current format is
`ElasticSearchBM25Retriever from langchain.retrievers` (class_name THEN
namespace)

This change is in line with other formats and improves readability.

 @baskaryan
2023-08-24 09:01:52 -07:00
seamusp
25f2c82ae8
docs:misc fixes (#9671)
Improve internal consistency in LangChain documentation
- Change occurrences of eg and eg. to e.g.
- Fix headers containing unnecessary capital letters.
- Change instances of "few shot" to "few-shot".
- Add periods to end of sentences where missing.
- Minor spelling and grammar fixes.
2023-08-23 22:36:54 -07:00
Bagatur
d8e2dd4c89 mv 2023-08-23 11:30:44 -07:00
Aashish Saini
eb92da84a1
Fixings grammatical errors in Doc Files (#9647)
Fixing some typos and grammatical error is doc file.

@eyurtsev , @baskaryan 

Thanks

---------

Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com>
Co-authored-by: Ishita Chauhan <136303787+IshitaChauhanShortHillsAI@users.noreply.github.com>
2023-08-23 07:04:29 -07:00
Adilkhan Sarsen
f29312eb84
Fixing deeplake.mdx file as it uses outdates links (#9602)
deeplake.mdx was using old links and was not working properly, in the PR
we fix the issue.
2023-08-22 15:12:24 -07:00
Bagatur
d09cdb4880
update data connection -> retrieval (#9561) 2023-08-21 13:03:29 -07:00
Harrison Chase
9930ddc555
beef up retrieval docs (#9518) 2023-08-21 07:22:22 -07:00
Lance Martin
589927e9e1
Update figure in OSS model guide (#9399) 2023-08-17 15:09:21 -07:00
AbhishekYadavShorthillsAI
90d7c55343
Fix Typo in "community.md" (#9360)
Corrected a typographical error in the "community.md" file by removing
an extra word from the sentence.

@baskaryan , @hwchase17
2023-08-17 01:54:13 -07:00
Lance Martin
b04e472acf
Open source LLM guide (#9266)
Guide for using open source LLMs locally.
2023-08-16 16:18:31 -07:00
Bagatur
bfbb97b74c
Bagatur/deeplake docs fixes (#9275)
Co-authored-by: adilkhan <adilkhan.sarsen@nu.edu.kz>
2023-08-15 15:56:36 -07:00
Bagatur
a8aa1aba1c
nit (#9243) 2023-08-15 00:49:12 -07:00
Bagatur
68d8f73698
consolidate redirects (#9242) 2023-08-15 00:48:23 -07:00
Lance Martin
41279a3ae1
Move self-check use case to "more" section (#9137)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-14 18:27:28 -07:00
Lance Martin
22858d99b5
Move code-writing use case to "more" section (#9134)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-14 18:27:19 -07:00
Lance Martin
969e1683de
Move graph use case to "more" section (#8997)
Clean `use_cases` by moving the `GraphDB` to `integrations`.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-14 17:20:38 -07:00
Aashish Saini
0aabded97f
Updating interactive walkthrough link in index.md to resolve 404 error (#9063)
Updated interactive walkthrough link in index.md to resolve 404 error.
Also, expressing deep gratitude to LangChain library developers for
their exceptional efforts 🥇 .

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-11 13:08:56 -07:00
Hai The Dude
e4418d1b7e
Added new use case docs for Web Scraping, Chromium loader, BS4 transformer (#8732)
- Description: Added a new use case category called "Web Scraping", and
a tutorial to scrape websites using OpenAI Functions Extraction chain to
the docs.
  - Tag maintainer:@baskaryan @hwchase17 ,
- Twitter handle: https://www.linkedin.com/in/haiphunghiem/ (I'm on
LinkedIn mostly)

---------

Co-authored-by: Lance Martin <lance@langchain.dev>
2023-08-11 11:46:59 -07:00
Manuel Soria
31cfc00845
Code understanding use case (#8801)
Code understanding docs

---------

Co-authored-by: Manuel Soria <manuel.soria@greyscaleai.com>
Co-authored-by: Lance Martin <lance@langchain.dev>
2023-08-11 10:16:05 -07:00
Francisco Ingham
9249d305af
tagging docs refactor (#8722)
refactor of tagging use case according to new format

---------

Co-authored-by: Lance Martin <lance@langchain.dev>
2023-08-11 08:06:07 -07:00
Nicolas
e3fb11bc10
docs: (Mendable Search) Fixes stuck when tabbing out issue (#9074)
This fixes Mendable not completing when tabbing out and fixes the
duplicate message issue as well.
2023-08-10 13:46:06 -07:00
Bagatur
1edead28b8
Add docs community page (#8992)
Co-authored-by: briannawolfson <brianna.wolfson@gmail.com>
2023-08-10 13:41:35 -07:00
Aashish Saini
8a320e55a0
Corrected grammatical errors and spelling mistakes in the index.mdx file. (#9026)
Expressing gratitude to the creator for crafting this remarkable
application. 🙌, Would like to Enhance grammar and spelling in the
documentation for a polished reader experience.

Your feedback is valuable as always 

@baskaryan , @hwchase17 , @eyurtsev
2023-08-10 10:17:09 -07:00
Lance Martin
2380492c8e
API use case (#8546)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-10 07:52:54 -07:00
Michael Shen
c2f46b2cdb
Fixed wrong paper reference (#8970)
The ReAct reference references to MRKL paper. Corrected so that it
points to the actual ReAct paper #8964.
2023-08-09 16:17:46 -04:00
arjunbansal
a2681f950d
add instructions on integrating Log10 (#8938)
- Description: Instruction for integration with Log10: an [open
source](https://github.com/log10-io/log10) proxiless LLM data management
and application development platform that lets you log, debug and tag
your Langchain calls
  - Tag maintainer: @baskaryan
  - Twitter handle: @log10io @coffeephoenix

Several examples showing the integration included
[here](https://github.com/log10-io/log10/tree/main/examples/logging) and
in the PR
2023-08-08 19:15:31 -07:00
Jeremy W
c5c0735fc4
Remove Evaluation from Modules page (#8926)
Remove Evaluation link (which gives 404 now) from Modules page, since it
lives under Guides page now
2023-08-08 10:20:24 -07:00
Jacob Lee
d1e305028f
Automatically set docs appearance to system default (#8924)
@baskaryan
2023-08-08 09:54:18 -07:00
Manuel Soria
e74a605379
SQL use case docs (#8513) 2023-08-08 03:30:18 -07:00
Nicolas
b57fa1a39c
docs: Improvements on Mendable Search (#8808)
- Balancing prioritization between keyword / AI search
- Show snippets of highlighted keywords when searching 
- Improved keyword search
- Fixed bugs and issues

Shoutout to @calebpeffer for implementing and gathering feedback on it 

cc: @dev2049 @rlancemartin @hwchase17
2023-08-06 15:32:06 -07:00
Francisco Ingham
ef5bc1fef1
Refactor for extraction docs (#8465)
Refactor for the extraction use case documentation

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Lance Martin <lance@langchain.dev>
2023-08-05 10:09:14 -07:00
Eugene Yurtsev
19dfe166c9
Update documentation for prompts (#8381)
* Documentation to favor creation without declaring input_variables
* Cut out obvious examples, but add more description in a few places

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2023-08-04 14:25:03 -07:00
Lance Martin
be638ad77d
Chatbots use case (#8554)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-04 07:02:14 -07:00
Lance Martin
37aade19da
Minor formatting and additional figure for summarization use case (#8663) 2023-08-02 21:52:29 -07:00
millerick
5018af8839
docs: fix some grammar (#8654)
### Description
Fixes a grammar issue I noticed when reading through the documentation.

### Maintainers
@baskaryan

Co-authored-by: mmillerick <mmillerick@blend.com>
2023-08-02 16:48:01 -07:00
Lance Martin
59194c2214
Add summarization use-case (#8376)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-02 14:25:11 -07:00
Bagatur
73072d3db8
mv (#8595) 2023-08-01 14:17:04 -07:00
Bharat Raghunathan
c19a0b9c10
doc(prompts): Follow up on broken Prompt Sublink pages (#8530)
- Description: Follow up of #8478  
  - Issue: #8477
  - Dependencies: None
  - Tag maintainer: @baskaryan
  - Twitter handle: [@BharatR123](twitter.com/BharatR123)

The links were still broken after #8478 and sadly the issue was not
caught with either the Vercel app build and `make docs_linkcheck`
2023-07-31 16:46:13 -07:00
Bharat Raghunathan
04ebdbe98f
doc(prompts): Add redirects in Prompt subcategories pages (#8478)
- Description: Fixes broken links in some Prompts subcategories in
documentation (Example Selectors, Prompt Templates)
  - Issue: #8477 (Fixes #8477)
  - Dependencies: None
  - Tag maintainer: @baskaryan
  - Twitter handle: [@BharatR123](https://twitter.com/BharatR123)
2023-07-30 19:38:52 -07:00
Harrison Chase
490ad93b3c
fix links generation (#8471) 2023-07-29 18:31:33 -07:00
Harrison Chase
412fa4e1db
add guide notebook (#8258)
<!-- 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!

Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

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
 -->

---------

Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2023-07-29 09:42:59 -07:00