Squashed from #7454 with updated features
We have separated the `SQLDatabseChain` from `VectorSQLDatabseChain` and
put everything into `experimental/`.
Below is the original PR message from #7454.
-------
We have been working on features to fill up the gap among SQL, vector
search and LLM applications. Some inspiring works like self-query
retrievers for VectorStores (for example
[Weaviate](https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/weaviate_self_query.html)
and
[others](https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query.html))
really turn those vector search databases into a powerful knowledge
base! 🚀🚀
We are thinking if we can merge all in one, like SQL and vector search
and LLMChains, making this SQL vector database memory as the only source
of your data. Here are some benefits we can think of for now, maybe you
have more 👀:
With ALL data you have: since you store all your pasta in the database,
you don't need to worry about the foreign keys or links between names
from other data source.
Flexible data structure: Even if you have changed your schema, for
example added a table, the LLM will know how to JOIN those tables and
use those as filters.
SQL compatibility: We found that vector databases that supports SQL in
the marketplace have similar interfaces, which means you can change your
backend with no pain, just change the name of the distance function in
your DB solution and you are ready to go!
### Issue resolved:
- [Feature Proposal: VectorSearch enabled
SQLChain?](https://github.com/hwchase17/langchain/issues/5122)
### Change made in this PR:
- An improved schema handling that ignore `types.NullType` columns
- A SQL output Parser interface in `SQLDatabaseChain` to enable Vector
SQL capability and further more
- A Retriever based on `SQLDatabaseChain` to retrieve data from the
database for RetrievalQAChains and many others
- Allow `SQLDatabaseChain` to retrieve data in python native format
- Includes PR #6737
- Vector SQL Output Parser for `SQLDatabaseChain` and
`SQLDatabaseChainRetriever`
- Prompts that can implement text to VectorSQL
- Corresponding unit-tests and notebook
### Twitter handle:
- @MyScaleDB
### Tag Maintainer:
Prompts / General: @hwchase17, @baskaryan
DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
### Dependencies:
No dependency added
# Description
This pull request allows to use the
[NucliaDB](https://docs.nuclia.dev/docs/docs/nucliadb/intro) as a vector
store in LangChain.
It works with both a [local NucliaDB
instance](https://docs.nuclia.dev/docs/docs/nucliadb/deploy/basics) or
with [Nuclia Cloud](https://nuclia.cloud).
# Dependencies
It requires an up-to-date version of the `nuclia` Python package.
@rlancemartin, @eyurtsev, @hinthornw, please review it when you have a
moment :)
Note: our Twitter handler is `@NucliaAI`
This PR replaces the generic `SET search_path TO` statement by `USE` for
the Trino dialect since Trino does not support `SET search_path`.
Official Trino documentation can be found
[here](https://trino.io/docs/current/sql/use.html).
With this fix, the `SQLdatabase` will now be able to set the current
schema and execute queries using the Trino engine. It will use the
catalog set as default by the connection uri.
- Description: Remove hardcoded/duplicated distance strategies in the
PGVector store.
- Issue: NA
- Dependencies: NA
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: @archmonkeymojo
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
I have updated the code to ensure consistent error handling for
ImportError. Instead of relying on ValueError as before, I've followed
the standard practice of raising ImportError while also including
detailed error messages. This modification improves code clarity and
explicitly indicates that any issues are related to module imports.
`mypy` cannot type-check code that relies on dependencies that aren't
installed.
Eventually we'll probably want to install as many optional dependencies
as possible. However, the full "extended deps" setup for langchain
creates a 3GB cache file and takes a while to unpack and install. We'll
probably want something a bit more targeted.
This is a first step toward something better.
A test file was accidentally dropping a `results.json` file in the
current working directory as a result of running `make test`.
This is undesirable, since we don't want to risk accidentally adding
stray files into the repo if we run tests locally and then do `git add
.` without inspecting the file list very closely.
Makes it easier to do recursion using regular python compositional
patterns
```py
def lambda_decorator(func):
"""Decorate function as a RunnableLambda"""
return runnable.RunnableLambda(func)
@lambda_decorator
def fibonacci(a, config: runnable.RunnableConfig) -> int:
if a <= 1:
return a
else:
return fibonacci.invoke(
a - 1, config
) + fibonacci.invoke(a - 2, config)
fibonacci.invoke(10)
```
https://smith.langchain.com/public/cb98edb4-3a09-4798-9c22-a930037faf88/r
Also makes it more natural to do things like error handle and call other
langchain objects in ways we probably don't want to support in
`with_fallbacks()`
```py
@lambda_decorator
def handle_errors(a, config: runnable.RunnableConfig) -> int:
try:
return my_chain.invoke(a, config)
except MyExceptionType as exc:
return my_other_chain.invoke({"original": a, "error": exc}, config)
```
In this case, the next chain takes in the exception object. Maybe this
could be something we toggle in `with_fallbacks` but I fear we'll get
into uglier APIs + heavier cognitive load if we try to do too much there
---------
Co-authored-by: Nuno Campos <nuno@boringbits.io>
- Description: Fix bug in SPARQL intent selection
- Issue: After the change in #7758 the intent is always set to "UPDATE".
Indeed, if the answer to the prompt contains only "SELECT" the
`find("SELECT")` operation returns a higher value w.r.t. `-1` returned
by `find("UPDATE")`.
- Dependencies: None,
- Tag maintainer: @baskaryan @aditya-29
- Twitter handle: @mario_scrock
Text Generation Inference's client permits the use of a None temperature
as seen
[here](033230ae66/clients/python/text_generation/client.py (L71C9-L71C20)).
While I haved dived into TGI's server code and don't know about the
implications of using None as a temperature setting, I think we should
grant users the option to pass None as a temperature parameter to TGI.
#9304 introduced a critical bug. The S3DirectoryLoader fails completely
because boto3 checks the naming of kw arguments and one of the args is
badly named (very sorry for that)
cc @baskaryan
Changes in:
- `create_sql_agent` function so that user can easily add custom tools
as complement for the toolkit.
- updating **sql use case** notebook to showcase 2 examples of extra
tools.
Motivation for these changes is having the possibility of including
domain expert knowledge to the agent, which improves accuracy and
reduces time/tokens.
---------
Co-authored-by: Manuel Soria <manuel.soria@greyscaleai.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
## Description
### Issue
This pull request addresses a lingering issue identified in PR #7070. In
that previous pull request, an attempt was made to address the problem
of empty embeddings when using the `OpenAIEmbeddings` class. While PR
#7070 introduced a mechanism to retry requests for embeddings, it didn't
fully resolve the issue as empty embeddings still occasionally
persisted.
### Problem
In certain specific use cases, empty embeddings can be encountered when
requesting data from the OpenAI API. In some cases, these empty
embeddings can be skipped or removed without affecting the functionality
of the application. However, they might not always be resolved through
retries, and their presence can adversely affect the functionality of
applications relying on the `OpenAIEmbeddings` class.
### Solution
To provide a more robust solution for handling empty embeddings, we
propose the introduction of an optional parameter, `skip_empty`, in the
`OpenAIEmbeddings` class. When set to `True`, this parameter will enable
the behavior of automatically skipping empty embeddings, ensuring that
problematic empty embeddings do not disrupt the processing flow. The
developer will be able to optionally toggle this behavior if needed
without disrupting the application flow.
## Changes Made
- Added an optional parameter, `skip_empty`, to the `OpenAIEmbeddings`
class.
- When `skip_empty` is set to `True`, empty embeddings are automatically
skipped without causing errors or disruptions.
### Example Usage
```python
from openai.embeddings import OpenAIEmbeddings
# Initialize the OpenAIEmbeddings class with skip_empty=True
embeddings = OpenAIEmbeddings(api_key="your_api_key", skip_empty=True)
# Request embeddings, empty embeddings are automatically skipped. docs is a variable containing the already splitted text.
results = embeddings.embed_documents(docs)
# Process results without interruption from empty embeddings
```
- Description:
Add a 'download_dir' argument to VLLM model (to change the cache
download directotu when retrieving a model from HF hub)
- Issue:
On some remote machine, I want the cache dir to be in a volume where I
have space (models are heavy nowadays). Sometimes the default HF cache
dir might not be what we want.
- Dependencies:
None
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
I have restructured the code to ensure uniform handling of ImportError.
In place of previously used ValueError, I've adopted the standard
practice of raising ImportError with explanatory messages. This
modification enhances code readability and clarifies that any problems
stem from module importation.
---------
Co-authored-by: Aashish Saini <141953346+AashishSainiShorthillsAI@users.noreply.github.com>
Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com>
Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: ChetnaGuptaShorthillsAI <142381084+ChetnaGuptaShorthillsAI@users.noreply.github.com>
Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com>
Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com>
Co-authored-by: AnujMauryaShorthillsAI <142393269+AnujMauryaShorthillsAI@users.noreply.github.com>
Previous PR #9353 has incomplete type checks and deprecation warnings.
This PR will fix those type check and add deprecation warning to myscale
vectorstore
(Reopen PR #7706, hope this problem can fix.)
When using `pdfplumber`, some documents may be parsed incorrectly,
resulting in **duplicated characters**.
Taking the
[linked](https://bruusgaard.no/wp-content/uploads/2021/05/Datasheet1000-series.pdf)
document as an example:
## Before
```python
from langchain.document_loaders import PDFPlumberLoader
pdf_file = 'file.pdf'
loader = PDFPlumberLoader(pdf_file)
docs = loader.load()
print(docs[0].page_content)
```
Results:
```
11000000 SSeerriieess
PPoorrttaabbllee ssiinnggllee ggaass ddeetteeccttoorrss ffoorr HHyyddrrooggeenn aanndd CCoommbbuussttiibbllee ggaasseess
TThhee RRiikkeenn KKeeiikkii GGPP--11000000 iiss aa ccoommppaacctt aanndd
lliigghhttwweeiigghhtt ggaass ddeetteeccttoorr wwiitthh hhiigghh sseennssiittiivviittyy ffoorr
tthhee ddeetteeccttiioonn ooff hhyyddrrooccaarrbboonnss.. TThhee mmeeaassuurreemmeenntt
iiss ppeerrffoorrmmeedd ffoorr tthhiiss ppuurrppoossee bbyy mmeeaannss ooff ccaattaallyyttiicc
sseennssoorr.. TThhee GGPP--11000000 hhaass aa bbuuiilltt--iinn ppuummpp wwiitthh
ppuummpp bboooosstteerr ffuunnccttiioonn aanndd aa ddiirreecctt sseelleeccttiioonn ffrroomm
aa lliisstt ooff 2255 hhyyddrrooccaarrbboonnss ffoorr eexxaacctt aalliiggnnmmeenntt ooff tthhee
ttaarrggeett ggaass -- OOnnllyy ccaalliibbrraattiioonn oonn CCHH iiss nneecceessssaarryy..
44
FFeeaattuurreess
TThhee RRiikkeenn KKeeiikkii 110000vvvvttaabbllee ssiinnggllee HHyyddrrooggeenn aanndd
CCoommbbuussttiibbllee ggaass ddeetteeccttoorrss..
TThheerree aarree 33 ssttaannddaarrdd mmooddeellss::
GGPP--11000000:: 00--1100%%LLEELL // 00--110000%%LLEELL ›› LLEELL ddeetteeccttoorr
NNCC--11000000:: 00--11000000ppppmm // 00--1100000000ppppmm ›› PPPPMM
ddeetteeccttoorr
DDiirreecctt rreeaaddiinngg ooff tthhee ccoonncceennttrraattiioonn vvaalluueess ooff
ccoommbbuussttiibbllee ggaasseess ooff 2255 ggaasseess ((55 NNPP--11000000))..
EEaassyy ooppeerraattiioonn ffeeaattuurree ooff cchhaannggiinngg tthhee ggaass nnaammee
ddiissppllaayy wwiitthh 11 sswwiittcchh bbuuttttoonn..
LLoonngg ddiissttaannccee ddrraawwiinngg ppoossssiibbllee wwiitthh tthhee ppuummpp
bboooosstteerr ffuunnccttiioonn..
VVaarriioouuss ccoommbbuussttiibbllee ggaasseess ccaann bbee mmeeaassuurreedd bbyy tthhee
ppppmm oorrddeerr wwiitthh NNCC--11000000..
www.bruusgaard.no postmaster@bruusgaard.no +47 67 54 93 30 Rev: 446-2
```
We can see that there are a large number of duplicated characters in the
text, which can cause issues in subsequent applications.
## After
Therefore, based on the
[solution](https://github.com/jsvine/pdfplumber/issues/71) provided by
the `pdfplumber` source project. I added the `"dedupe_chars()"` method
to address this problem. (Just pass the parameter `dedupe` to `True`)
```python
from langchain.document_loaders import PDFPlumberLoader
pdf_file = 'file.pdf'
loader = PDFPlumberLoader(pdf_file, dedupe=True)
docs = loader.load()
print(docs[0].page_content)
```
Results:
```
1000 Series
Portable single gas detectors for Hydrogen and Combustible gases
The Riken Keiki GP-1000 is a compact and
lightweight gas detector with high sensitivity for
the detection of hydrocarbons. The measurement
is performed for this purpose by means of catalytic
sensor. The GP-1000 has a built-in pump with
pump booster function and a direct selection from
a list of 25 hydrocarbons for exact alignment of the
target gas - Only calibration on CH is necessary.
4
Features
The Riken Keiki 100vvtable single Hydrogen and
Combustible gas detectors.
There are 3 standard models:
GP-1000: 0-10%LEL / 0-100%LEL › LEL detector
NC-1000: 0-1000ppm / 0-10000ppm › PPM
detector
Direct reading of the concentration values of
combustible gases of 25 gases (5 NP-1000).
Easy operation feature of changing the gas name
display with 1 switch button.
Long distance drawing possible with the pump
booster function.
Various combustible gases can be measured by the
ppm order with NC-1000.
www.bruusgaard.no postmaster@bruusgaard.no +47 67 54 93 30 Rev: 446-2
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
I have restructured the code to ensure uniform handling of ImportError.
In place of previously used ValueError, I've adopted the standard
practice of raising ImportError with explanatory messages. This
modification enhances code readability and clarifies that any problems
stem from module importation.
---------
Co-authored-by: Aashish Saini <141953346+AashishSainiShorthillsAI@users.noreply.github.com>
Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com>
Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: ChetnaGuptaShorthillsAI <142381084+ChetnaGuptaShorthillsAI@users.noreply.github.com>
Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com>
Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com>
Co-authored-by: AnujMauryaShorthillsAI <142393269+AnujMauryaShorthillsAI@users.noreply.github.com>
- Implemented the MilvusTranslator for self-querying using Milvus vector
store
- Made unit tests to test its functionality
- Documented the Milvus self-querying
- Description: this PR adds the possibility to configure boto3 in the S3
loaders. Any named argument you add will be used to create the Boto3
session. This is useful when the AWS credentials can't be passed as env
variables or can't be read from the credentials file.
- Issue: N/A
- Dependencies: N/A
- Tag maintainer: ?
- Twitter handle: cbornet_
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR implements two new classes in the cache module: `CassandraCache`
and `CassandraSemanticCache`, similar in structure and functionality to
their Redis counterpart: providing a cache for the response to a
(prompt, llm) pair.
Integration tests are included. Moreover, linting and type checks are
all passing on my machine.
Dependencies: the `pyproject.toml` and `poetry.lock` have the newest
version of cassIO (the very same as in the Cassandra vector store
metadata PR, submitted as #9280).
If I may suggest, this issue and #9280 might be reviewed together (as
they bring the same poetry changes along), so I'm tagging @baskaryan who
already helped out a little with poetry-related conflicts there. (Thank
you!)
I'd be happy to add a short notebook if this is deemed necessary (but it
seems to me that, contrary e.g. to vector stores, caches are not covered
in specific notebooks).
Thank you!
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Enhance SerpApi response which potential to have more relevant output.
<img width="345" alt="Screenshot 2023-09-01 at 8 26 13 AM"
src="https://github.com/langchain-ai/langchain/assets/10222402/80ff684d-e02e-4143-b218-5c1b102cbf75">
Query: What is the weather in Pomfret?
**Before:**
> I should look up the current weather conditions.
...
Final Answer: The current weather in Pomfret is 73°F with 1% chance of
precipitation and winds at 10 mph.
**After:**
> I should look up the current weather conditions.
...
Final Answer: The current weather in Pomfret is 62°F, 1% precipitation,
61% humidity, and 4 mph wind.
---
Query: Top team in english premier league?
**Before:**
> I need to find out which team is currently at the top of the English
Premier League
...
Final Answer: Liverpool FC is currently at the top of the English
Premier League.
**After:**
> I need to find out which team is currently at the top of the English
Premier League
...
Final Answer: Man City is currently at the top of the English Premier
League.
---
Query: Top team in english premier league?
**Before:**
> I need to find out which team is currently at the top of the English
Premier League
...
Final Answer: Liverpool FC is currently at the top of the English
Premier League.
**After:**
> I need to find out which team is currently at the top of the English
Premier League
...
Final Answer: Man City is currently at the top of the English Premier
League.
---
Query: Any upcoming events in Paris?
**Before:**
> I should look for events in Paris
Action: Search
...
Final Answer: Upcoming events in Paris this month include Whit Sunday &
Whit Monday (French National Holiday), Makeup in Paris, Paris Jazz
Festival, Fete de la Musique, and Salon International de la Maison de.
**After:**
> I should look for events in Paris
Action: Search
...
Final Answer: Upcoming events in Paris include Elektric Park 2023, The
Aces, and BEING AS AN OCEAN.
JSONLoader.load does not specify `encoding` in
`self.file_path.read_text()` as `self.file_path.open()`
<!-- Thank you for contributing to LangChain!
Replace this entire 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 your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
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. These live is docs/extras
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17, @rlancemartin.
-->
Description:
Gmail message retrieval in GmailGetMessage and GmailSearch returned an
empty string when encountering multipart emails. This change correctly
extracts the email body for multipart emails.
Dependencies: None
@hwchase17 @vowelparrot
# Description
This change allows you to customize the prompt used in
`create_extraction_chain` as well as `create_extraction_chain_pydantic`.
It also adds the `verbose` argument to
`create_extraction_chain_pydantic` - because `create_extraction_chain`
had it already and `create_extraction_chain_pydantic` did not.
# Issue
N/A
# Dependencies
N/A
# Twitter
https://twitter.com/CamAHutchison
Hi,
- Description:
- Solves the issue #6478.
- Includes some additional rework on the `JSONLoader` class:
- Getting metadata is decoupled from `_get_text`
- Validating metadata_func is perform now by `_validate_metadata_func`,
instead of `_validate_content_key`
- Issue: #6478
- Dependencies: NA
- Tag maintainer: @hwchase17
Description: Adds tags and dataview fields to ObsidianLoader doc
metadata.
- Issue: #9800, #4991
- Dependencies: none
- Tag maintainer: My best guess is @hwchase17 looking through the git
logs
- Twitter handle: I don't use twitter, sorry!
### Description
There is a really nice class for saving chat messages into a database -
SQLChatMessageHistory.
It leverages SqlAlchemy to be compatible with any supported database (in
contrast with PostgresChatMessageHistory, which is basically the same
but is limited to Postgres).
However, the class is not really customizable in terms of what you can
store. I can imagine a lot of use cases, when one will need to save a
message date, along with some additional metadata.
To solve this, I propose to extract the converting logic from
BaseMessage to SQLAlchemy model (and vice versa) into a separate class -
message converter. So instead of rewriting the whole
SQLChatMessageHistory class, a user will only need to write a custom
model and a simple mapping class, and pass its instance as a parameter.
I also noticed that there is no documentation on this class, so I added
that too, with an example of custom message converter.
### Issue
N/A
### Dependencies
N/A
### Tag maintainer
Not yet
### Twitter handle
N/A
Description: new chain for logical fallacy removal from model output in
chain and docs
Issue: n/a see above
Dependencies: none
Tag maintainer: @hinthornw in past from my end but not sure who that
would be for maintenance of chains
Twitter handle: no twitter feel free to call out my git user if shout
out j-space-b
Note: created documentation in docs/extras
---------
Co-authored-by: Jon Bennion <jb@Jons-MacBook-Pro.local>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Issue: closes#9855
* consolidates `from_texts` and `add_texts` functions for pinecone
upsert
* adds two types of batching (one for embeddings and one for index
upsert)
* adds thread pool size when instantiating pinecone index
