The most reliable way to not have a chain run an undesirable SQL command
is to not give it database permissions to run that command. That way the
database itself performs the rule enforcement, so it's much easier to
configure and use properly than anything we could add in ourselves.
## Description
The following PR enables the [grammar-based
sampling](https://github.com/ggerganov/llama.cpp/tree/master/grammars)
in llama-cpp LLM.
In short, loading file with formal grammar definition will constrain
model outputs. For instance, one can force the model to generate valid
JSON or generate only python lists.
In the follow-up PR we will add:
* docs with some description why it is cool and how it works
* maybe some code sample for some task such as in llama repo
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
<!-- 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.
-->
Hi LangChain :) Thank you for such a great project!
I was going through the CONTRIBUTING.md and found a few minor issues.
Expose classmethods to convenient initialize the vectostore.
The purpose of this PR is to make it easy for users to initialize an
empty vectorstore that's properly pre-configured without having to index
documents into it via `from_documents`.
This will make it easier for users to rely on the following indexing
code: https://github.com/langchain-ai/langchain/pull/9614
to help manage data in the qdrant vectorstore.
### Description
The previous Redis implementation did not allow for the user to specify
the index configuration (i.e. changing the underlying algorithm) or add
additional metadata to use for querying (i.e. hybrid or "filtered"
search).
This PR introduces the ability to specify custom index attributes and
metadata attributes as well as use that metadata in filtered queries.
Overall, more structure was introduced to the Redis implementation that
should allow for easier maintainability moving forward.
# New Features
The following features are now available with the Redis integration into
Langchain
## Index schema generation
The schema for the index will now be automatically generated if not
specified by the user. For example, the data above has the multiple
metadata categories. The the following example
```python
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores.redis import Redis
embeddings = OpenAIEmbeddings()
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users"
)
```
Loading the data in through this and the other ``from_documents`` and
``from_texts`` methods will now generate index schema in Redis like the
following.
view index schema with the ``redisvl`` tool. [link](redisvl.com)
```bash
$ rvl index info -i users
```
Index Information:
| Index Name | Storage Type | Prefixes | Index Options | Indexing |
|--------------|----------------|---------------|-----------------|------------|
| users | HASH | ['doc:users'] | [] | 0 |
Index Fields:
| Name | Attribute | Type | Field Option | Option Value |
|----------------|----------------|---------|----------------|----------------|
| user | user | TEXT | WEIGHT | 1 |
| job | job | TEXT | WEIGHT | 1 |
| credit_score | credit_score | TEXT | WEIGHT | 1 |
| content | content | TEXT | WEIGHT | 1 |
| age | age | NUMERIC | | |
| content_vector | content_vector | VECTOR | | |
### Custom Metadata specification
The metadata schema generation has the following rules
1. All text fields are indexed as text fields.
2. All numeric fields are index as numeric fields.
If you would like to have a text field as a tag field, users can specify
overrides like the following for the example data
```python
# this can also be a path to a yaml file
index_schema = {
"text": [{"name": "user"}, {"name": "job"}],
"tag": [{"name": "credit_score"}],
"numeric": [{"name": "age"}],
}
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users"
)
```
This will change the index specification to
Index Information:
| Index Name | Storage Type | Prefixes | Index Options | Indexing |
|--------------|----------------|----------------|-----------------|------------|
| users2 | HASH | ['doc:users2'] | [] | 0 |
Index Fields:
| Name | Attribute | Type | Field Option | Option Value |
|----------------|----------------|---------|----------------|----------------|
| user | user | TEXT | WEIGHT | 1 |
| job | job | TEXT | WEIGHT | 1 |
| content | content | TEXT | WEIGHT | 1 |
| credit_score | credit_score | TAG | SEPARATOR | , |
| age | age | NUMERIC | | |
| content_vector | content_vector | VECTOR | | |
and throw a warning to the user (log output) that the generated schema
does not match the specified schema.
```text
index_schema does not match generated schema from metadata.
index_schema: {'text': [{'name': 'user'}, {'name': 'job'}], 'tag': [{'name': 'credit_score'}], 'numeric': [{'name': 'age'}]}
generated_schema: {'text': [{'name': 'user'}, {'name': 'job'}, {'name': 'credit_score'}], 'numeric': [{'name': 'age'}]}
```
As long as this is on purpose, this is fine.
The schema can be defined as a yaml file or a dictionary
```yaml
text:
- name: user
- name: job
tag:
- name: credit_score
numeric:
- name: age
```
and you pass in a path like
```python
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users3",
index_schema=Path("sample1.yml").resolve()
)
```
Which will create the same schema as defined in the dictionary example
Index Information:
| Index Name | Storage Type | Prefixes | Index Options | Indexing |
|--------------|----------------|----------------|-----------------|------------|
| users3 | HASH | ['doc:users3'] | [] | 0 |
Index Fields:
| Name | Attribute | Type | Field Option | Option Value |
|----------------|----------------|---------|----------------|----------------|
| user | user | TEXT | WEIGHT | 1 |
| job | job | TEXT | WEIGHT | 1 |
| content | content | TEXT | WEIGHT | 1 |
| credit_score | credit_score | TAG | SEPARATOR | , |
| age | age | NUMERIC | | |
| content_vector | content_vector | VECTOR | | |
### Custom Vector Indexing Schema
Users with large use cases may want to change how they formulate the
vector index created by Langchain
To utilize all the features of Redis for vector database use cases like
this, you can now do the following to pass in index attribute modifiers
like changing the indexing algorithm to HNSW.
```python
vector_schema = {
"algorithm": "HNSW"
}
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users3",
vector_schema=vector_schema
)
```
A more complex example may look like
```python
vector_schema = {
"algorithm": "HNSW",
"ef_construction": 200,
"ef_runtime": 20
}
rds, keys = Redis.from_texts_return_keys(
texts,
embeddings,
metadatas=metadata,
redis_url="redis://localhost:6379",
index_name="users3",
vector_schema=vector_schema
)
```
All names correspond to the arguments you would set if using Redis-py or
RedisVL. (put in doc link later)
### Better Querying
Both vector queries and Range (limit) queries are now available and
metadata is returned by default. The outputs are shown.
```python
>>> query = "foo"
>>> results = rds.similarity_search(query, k=1)
>>> print(results)
[Document(page_content='foo', metadata={'user': 'derrick', 'job': 'doctor', 'credit_score': 'low', 'age': '14', 'id': 'doc:users:657a47d7db8b447e88598b83da879b9d', 'score': '7.15255737305e-07'})]
>>> results = rds.similarity_search_with_score(query, k=1, return_metadata=False)
>>> print(results) # no metadata, but with scores
[(Document(page_content='foo', metadata={}), 7.15255737305e-07)]
>>> results = rds.similarity_search_limit_score(query, k=6, score_threshold=0.0001)
>>> print(len(results)) # range query (only above threshold even if k is higher)
4
```
### Custom metadata filtering
A big advantage of Redis in this space is being able to do filtering on
data stored alongside the vector itself. With the example above, the
following is now possible in langchain. The equivalence operators are
overridden to describe a new expression language that mimic that of
[redisvl](redisvl.com). This allows for arbitrarily long sequences of
filters that resemble SQL commands that can be used directly with vector
queries and range queries.
There are two interfaces by which to do so and both are shown.
```python
>>> from langchain.vectorstores.redis import RedisFilter, RedisNum, RedisText
>>> age_filter = RedisFilter.num("age") > 18
>>> age_filter = RedisNum("age") > 18 # equivalent
>>> results = rds.similarity_search(query, filter=age_filter)
>>> print(len(results))
3
>>> job_filter = RedisFilter.text("job") == "engineer"
>>> job_filter = RedisText("job") == "engineer" # equivalent
>>> results = rds.similarity_search(query, filter=job_filter)
>>> print(len(results))
2
# fuzzy match text search
>>> job_filter = RedisFilter.text("job") % "eng*"
>>> results = rds.similarity_search(query, filter=job_filter)
>>> print(len(results))
2
# combined filters (AND)
>>> combined = age_filter & job_filter
>>> results = rds.similarity_search(query, filter=combined)
>>> print(len(results))
1
# combined filters (OR)
>>> combined = age_filter | job_filter
>>> results = rds.similarity_search(query, filter=combined)
>>> print(len(results))
4
```
All the above filter results can be checked against the data above.
### Other
- Issue: #3967
- Dependencies: No added dependencies
- Tag maintainer: @hwchase17 @baskaryan @rlancemartin
- Twitter handle: @sampartee
---------
Co-authored-by: Naresh Rangan <naresh.rangan0@walmart.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
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>
This PR fixes `QuestionListOutputParser` text splitting.
`QuestionListOutputParser` incorrectly splits numbered list text into
lines. If text doesn't end with `\n` , the regex doesn't capture the
last item. So it always returns `n - 1` items, and
`WebResearchRetriever.llm_chain` generates less queries than requested
in the search prompt.
How to reproduce:
```python
from langchain.retrievers.web_research import QuestionListOutputParser
parser = QuestionListOutputParser()
good = parser.parse(
"""1. This is line one.
2. This is line two.
""" # <-- !
)
bad = parser.parse(
"""1. This is line one.
2. This is line two.""" # <-- No new line.
)
assert good.lines == ['1. This is line one.\n', '2. This is line two.\n'], good.lines
assert bad.lines == ['1. This is line one.\n', '2. This is line two.'], bad.lines
```
NOTE: Last item will not contain a line break but this seems ok because
the items are stripped in the
`WebResearchRetriever.clean_search_query()`.
Description: You cannot execute spark_sql with versions prior to 3.4 due
to the introduction of pyspark.errors in version 3.4.
And if you are below you get 3.4 "pyspark is not installed. Please
install it with pip nstall pyspark" which is not helpful. Also if you
not have pyspark installed you get already the error in init. I would
return all errors. But if you have a different idea feel free to
comment.
Issue: None
Dependencies: None
Maintainer:
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description:
- adding implementation of delete for pgvector
- adding modification time in docs metadata for confluence and google
drive.
Issue:
https://github.com/langchain-ai/langchain/issues/9312
Tag maintainer: @baskaryan, @eyurtsev, @hwchase17, @rlancemartin.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
This adds Xata as a memory store also to the python version of
LangChain, similar to the [one for
LangChain.js](https://github.com/hwchase17/langchainjs/pull/2217).
I have added a Jupyter Notebook with a simple and a more complex example
using an agent.
To run the integration test, you need to execute something like:
```
XATA_API_KEY='xau_...' XATA_DB_URL="https://demo-uni3q8.eu-west-1.xata.sh/db/langchain" poetry run pytest tests/integration_tests/memory/test_xata.py
```
Where `langchain` is the database you create in Xata.
Still working out interface/notebooks + need discord data dump to test
out things other than copy+paste
Update:
- Going to remove the 'user_id' arg in the loaders themselves and just
standardize on putting the "sender" arg in the extra kwargs. Then can
provide a utility function to map these to ai and human messages
- Going to move the discord one into just a notebook since I don't have
a good dump to test on and copy+paste maybe isn't the greatest thing to
support in v0
- Need to do more testing on slack since it seems the dump only includes
channels and NOT 1 on 1 convos
-
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Adds the qdrant search filter/params to the
`max_marginal_relevance_search` method, which is present on others. I
did not add `offset` for pagination, because it's behavior would be
ambiguous in this setting (since we fetch extra and down-select).
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Kacper Łukawski <lukawski.kacper@gmail.com>
The Graph Chains are different in the way that it uses two LLMChains
instead of one like the retrievalQA chains. Therefore, sometimes you
want to use different LLM to generate the database query and to generate
the final answer.
This feature would make it more convenient to use different LLMs in the
same chain.
I have also renamed the Graph DB QA Chain to Neo4j DB QA Chain in the
documentation only as it is used only for Neo4j. The naming was
ambigious as it was the first graphQA chain added and wasn't sure how do
you want to spin it.
Updated design of the "API Reference" text
Here is an example of the current format:
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
Uses the shorter import path
`from langchain.document_loaders import` instead of the full path
`from langchain.document_loaders.assemblyai`
Applies those changes to the docs and the unit test.
See #9667 that adds this new loader.
<!-- 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.
-->
