This PR provides idiomatic implementations for the exact-match and the
semantic LLM caches using Astra DB as backend through the database's
HTTP JSON API. These caches require the `astrapy` library as dependency.
Comes with integration tests and example usage in the `llm_cache.ipynb`
in the docs.
@baskaryan this is the Astra DB counterpart for the Cassandra classes
you merged some time ago, tagging you for your familiarity with the
topic. Thank you!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Changes:
- remove langchain_core/schema since no clear distinction b/n schema and
non-schema modules
- make every module that doesn't end in -y plural
- where easy have 1-2 classes per file
- no more than one level of nesting in directories
- only import from top level core modules in langchain
**Description**:
- Added Momento Vector Index (MVI) as a vector store provider. This
includes an implementation with docstrings, integration tests, a
notebook, and documentation on the docs pages.
- Updated the Momento dependency in pyproject.toml and the lock file to
enable access to MVI.
- Refactored the Momento cache and chat history session store to prefer
using "MOMENTO_API_KEY" over "MOMENTO_AUTH_TOKEN" for consistency with
MVI. This change is backwards compatible with the previous "auth_token"
variable usage. Updated the code and tests accordingly.
**Dependencies**:
- Updated Momento dependency in pyproject.toml.
**Testing**:
- Run the integration tests with a Momento API key. Get one at the
[Momento Console](https://console.gomomento.com) for free. MVI is
available in AWS us-west-2 with a superuser key.
- `MOMENTO_API_KEY=<your key> poetry run pytest
tests/integration_tests/vectorstores/test_momento_vector_index.py`
**Tag maintainer:**
@eyurtsev
**Twitter handle**:
Please mention @momentohq for this addition to langchain. With the
integration of Momento Vector Index, Momento caching, and session store,
Momento provides serverless support for the core langchain data needs.
Also mention @mlonml for the integration.
# Description
Attempts to fix RedisCache for ChatGenerations using `loads` and `dumps`
used in SQLAlchemy cache by @hwchase17 . this is better than pickle
dump, because this won't execute any arbitrary code during
de-serialisation.
# Issues
#7722 & #8666
# Dependencies
None, but removes the warning introduced in #8041 by @baskaryan
Handle: @jaikanthjay46
Hello,
this PR improves coverage for caching by the two Cassandra-related
caches (i.e. exact-match and semantic alike) by switching to the more
general `dumps`/`loads` serdes utilities.
This enables cache usage within e.g. `ChatOpenAI` contexts (which need
to store lists of `ChatGeneration` instead of `Generation`s), which was
not possible as long as the cache classes were relying on the legacy
`_dump_generations_to_json` and `_load_generations_from_json`).
Additionally, a slightly different init signature is introduced for the
cache objects:
- named parameters required for init, to pave the way for easier changes
in the future connect-to-db flow (and tests adjusted accordingly)
- added a `skip_provisioning` optional passthrough parameter for use
cases where the user knows the underlying DB table, etc already exist.
Thank you for a review!
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>
### 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>
Stefano Lottini