Adding `UpstashRatelimitHandler` callback for rate limiting based on
number of chain invocations or LLM token usage.
For more details, see [upstash/ratelimit-py
repository](https://github.com/upstash/ratelimit-py) or the notebook
guide included in this PR.
Twitter handle: @cahidarda
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- Refactor streaming to use raw events;
- Add `stream_usage` class attribute and kwarg to stream methods that,
if True, will include separate chunks in the stream containing usage
metadata.
There are two ways to implement streaming with anthropic's python sdk.
They have slight differences in how they surface usage metadata.
1. [Use helper
functions](https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#streaming-helpers).
This is what we are doing now.
```python
count = 1
with client.messages.stream(**params) as stream:
for text in stream.text_stream:
snapshot = stream.current_message_snapshot
print(f"{count}: {snapshot.usage} -- {text}")
count = count + 1
final_snapshot = stream.get_final_message()
print(f"{count}: {final_snapshot.usage}")
```
```
1: Usage(input_tokens=8, output_tokens=1) -- Hello
2: Usage(input_tokens=8, output_tokens=1) -- !
3: Usage(input_tokens=8, output_tokens=1) -- How
4: Usage(input_tokens=8, output_tokens=1) -- can
5: Usage(input_tokens=8, output_tokens=1) -- I
6: Usage(input_tokens=8, output_tokens=1) -- assist
7: Usage(input_tokens=8, output_tokens=1) -- you
8: Usage(input_tokens=8, output_tokens=1) -- today
9: Usage(input_tokens=8, output_tokens=1) -- ?
10: Usage(input_tokens=8, output_tokens=12)
```
To do this correctly, we need to emit a new chunk at the end of the
stream containing the usage metadata.
2. [Handle raw
events](https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#streaming-responses)
```python
stream = client.messages.create(**params, stream=True)
count = 1
for event in stream:
print(f"{count}: {event}")
count = count + 1
```
```
1: RawMessageStartEvent(message=Message(id='msg_01Vdyov2kADZTXqSKkfNJXcS', content=[], model='claude-3-haiku-20240307', role='assistant', stop_reason=None, stop_sequence=None, type='message', usage=Usage(input_tokens=8, output_tokens=1)), type='message_start')
2: RawContentBlockStartEvent(content_block=TextBlock(text='', type='text'), index=0, type='content_block_start')
3: RawContentBlockDeltaEvent(delta=TextDelta(text='Hello', type='text_delta'), index=0, type='content_block_delta')
4: RawContentBlockDeltaEvent(delta=TextDelta(text='!', type='text_delta'), index=0, type='content_block_delta')
5: RawContentBlockDeltaEvent(delta=TextDelta(text=' How', type='text_delta'), index=0, type='content_block_delta')
6: RawContentBlockDeltaEvent(delta=TextDelta(text=' can', type='text_delta'), index=0, type='content_block_delta')
7: RawContentBlockDeltaEvent(delta=TextDelta(text=' I', type='text_delta'), index=0, type='content_block_delta')
8: RawContentBlockDeltaEvent(delta=TextDelta(text=' assist', type='text_delta'), index=0, type='content_block_delta')
9: RawContentBlockDeltaEvent(delta=TextDelta(text=' you', type='text_delta'), index=0, type='content_block_delta')
10: RawContentBlockDeltaEvent(delta=TextDelta(text=' today', type='text_delta'), index=0, type='content_block_delta')
11: RawContentBlockDeltaEvent(delta=TextDelta(text='?', type='text_delta'), index=0, type='content_block_delta')
12: RawContentBlockStopEvent(index=0, type='content_block_stop')
13: RawMessageDeltaEvent(delta=Delta(stop_reason='end_turn', stop_sequence=None), type='message_delta', usage=MessageDeltaUsage(output_tokens=12))
14: RawMessageStopEvent(type='message_stop')
```
Here we implement the second option, in part because it should make
things easier when implementing streaming tool calls in the near future.
This would add two new chunks to the stream-- one at the beginning and
one at the end-- with blank content and containing usage metadata. We
add kwargs to the stream methods and a class attribute allowing for this
behavior to be toggled. I enabled it by default. If we merge this we can
add the same kwargs / attribute to OpenAI.
Usage:
```python
from langchain_anthropic import ChatAnthropic
model = ChatAnthropic(
model="claude-3-haiku-20240307",
temperature=0
)
full = None
for chunk in model.stream("hi"):
full = chunk if full is None else full + chunk
print(chunk)
print(f"\nFull: {full}")
```
```
content='' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 8, 'output_tokens': 0, 'total_tokens': 8}
content='Hello' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content='!' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content=' How' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content=' can' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content=' I' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content=' assist' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content=' you' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content=' today' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content='?' id='run-8a20843f-25c7-4025-ad72-9add395899e3'
content='' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 0, 'output_tokens': 12, 'total_tokens': 12}
Full: content='Hello! How can I assist you today?' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 8, 'output_tokens': 12, 'total_tokens': 20}
```
They cause `poetry lock` to take a ton of time, and `uv pip install` can
resolve the constraints from these toml files in trivial time
(addressing problem with #19153)
This allows us to properly upgrade lockfile dependencies moving forward,
which revealed some issues that were either fixed or type-ignored (see
file comments)
- [x] **Adding AsyncRootListener**: "langchain_core: Adding
AsyncRootListener"
- **Description:** Adding an AsyncBaseTracer, AsyncRootListener and
`with_alistener` function. This is to enable binding async root listener
to runnables. This currently only supported for sync listeners.
- **Issue:** None
- **Dependencies:** None
- [x] **Add tests and docs**: Added units tests and example snippet code
within the function description of `with_alistener`
- [x] **Lint and test**: Run make format_diff, make lint_diff and make
test
## Description
The `path` param is used to specify the local persistence directory,
which isn't required if using Qdrant server.
This is a breaking but necessary change.
This PR adds support for using Databricks Unity Catalog functions as
LangChain tools, which runs inside a Databricks SQL warehouse.
* An example notebook is provided.
The response.get("model", self.model_name) checks if the model key
exists in the response dictionary. If it does, it uses that value;
otherwise, it uses self.model_name.
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: 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. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
langchain-together depends on langchain-openai ^0.1.8
langchain-openai 0.1.8 has langchain-core >= 0.2.2
Here we bump langchain-core to 0.2.2, just to pass minimum dependency
version tests.
decisions to discuss
- only chat models
- model_provider isn't based on any existing values like llm-type,
package names, class names
- implemented as function not as a wrapper ChatModel
- function name (init_model)
- in langchain as opposed to community or core
- marked beta
Thank you for contributing to LangChain!
**Description:** Adds Langchain support for Nomic Embed Vision
**Twitter handle:** nomic_ai,zach_nussbaum
- [x] **Add tests and docs**: 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. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Lance Martin <122662504+rlancemartin@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** This PR addresses an issue with an existing test that
was not effectively testing the intended functionality. The previous
test setup did not adequately validate the filtering of the labels in
neo4j, because the nodes and relationship in the test data did not have
any properties set. Without properties these labels would not have been
returned, regardless of the filtering.
---------
Co-authored-by: Oskar Hane <oh@oskarhane.com>
This PR adds a constructor `metadata_indexing` parameter to the
Cassandra vector store to allow optional fine-tuning of which fields of
the metadata are to be indexed.
This is a feature supported by the underlying CassIO library. Indexing
mode of "all", "none" or deny- and allow-list based choices are
available.
The rationale is, in some cases it's advisable to programmatically
exclude some portions of the metadata from the index if one knows in
advance they won't ever be used at search-time. this keeps the index
more lightweight and performant and avoids limitations on the length of
_indexed_ strings.
I added a integration test of the feature. I also added the possibility
of running the integration test with Cassandra on an arbitrary IP
address (e.g. Dockerized), via
`CASSANDRA_CONTACT_POINTS=10.1.1.5,10.1.1.6 poetry run pytest [...]` or
similar.
While I was at it, I added a line to the `.gitignore` since the mypy
_test_ cache was not ignored yet.
My X (Twitter) handle: @rsprrs.
**Description:** This PR adds a `USER_AGENT` env variable that is to be
used for web scraping. It creates a util to get that user agent and uses
it in the classes used for scraping in [this piece of
doc](https://python.langchain.com/v0.1/docs/use_cases/web_scraping/).
Identifying your scraper is considered a good politeness practice, this
PR aims at easing it.
**Issue:** `None`
**Dependencies:** `None`
**Twitter handle:** `None`
# package community: Fix SQLChatMessageHistory
## Description
Here is a rewrite of `SQLChatMessageHistory` to properly implement the
asynchronous approach. The code circumvents [issue
22021](https://github.com/langchain-ai/langchain/issues/22021) by
accepting a synchronous call to `def add_messages()` in an asynchronous
scenario. This bypasses the bug.
For the same reasons as in [PR
22](https://github.com/langchain-ai/langchain-postgres/pull/32) of
`langchain-postgres`, we use a lazy strategy for table creation. Indeed,
the promise of the constructor cannot be fulfilled without this. It is
not possible to invoke a synchronous call in a constructor. We
compensate for this by waiting for the next asynchronous method call to
create the table.
The goal of the `PostgresChatMessageHistory` class (in
`langchain-postgres`) is, among other things, to be able to recycle
database connections. The implementation of the class is problematic, as
we have demonstrated in [issue
22021](https://github.com/langchain-ai/langchain/issues/22021).
Our new implementation of `SQLChatMessageHistory` achieves this by using
a singleton of type (`Async`)`Engine` for the database connection. The
connection pool is managed by this singleton, and the code is then
reentrant.
We also accept the type `str` (optionally complemented by `async_mode`.
I know you don't like this much, but it's the only way to allow an
asynchronous connection string).
In order to unify the different classes handling database connections,
we have renamed `connection_string` to `connection`, and `Session` to
`session_maker`.
Now, a single transaction is used to add a list of messages. Thus, a
crash during this write operation will not leave the database in an
unstable state with a partially added message list. This makes the code
resilient.
We believe that the `PostgresChatMessageHistory` class is no longer
necessary and can be replaced by:
```
PostgresChatMessageHistory = SQLChatMessageHistory
```
This also fixes the bug.
## Issue
- [issue 22021](https://github.com/langchain-ai/langchain/issues/22021)
- Bug in _exit_history()
- Bugs in PostgresChatMessageHistory and sync usage
- Bugs in PostgresChatMessageHistory and async usage
- [issue
36](https://github.com/langchain-ai/langchain-postgres/issues/36)
## Twitter handle:
pprados
## Tests
- libs/community/tests/unit_tests/chat_message_histories/test_sql.py
(add async test)
@baskaryan, @eyurtsev or @hwchase17 can you check this PR ?
And, I've been waiting a long time for validation from other PRs. Can
you take a look?
- [PR 32](https://github.com/langchain-ai/langchain-postgres/pull/32)
- [PR 15575](https://github.com/langchain-ai/langchain/pull/15575)
- [PR 13200](https://github.com/langchain-ai/langchain/pull/13200)
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- **Description:** The InMemoryVectorStore is a nice and simple vector
store implementation for quick development and debugging. The current
implementation is quite limited in its functionalities. This PR extends
the functionalities by adding utility function to persist the vector
store to a json file and to load it from a json file. We choose the json
file format because it allows inspection of the database contents in a
text editor, which is great for debugging. Furthermore, it adds a
`filter` keyword that can be used to filter out documents on their
`page_content` or `metadata`.
- **Issue:** -
- **Dependencies:** -
- **Twitter handle:** @Vincent_Min
- [ ] **community**: "vectorstore: added filtering support for LanceDB
vector store"
- [ ] **This PR adds filtering capabilities to LanceDB**:
- **Description:** In LanceDB filtering can be applied when searching
for data into the vectorstore. It is using the SQL language as mentioned
in the LanceDB documentation.
- **Issue:** #18235
- **Dependencies:** No
- [ ] **Add tests and docs**: 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. It lives in
`docs/docs/integrations` directory.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
