minor changes to module import error handling and minor issues in
tutorial documents.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
**Desscription**: When the ``sql_database.from_databricks`` is executed
from a Workflow Job, the ``context`` object does not have a
"browserHostName" property, resulting in an error. This change manages
the error so the "DATABRICKS_HOST" env variable value is used instead of
stoping the flow
Co-authored-by: lmorosdb <lmorosdb>
The return type of `json.loads` is `Any`.
In fact, the return type of `dumpd` must be based on `json.loads`, so
the correction here is understandable.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- Fix bug with TypedDicts rendering inherited methods if inherting from
typing_extensions.TypedDict rather than typing.TypedDict
- Do not surface inherited pydantic methods for subclasses of BaseModel
- Subclasses of RunnableSerializable will not how methods inherited from
Runnable or from BaseModel
- Subclasses of Runnable that not pydantic models will include a link to
RunnableInterface (they still show inherited methods, we can fix this
later)
- [x] **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/
Description: Update Rag tutorial notebook so it includes an additional
notebook cell with pip installs of required langchain_chroma and
langchain_community.
This fixes the issue with the rag tutorial gives you a 'missing modules'
error if you run code in the notebook as is.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- **Description:** Add optional max_messages to MessagePlaceholder
- **Issue:**
[16096](https://github.com/langchain-ai/langchain/issues/16096)
- **Dependencies:** None
- **Twitter handle:** @davedecaprio
Sometimes it's better to limit the history in the prompt itself rather
than the memory. This is needed if you want different prompts in the
chain to have different history lengths.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Thank you for contributing to LangChain!
**Description**
The current code snippet for `Fireworks` had incorrect parameters. This
PR fixes those parameters.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
currently we skip CI on diffs >= 300 files. think we should just run it
on all packages instead
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- Moved doc-strings below attribtues in TypedDicts -- seems to render
better on APIReference pages.
* Provided more description and some simple code examples
- **Description:** Restores compatibility with SQLAlchemy 1.4.x that was
broken since #18992 and adds a test run for this version on CI (only for
Python 3.11)
- **Issue:** fixes#19681
- **Dependencies:** None
- **Twitter handle:** `@krassowski_m`
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** sambanova sambaverse integration improvement: removed
input parsing that was changing raw user input, and was making to use
process prompt parameter as true mandatory
**Description:** `astream_events(version="v2")` didn't propagate
exceptions in `langchain-core<=0.2.6`, fixed in the #22916. This PR adds
a unit test to check that exceptions are propagated upwards.
Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>
Added missed docstrings. Format docstrings to the consistent format
(used in the API Reference)
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
- [x] **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/
This raises ImportError due to a circular import:
```python
from langchain_core import chat_history
```
This does not:
```python
from langchain_core import runnables
from langchain_core import chat_history
```
Here we update `test_imports` to run each import in a separate
subprocess. Open to other ways of doing this!
Tests failing on master with
> FAILED
tests/unit_tests/embeddings/test_ovhcloud.py::test_ovhcloud_embed_documents
- ValueError: Request failed with status code: 401, {"message":"Bad
token; invalid JSON"}
Thank you for contributing to LangChain!
**Description:** Noticed an issue with when I was calling
`RecursiveJsonSplitter().split_json()` multiple times that I was getting
weird results. I found an issue where `chunks` list in the `_json_split`
method. If chunks is not provided when _json_split (which is the case
when split_json calls _json_split) then the same list is used for
subsequent calls to `_json_split`.
You can see this in the test case i also added to this commit.
Output should be:
```
[{'a': 1, 'b': 2}]
[{'c': 3, 'd': 4}]
```
Instead you get:
```
[{'a': 1, 'b': 2}]
[{'a': 1, 'b': 2, 'c': 3, 'd': 4}]
```
---------
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
- **Description:** add `**request_kwargs` and expect `TimeError` in
`_fetch` function for AsyncHtmlLoader. This allows you to fill in the
kwargs parameter when using the `load()` method of the `AsyncHtmlLoader`
class.
Co-authored-by: Yucolu <yucolu@tencent.com>
#### Description
This MR defines a `ExperimentalMarkdownSyntaxTextSplitter` class. The
main goal is to replicate the functionality of the original
`MarkdownHeaderTextSplitter` which extracts the header stack as metadata
but with one critical difference: it keeps the whitespace of the
original text intact.
This draft reimplements the `MarkdownHeaderTextSplitter` with a very
different algorithmic approach. Instead of marking up each line of the
text individually and aggregating them back together into chunks, this
method builds each chunk sequentially and applies the metadata to each
chunk. This makes the implementation simpler. However, since it's
designed to keep white space intact its not a full drop in replacement
for the original. Since it is a radical implementation change to the
original code and I would like to get feedback to see if this is a
worthwhile replacement, should be it's own class, or is not a good idea
at all.
Note: I implemented the `return_each_line` parameter but I don't think
it's a necessary feature. I'd prefer to remove it.
This implementation also adds the following additional features:
- Splits out code blocks and includes the language in the `"Code"`
metadata key
- Splits text on the horizontal rule `---` as well
- The `headers_to_split_on` parameter is now optional - with sensible
defaults that can be overridden.
#### Issue
Keeping the whitespace keeps the paragraphs structure and the formatting
of the code blocks intact which allows the caller much more flexibility
in how they want to further split the individuals sections of the
resulting documents. This addresses the issues brought up by the
community in the following issues:
- https://github.com/langchain-ai/langchain/issues/20823
- https://github.com/langchain-ai/langchain/issues/19436
- https://github.com/langchain-ai/langchain/issues/22256
#### Dependencies
N/A
#### Twitter handle
@RyanElston
---------
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
# Description
This pull request aims to address specific issues related to the
ambiguity and error-proneness of the output types of certain output
parsers, as well as the absence of unit tests for some parsers. These
issues could potentially lead to runtime errors or unexpected behaviors
due to type mismatches when used, causing confusion for developers and
users. Through clarifying output types, this PR seeks to improve the
stability and reliability.
Therefore, this pull request
- fixes the `OutputType` of OutputParsers to be the expected type;
- e.g. `OutputType` property of `EnumOutputParser` raises `TypeError`.
This PR introduce a logic to extract `OutputType` from its attribute.
- and fixes the legacy API in OutputParsers like `LLMChain.run` to the
modern API like `LLMChain.invoke`;
- Note: For `OutputFixingParser`, `RetryOutputParser` and
`RetryWithErrorOutputParser`, this PR introduces `legacy` attribute with
False as default value in order to keep the backward compatibility
- and adds the tests for the `OutputFixingParser` and
`RetryOutputParser`.
The following table shows my expected output and the actual output of
the `OutputType` of OutputParsers.
I have used this table to fix `OutputType` of OutputParsers.
| Class Name of OutputParser | My Expected `OutputType` (after this PR)|
Actual `OutputType` [evidence](#evidence) (before this PR)| Fix Required
|
|---------|--------------|---------|--------|
| BooleanOutputParser | `<class 'bool'>` | `<class 'bool'>` | NO |
| CombiningOutputParser | `typing.Dict[str, Any]` | `TypeError` is
raised | YES |
| DatetimeOutputParser | `<class 'datetime.datetime'>` | `<class
'datetime.datetime'>` | NO |
| EnumOutputParser(enum=MyEnum) | `MyEnum` | `TypeError` is raised | YES
|
| OutputFixingParser | The same type as `self.parser.OutputType` | `~T`
| YES |
| CommaSeparatedListOutputParser | `typing.List[str]` |
`typing.List[str]` | NO |
| MarkdownListOutputParser | `typing.List[str]` | `typing.List[str]` |
NO |
| NumberedListOutputParser | `typing.List[str]` | `typing.List[str]` |
NO |
| JsonOutputKeyToolsParser | `typing.Any` | `typing.Any` | NO |
| JsonOutputToolsParser | `typing.Any` | `typing.Any` | NO |
| PydanticToolsParser | `typing.Any` | `typing.Any` | NO |
| PandasDataFrameOutputParser | `typing.Dict[str, Any]` | `TypeError` is
raised | YES |
| PydanticOutputParser(pydantic_object=MyModel) | `<class
'__main__.MyModel'>` | `<class '__main__.MyModel'>` | NO |
| RegexParser | `typing.Dict[str, str]` | `TypeError` is raised | YES |
| RegexDictParser | `typing.Dict[str, str]` | `TypeError` is raised |
YES |
| RetryOutputParser | The same type as `self.parser.OutputType` | `~T` |
YES |
| RetryWithErrorOutputParser | The same type as `self.parser.OutputType`
| `~T` | YES |
| StructuredOutputParser | `typing.Dict[str, Any]` | `TypeError` is
raised | YES |
| YamlOutputParser(pydantic_object=MyModel) | `MyModel` | `~T` | YES |
NOTE: In "Fix Required", "YES" means that it is required to fix in this
PR while "NO" means that it is not required.
# Issue
No issues for this PR.
# Twitter handle
- [hmdev3](https://twitter.com/hmdev3)
# Questions:
1. Is it required to create tests for legacy APIs `LLMChain.run` in the
following scripts?
- libs/langchain/tests/unit_tests/output_parsers/test_fix.py;
- libs/langchain/tests/unit_tests/output_parsers/test_retry.py.
2. Is there a more appropriate expected output type than I expect in the
above table?
- e.g. the `OutputType` of `CombiningOutputParser` should be
SOMETHING...
# Actual outputs (before this PR)
<div id='evidence'></div>
<details><summary>Actual outputs</summary>
## Requirements
- Python==3.9.13
- langchain==0.1.13
```python
Python 3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import langchain
>>> langchain.__version__
'0.1.13'
>>> from langchain import output_parsers
```
### `BooleanOutputParser`
```python
>>> output_parsers.BooleanOutputParser().OutputType
<class 'bool'>
```
### `CombiningOutputParser`
```python
>>> output_parsers.CombiningOutputParser(parsers=[output_parsers.DatetimeOutputParser(), output_parsers.CommaSeparatedListOutputParser()]).OutputType
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "D:\workspace\venv\lib\site-packages\langchain_core\output_parsers\base.py", line 160, in OutputType
raise TypeError(
TypeError: Runnable CombiningOutputParser doesn't have an inferable OutputType. Override the OutputType property to specify the output type.
```
### `DatetimeOutputParser`
```python
>>> output_parsers.DatetimeOutputParser().OutputType
<class 'datetime.datetime'>
```
### `EnumOutputParser`
```python
>>> from enum import Enum
>>> class MyEnum(Enum):
... a = 'a'
... b = 'b'
...
>>> output_parsers.EnumOutputParser(enum=MyEnum).OutputType
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "D:\workspace\venv\lib\site-packages\langchain_core\output_parsers\base.py", line 160, in OutputType
raise TypeError(
TypeError: Runnable EnumOutputParser doesn't have an inferable OutputType. Override the OutputType property to specify the output type.
```
### `OutputFixingParser`
```python
>>> output_parsers.OutputFixingParser(parser=output_parsers.DatetimeOutputParser()).OutputType
~T
```
### `CommaSeparatedListOutputParser`
```python
>>> output_parsers.CommaSeparatedListOutputParser().OutputType
typing.List[str]
```
### `MarkdownListOutputParser`
```python
>>> output_parsers.MarkdownListOutputParser().OutputType
typing.List[str]
```
### `NumberedListOutputParser`
```python
>>> output_parsers.NumberedListOutputParser().OutputType
typing.List[str]
```
### `JsonOutputKeyToolsParser`
```python
>>> output_parsers.JsonOutputKeyToolsParser(key_name='tool').OutputType
typing.Any
```
### `JsonOutputToolsParser`
```python
>>> output_parsers.JsonOutputToolsParser().OutputType
typing.Any
```
### `PydanticToolsParser`
```python
>>> from langchain.pydantic_v1 import BaseModel
>>> class MyModel(BaseModel):
... a: int
...
>>> output_parsers.PydanticToolsParser(tools=[MyModel, MyModel]).OutputType
typing.Any
```
### `PandasDataFrameOutputParser`
```python
>>> output_parsers.PandasDataFrameOutputParser().OutputType
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "D:\workspace\venv\lib\site-packages\langchain_core\output_parsers\base.py", line 160, in OutputType
raise TypeError(
TypeError: Runnable PandasDataFrameOutputParser doesn't have an inferable OutputType. Override the OutputType property to specify the output type.
```
### `PydanticOutputParser`
```python
>>> output_parsers.PydanticOutputParser(pydantic_object=MyModel).OutputType
<class '__main__.MyModel'>
```
### `RegexParser`
```python
>>> output_parsers.RegexParser(regex='$', output_keys=['a']).OutputType
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "D:\workspace\venv\lib\site-packages\langchain_core\output_parsers\base.py", line 160, in OutputType
raise TypeError(
TypeError: Runnable RegexParser doesn't have an inferable OutputType. Override the OutputType property to specify the output type.
```
### `RegexDictParser`
```python
>>> output_parsers.RegexDictParser(output_key_to_format={'a':'a'}).OutputType
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "D:\workspace\venv\lib\site-packages\langchain_core\output_parsers\base.py", line 160, in OutputType
raise TypeError(
TypeError: Runnable RegexDictParser doesn't have an inferable OutputType. Override the OutputType property to specify the output type.
```
### `RetryOutputParser`
```python
>>> output_parsers.RetryOutputParser(parser=output_parsers.DatetimeOutputParser()).OutputType
~T
```
### `RetryWithErrorOutputParser`
```python
>>> output_parsers.RetryWithErrorOutputParser(parser=output_parsers.DatetimeOutputParser()).OutputType
~T
```
### `StructuredOutputParser`
```python
>>> from langchain.output_parsers.structured import ResponseSchema
>>> response_schemas = [ResponseSchema(name="foo",description="a list of strings",type="List[string]"),ResponseSchema(name="bar",description="a string",type="string"), ]
>>> output_parsers.StructuredOutputParser.from_response_schemas(response_schemas).OutputType
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "D:\workspace\venv\lib\site-packages\langchain_core\output_parsers\base.py", line 160, in OutputType
raise TypeError(
TypeError: Runnable StructuredOutputParser doesn't have an inferable OutputType. Override the OutputType property to specify the output type.
```
### `YamlOutputParser`
```python
>>> output_parsers.YamlOutputParser(pydantic_object=MyModel).OutputType
~T
```
<div>
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
This change adds args_schema (pydantic BaseModel) to SearxSearchRun for
correct schema formatting on LLM function calls
Issue: currently using SearxSearchRun with OpenAI function calling
returns the following error "TypeError: SearxSearchRun._run() got an
unexpected keyword argument '__arg1' ".
This happens because the schema sent to the LLM is "input:
'{"__arg1":"foobar"}'" while the method should be called with the
"query" parameter.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:** Updated
*community.langchain_community.document_loaders.directory.py* to enable
the use of multiple glob patterns in the `DirectoryLoader` class. Now,
the glob parameter is of type `list[str] | str` and still defaults to
the same value as before. I updated the docstring of the class to
reflect this, and added a unit test to
*community.tests.unit_tests.document_loaders.test_directory.py* named
`test_directory_loader_glob_multiple`. This test also shows an example
of how to use the new functionality.
- ~~Issue:~~**Discussion Thread:**
https://github.com/langchain-ai/langchain/discussions/18559
- **Dependencies:** None
- **Twitter handle:** N/a
- [x] **Add tests and docs**
- Added test (described above)
- Updated class docstring
- [x] **Lint and test**
---------
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
Fix https://github.com/langchain-ai/langchain/issues/22972.
- [x] **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"
- [x] **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!
- [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.
- [x] **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.
```SemanticChunker``` currently provide three methods to split the texts semantically:
- percentile
- standard_deviation
- interquartile
I propose new method ```gradient```. In this method, the gradient of distance is used to split chunks along with the percentile method (technically) . This method is useful when chunks are highly correlated with each other or specific to a domain e.g. legal or medical. The idea is to apply anomaly detection on gradient array so that the distribution become wider and easy to identify boundaries in highly semantic data.
I have tested this merge on a set of 10 domain specific documents (mostly legal).
Details :
- **Issue:** Improvement
- **Dependencies:** NA
- **Twitter handle:** [x.com/prajapat_ravi](https://x.com/prajapat_ravi)
@hwchase17
---------
Co-authored-by: Raviraj Prajapat <raviraj.prajapat@sirionlabs.com>
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
Add chat history store based on Kafka.
Files added:
`libs/community/langchain_community/chat_message_histories/kafka.py`
`docs/docs/integrations/memory/kafka_chat_message_history.ipynb`
New issue to be created for future improvement:
1. Async method implementation.
2. Message retrieval based on timestamp.
3. Support for other configs when connecting to cloud hosted Kafka (e.g.
add `api_key` field)
4. Improve unit testing & integration testing.
**Description:**
- What I changed
- By specifying the `id_key` during the initialization of
`EnsembleRetriever`, it is now possible to determine which documents to
merge scores for based on the value corresponding to the `id_key`
element in the metadata, instead of `page_content`. Below is an example
of how to use the modified `EnsembleRetriever`:
```python
retriever = EnsembleRetriever(retrievers=[ret1, ret2], id_key="id") #
The Document returned by each retriever must keep the "id" key in its
metadata.
```
- Additionally, I added a script to easily test the behavior of the
`invoke` method of the modified `EnsembleRetriever`.
- Why I changed
- There are cases where you may want to calculate scores by treating
Documents with different `page_content` as the same when using
`EnsembleRetriever`. For example, when you want to ensemble the search
results of the same document described in two different languages.
- The previous `EnsembleRetriever` used `page_content` as the basis for
score aggregation, making the above usage difficult. Therefore, the
score is now calculated based on the specified key value in the
Document's metadata.
**Twitter handle:** @shimajiroxyz
- **Description:** add tool_messages_formatter for tool calling agent,
make tool messages can be formatted in different ways for your LLM.
- **Issue:** N/A
- **Dependencies:** N/A
**Standardizing DocumentLoader docstrings (of which there are many)**
This PR addresses issue #22866 and adds docstrings according to the
issue's specified format (in the appendix) for files csv_loader.py and
json_loader.py in langchain_community.document_loaders. In particular,
the following sections have been added to both CSVLoader and JSONLoader:
Setup, Instantiate, Load, Async load, and Lazy load. It may be worth
adding a 'Metadata' section to the JSONLoader docstring to clarify how
we want to extract the JSON metadata (using the `metadata_func`
argument). The files I used to walkthrough the various sections were
`example_2.json` from
[HERE](https://support.oneskyapp.com/hc/en-us/articles/208047697-JSON-sample-files)
and `hw_200.csv` from
[HERE](https://people.sc.fsu.edu/~jburkardt/data/csv/csv.html).
---------
Co-authored-by: lucast2021 <lucast2021@headroyce.org>
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
- **Description:** A very small fix in the Docstring of
`DuckDuckGoSearchResults` identified in the following issue.
- **Issue:** #22961
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **PR title**: "community: Fix#22975 (Add SSL Verification Option to
Requests Class in langchain_community)"
- **PR message**:
- **Description:**
- Added an optional verify parameter to the Requests class with a
default value of True.
- Modified the get, post, patch, put, and delete methods to include the
verify parameter.
- Updated the _arequest async context manager to include the verify
parameter.
- Added the verify parameter to the GenericRequestsWrapper class and
passed it to the Requests class.
- **Issue:** This PR fixes issue #22975.
- **Dependencies:** No additional dependencies are required for this
change.
- **Twitter handle:** @lunara_x
You can check this change with below code.
```python
from langchain_openai.chat_models import ChatOpenAI
from langchain.requests import RequestsWrapper
from langchain_community.agent_toolkits.openapi import planner
from langchain_community.agent_toolkits.openapi.spec import reduce_openapi_spec
with open("swagger.yaml") as f:
data = yaml.load(f, Loader=yaml.FullLoader)
swagger_api_spec = reduce_openapi_spec(data)
llm = ChatOpenAI(model='gpt-4o')
swagger_requests_wrapper = RequestsWrapper(verify=False) # modified point
superset_agent = planner.create_openapi_agent(swagger_api_spec, swagger_requests_wrapper, llm, allow_dangerous_requests=True, handle_parsing_errors=True)
superset_agent.run(
"Tell me the number and types of charts and dashboards available."
)
```
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:** The PR #22777 introduced a bug in
`_similarity_search_without_score` which was raising the
`OperationFailure` error. The mistake was syntax error for MongoDB
pipeline which has been corrected now.
- **Issue:** #22770
- [x] **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/
Thank you for contributing to LangChain!
- [x] **PR title**: "community: OCI GenAI embedding batch size"
- [x] **PR message**:
- **Issue:** #22985
- [ ] **Add tests and docs**: N/A
- [x] **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.
---------
Signed-off-by: Anders Swanson <anders.swanson@oracle.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- StopIteration can't be set on an asyncio.Future it raises a TypeError
and leaves the Future pending forever so we need to convert it to a
RuntimeError
- Refactor standard test classes to make them easier to configure
- Update openai to support stop_sequences init param
- Update groq to support stop_sequences init param
- Update fireworks to support max_retries init param
- Update ChatModel.bind_tools to type tool_choice
- Update groq to handle tool_choice="any". **this may be controversial**
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Langchain is very popular among developers in China, but there are still
no good Chinese books or documents, so I want to add my own Chinese
resources on langchain topics, hoping to give Chinese readers a better
experience using langchain. This is not a translation of the official
langchain documentation, but my understanding.
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
- **Support batch size**
Baichuan updates the document, indicating that up to 16 documents can be
imported at a time
- **Standardized model init arg names**
- baichuan_api_key -> api_key
- model_name -> model
Here we add `stream_usage` to ChatOpenAI as:
1. a boolean attribute
2. a kwarg to _stream and _astream.
Question: should the `stream_usage` attribute be `bool`, or `bool |
None`?
Currently I've kept it `bool` and defaulted to False. It was implemented
on
[ChatAnthropic](e832bbb486/libs/partners/anthropic/langchain_anthropic/chat_models.py (L535))
as a bool. However, to maintain support for users who access the
behavior via OpenAI's `stream_options` param, this ends up being
possible:
```python
llm = ChatOpenAI(model_kwargs={"stream_options": {"include_usage": True}})
assert not llm.stream_usage
```
(and this model will stream token usage).
Some options for this:
- it's ok
- make the `stream_usage` attribute bool or None
- make an \_\_init\_\_ for ChatOpenAI, set a `._stream_usage` attribute
and read `.stream_usage` from a property
Open to other ideas as well.
**Description:** This PR adds a chat model integration for [Snowflake
Cortex](https://docs.snowflake.com/en/user-guide/snowflake-cortex/llm-functions),
which gives an instant access to industry-leading large language models
(LLMs) trained by researchers at companies like Mistral, Reka, Meta, and
Google, including [Snowflake
Arctic](https://www.snowflake.com/en/data-cloud/arctic/), an open
enterprise-grade model developed by Snowflake.
**Dependencies:** Snowflake's
[snowpark](https://pypi.org/project/snowflake-snowpark-python/) library
is required for using this integration.
**Twitter handle:** [@gethouseware](https://twitter.com/gethouseware)
- [x] **Add tests and docs**:
1. integration tests:
`libs/community/tests/integration_tests/chat_models/test_snowflake.py`
2. unit tests:
`libs/community/tests/unit_tests/chat_models/test_snowflake.py`
3. example notebook: `docs/docs/integrations/chat/snowflake.ipynb`
- [x] **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/
Adds `response_metadata` to stream responses from OpenAI. This is
returned with `invoke` normally, but wasn't implemented for `stream`.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
## Description
While `YouRetriever` supports both You.com's Search and News APIs, news
is supported as an afterthought.
More specifically, not all of the News API parameters are exposed for
the user, only those that happen to overlap with the Search API.
This PR:
- improves support for both APIs, exposing the remaining News API
parameters while retaining backward compatibility
- refactor some REST parameter generation logic
- updates the docstring of `YouSearchAPIWrapper`
- add input validation and warnings to ensure parameters are properly
set by user
- 🚨 Breaking: Limit the news results to `k` items
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Ollama has a raw option now.
https://github.com/ollama/ollama/blob/main/docs/api.md
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, hwchase17.
---------
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
**Issue:**
When using the similarity_search_with_score function in
ElasticsearchStore, I expected to pass in the query_vector that I have
already obtained. I noticed that the _search function does support the
query_vector parameter, but it seems to be ineffective. I am attempting
to resolve this issue.
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
Update former pull request:
https://github.com/langchain-ai/langchain/pull/22654.
Modified `langchain_text_splitters.HTMLSectionSplitter`, where in the
latest version `dict` data structure is used to store sections from a
html document, in function `split_html_by_headers`. The header/section
element names serve as dict keys. This can be a problem when duplicate
header/section element names are present in a single html document.
Latter ones can replace former ones with the same name. Therefore some
contents can be miss after html text splitting is conducted.
Using a list to store sections can hopefully solve the problem. A Unit
test considering duplicate header names has been added.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:**
The generated relationships in the graph had no properties, but the
Relationship class was properly defined with properties. This made it
very difficult to transform conditional sentences into a graph. Adding
properties to relationships can solve this issue elegantly.
The changes expand on the existing LLMGraphTransformer implementation
but add the possibility to define allowed relationship properties like
this: LLMGraphTransformer(llm=llm, relationship_properties=["Condition",
"Time"],)
- **Issue:**
no issue found
- **Dependencies:**
n/a
- **Twitter handle:**
@IstvanSpace
-Quick Test
=================================================================
from dotenv import load_dotenv
import os
from langchain_community.graphs import Neo4jGraph
from langchain_experimental.graph_transformers import
LLMGraphTransformer
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.documents import Document
load_dotenv()
os.environ["NEO4J_URI"] = os.getenv("NEO4J_URI")
os.environ["NEO4J_USERNAME"] = os.getenv("NEO4J_USERNAME")
os.environ["NEO4J_PASSWORD"] = os.getenv("NEO4J_PASSWORD")
graph = Neo4jGraph()
llm = ChatOpenAI(temperature=0, model_name="gpt-4o")
llm_transformer = LLMGraphTransformer(llm=llm)
#text = "Harry potter likes pies, but only if it rains outside"
text = "Jack has a dog named Max. Jack only walks Max if it is sunny
outside."
documents = [Document(page_content=text)]
llm_transformer_props = LLMGraphTransformer(
llm=llm,
relationship_properties=["Condition"],
)
graph_documents_props =
llm_transformer_props.convert_to_graph_documents(documents)
print(f"Nodes:{graph_documents_props[0].nodes}")
print(f"Relationships:{graph_documents_props[0].relationships}")
graph.add_graph_documents(graph_documents_props)
---------
Co-authored-by: Istvan Lorincz <istvan.lorincz@pm.me>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Add admonition to the documentation to make sure users are aware that
the tool allows execution of code on the host machine using a python
interpreter (by design).
If the global `debug` flag is enabled, the agent will get the following
error in `FunctionCallbackHandler._on_tool_end` at runtime.
```
Error in ConsoleCallbackHandler.on_tool_end callback: AttributeError("'list' object has no attribute 'strip'")
```
By calling str() before strip(), the error was avoided.
This error can be seen at
[debugging.ipynb](https://github.com/langchain-ai/langchain/blob/master/docs/docs/how_to/debugging.ipynb).
- Issue: NA
- Dependencies: NA
- Twitter handle: https://x.com/kiarina37
Remove the REPL from community, and suggest an alternative import from
langchain_experimental.
Fix for this issue:
https://github.com/langchain-ai/langchain/issues/14345
This is not a bug in the code or an actual security risk. The python
REPL itself is behaving as expected.
The PR is done to appease blanket security policies that are just
looking for the presence of exec in the code.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR moves the validation of the decorator to a better place to avoid
creating bugs while deprecating code.
Prevent issues like this from arising:
https://github.com/langchain-ai/langchain/issues/22510
we should replace with a linter at some point that just does static
analysis
Preserves string content chunks for non tool call requests for
convenience.
One thing - Anthropic events look like this:
```
RawContentBlockStartEvent(content_block=TextBlock(text='', type='text'), index=0, type='content_block_start')
RawContentBlockDeltaEvent(delta=TextDelta(text='<thinking>\nThe', type='text_delta'), index=0, type='content_block_delta')
RawContentBlockDeltaEvent(delta=TextDelta(text=' provide', type='text_delta'), index=0, type='content_block_delta')
...
RawContentBlockStartEvent(content_block=ToolUseBlock(id='toolu_01GJ6x2ddcMG3psDNNe4eDqb', input={}, name='get_weather', type='tool_use'), index=1, type='content_block_start')
RawContentBlockDeltaEvent(delta=InputJsonDelta(partial_json='', type='input_json_delta'), index=1, type='content_block_delta')
```
Note that `delta` has a `type` field. With this implementation, I'm
dropping it because `merge_list` behavior will concatenate strings.
We currently have `index` as a special field when merging lists, would
it be worth adding `type` too?
If so, what do we set as a context block chunk? `text` vs.
`text_delta`/`tool_use` vs `input_json_delta`?
CC @ccurme @efriis @baskaryan
- **Description:** Some of the Cross-Encoder models provide scores in
pairs, i.e., <not-relevant score (higher means the document is less
relevant to the query), relevant score (higher means the document is
more relevant to the query)>. However, the `HuggingFaceCrossEncoder`
`score` method does not currently take into account the pair situation.
This PR addresses this issue by modifying the method to consider only
the relevant score if score is being provided in pair. The reason for
focusing on the relevant score is that the compressors select the top-n
documents based on relevance.
- **Issue:** #22556
- Please also refer to this
[comment](https://github.com/UKPLab/sentence-transformers/issues/568#issuecomment-729153075)
- **PR title**: [community] add chat model llamacpp
- **PR message**:
- **Description:** This PR introduces a new chat model integration with
llamacpp_python, designed to work similarly to the existing ChatOpenAI
model.
+ Work well with instructed chat, chain and function/tool calling.
+ Work with LangGraph (persistent memory, tool calling), will update
soon
- **Dependencies:** This change requires the llamacpp_python library to
be installed.
@baskaryan
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Updated ChatGroq doc string as per issue
https://github.com/langchain-ai/langchain/issues/22296:"langchain_groq:
updated docstring for ChatGroq in langchain_groq to match that of the
description (in the appendix) provided in issue
https://github.com/langchain-ai/langchain/issues/22296. "
Issue: This PR is in response to issue
https://github.com/langchain-ai/langchain/issues/22296, and more
specifically the ChatGroq model. In particular, this PR updates the
docstring for langchain/libs/partners/groq/langchain_groq/chat_model.py
by adding the following sections: Instantiate, Invoke, Stream, Async,
Tool calling, Structured Output, and Response metadata. I used the
template from the Anthropic implementation and referenced the Appendix
of the original issue post. I also noted that: `usage_metadata `returns
none for all ChatGroq models I tested; there is no mention of image
input in the ChatGroq documentation; unlike that of ChatHuggingFace,
`.stream(messages)` for ChatGroq returned blocks of output.
---------
Co-authored-by: lucast2021 <lucast2021@headroyce.org>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR adds the feature add Prem Template feature in ChatPremAI.
Additionally it fixes a minor bug for API auth error when API passed
through arguments.
Description: Adjusting the syntax for creating the vectorstore
collection (in the case of automatic embedding computation) for the most
idiomatic way to submit the stored secret name.
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description:**
Update the NVIDIA Riva tool documentation to use NVIDIA NIM for the LLM.
Show how to use NVIDIA NIMs and link to documentation for LangChain with
NIM.
---------
Co-authored-by: Hayden Wolff <hwolff@nvidia.com>
Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com>
This PR addresses several lint errors in the core package of LangChain.
Specifically, the following issues were fixed:
1.Unexpected keyword argument "required" for "Field" [call-arg]
2.tests/integration_tests/chains/test_cpal.py:263: error: Unexpected
keyword argument "narrative_input" for "QueryModel" [call-arg]
This should make it obvious that a few of the agents in langchain
experimental rely on the python REPL as a tool under the hood, and will
force users to opt-in.
This downgrades `Function/tool calling` from a h3 to an h4 which means
it'll no longer show up in the right sidebar, but any direct links will
still work. I think that is ok, but LMK if you disapprove.
CC @hwchase17 @eyurtsev @rlancemartin
We need to use a different version of numpy for py3.8 and py3.12 in
pyproject.
And so do projects that use that Python version range and import
langchain.
- **Twitter handle:** _cbornet
**Description**
sqlalchemy uses "sqlalchemy.engine.URL" type for db uri argument.
Added 'URL' type for compatibility.
**Issue**: None
**Dependencies:** None
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** This implements `show_progress` more consistently
(i.e. it is also added to the `HuggingFaceBgeEmbeddings` object).
- **Issue:** This implements `show_progress` more consistently in the
embeddings huggingface classes. Previously this could have been set via
`encode_kwargs`.
- **Dependencies:** None
- **Twitter handle:** @jonzeolla
… (#22795)
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.
**Description:** This PR updates the documentation to reflect the recent
code changes.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- **Description:** A change I submitted recently introduced a bug in
`YoutubeLoader`'s `LINES` output format. In those conditions, curly
braces ("`{}`") creates a set, not a dictionary. This bugfix explicitly
specifies that a dictionary is created.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter:** lsloan_umich
- **Mastodon:**
[lsloan@mastodon.social](https://mastodon.social/@lsloan)
changed "# 🌟Recognition" to "### 🌟 Recognition" to match the rest of the
subheadings.
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.
Thank you for contributing to LangChain!
- [x] **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"
- [x] **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!
- [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.
- [x] **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>
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
Support for old clients (Thin and Thick) Oracle Vector Store
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
Support for old clients (Thin and Thick) Oracle Vector Store
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
Have our own local tests
---------
Co-authored-by: rohan.aggarwal@oracle.com <rohaagga@phoenix95642.dev3sub2phx.databasede3phx.oraclevcn.com>
- **Description:** Add a new format, `CHUNKS`, to
`langchain_community.document_loaders.youtube.YoutubeLoader` which
creates multiple `Document` objects from YouTube video transcripts
(captions), each of a fixed duration. The metadata of each chunk
`Document` includes the start time of each one and a URL to that time in
the video on the YouTube website.
I had implemented this for UMich (@umich-its-ai) in a local module, but
it makes sense to contribute this to LangChain community for all to
benefit and to simplify maintenance.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter:** lsloan_umich
- **Mastodon:**
[lsloan@mastodon.social](https://mastodon.social/@lsloan)
With regards to **tests and documentation**, most existing features of
the `YoutubeLoader` class are not tested. Only the
`YoutubeLoader.extract_video_id()` static method had a test. However,
while I was waiting for this PR to be reviewed and merged, I had time to
add a test for the chunking feature I've proposed in this PR.
I have added an example of using chunking to the
`docs/docs/integrations/document_loaders/youtube_transcript.ipynb`
notebook.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR add supports for Azure Cosmos DB for NoSQL vector store.
Summary:
Description: added vector store integration for Azure Cosmos DB for
NoSQL Vector Store,
Dependencies: azure-cosmos dependency,
Tag maintainer: @hwchase17, @baskaryan @efriis @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
- **Description:** As pointed out in this issue #22770, DocumentDB
`similarity_search` does not support filtering through metadata which
this PR adds by passing in the parameter `filter`. Also this PR fixes a
minor Documentation error.
- **Issue:** #22770
---------
Co-authored-by: Erick Friis <erickfriis@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description:** Ollama vision with messages in OpenAI-style support `{
"image_url": { "url": ... } }`
**Issue:** #22460
Added flexible solution for ChatOllama to support chat messages with
images. Works when you provide either `image_url` as a string or as a
dict with "url" inside (like OpenAI does). So it makes available to use
tuples with `ChatPromptTemplate.from_messages()`
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Thank you for contributing to LangChain!
- [ ] **PR title**: "langchain: Fix chain_filter.py to be compatible
with async"
- [ ] **PR message**:
- **Description:** chain_filter is not compatible with async.
- **Twitter handle:** pprados
- [X ] **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/
---------
Signed-off-by: zhangwangda <zhangwangda94@163.com>
Co-authored-by: Prakul <discover.prakul@gmail.com>
Co-authored-by: Lei Zhang <zhanglei@apache.org>
Co-authored-by: Gin <ictgtvt@gmail.com>
Co-authored-by: wangda <38549158+daziz@users.noreply.github.com>
Co-authored-by: Max Mulatz <klappradla@posteo.net>
Thank you for contributing to LangChain!
### Description
Fix the example in the docstring of redis store.
Change the initilization logic and remove redundant check, enhance error
message.
### Issue
The example in docstring of how to use redis store was wrong.
### Dependencies
Nothing
- [ ] **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.
- [x] **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/
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- [ ] **Miscellaneous updates and fixes**:
- **Description:** Handled error in querying; quotes in table names;
updated gpudb API
- **Issue:** Threw an error with an error message difficult to
understand if a query failed or returned no records
- **Dependencies:** Updated GPUDB API version to `7.2.0.9`
@baskaryan @hwchase17
- **Description:** allow to use partial variables to pass `top_k` and
`table_info`
- **Issue:** no
- **Dependencies:** no
- **Twitter handle:** @gymnstcs
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** This PR updates the `WandbTracer` to work with the
new RunV2 API so that wandb Traces logging works correctly for new
LangChain versions. Here's an example
[run](https://wandb.ai/parambharat/langchain-tracing/runs/wpm99ftq) from
the existing tests
- **Issue:** https://github.com/wandb/wandb/issues/7762
- **Twitter handle:** @ParamBharat
_If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17._
**Updated ChatHuggingFace doc string as per issue #22296**:
"langchain_huggingface: updated docstring for ChatHuggingFace in
langchain_huggingface to match that of the description (in the appendix)
provided in issue #22296. "
**Issue:** This PR is in response to issue #22296, and more specifically
ChatHuggingFace model. In particular, this PR updates the docstring for
langchain/libs/partners/hugging_face/langchain_huggingface/chat_models/huggingface.py
by adding the following sections: Instantiate, Invoke, Stream, Async,
Tool calling, and Response metadata. I used the template from the
Anthropic implementation and referenced the Appendix of the original
issue post. I also noted that: langchain_community hugging face llms do
not work with langchain_huggingface's ChatHuggingFace model (at least
for me); the .stream(messages) functionality of ChatHuggingFace only
returned a block of response.
---------
Co-authored-by: lucast2021 <lucast2021@headroyce.org>
Co-authored-by: Bagatur <baskaryan@gmail.com>
LLMs struggle with Graph RAG, because it's different from vector RAG in
a way that you don't provide the whole context, only the answer and the
LLM has to believe. However, that doesn't really work a lot of the time.
However, if you wrap the context as function response the accuracy is
much better.
btw... `union[LLMChain, Runnable]` is linting fun, that's why so many
ignores
**Description:** this PR adds Volcengine Rerank capability to Langchain,
you can find Volcengine Rerank API from
[here](https://www.volcengine.com/docs/84313/1254474) &
[here](https://www.volcengine.com/docs/84313/1254605).
[Volcengine](https://www.volcengine.com/) is a cloud service platform
developed by ByteDance, the parent company of TikTok. You can obtain
Volcengine API AK/SK from
[here](https://www.volcengine.com/docs/84313/1254553).
**Dependencies:** VolcengineRerank depends on `volcengine` python
package.
**Twitter handle:** my twitter/x account is https://x.com/LastMonopoly
and I'd like a mention, thank you!
**Tests and docs**
1. integration test: `test_volcengine_rerank.py`
2. example notebook: `volcengine_rerank.ipynb`
**Lint and test**: I have run `make format`, `make lint` and `make test`
from the root of the package I've modified.
Hi 👋
First off, thanks a ton for your work on this 💚 Really appreciate what
you're providing here for the community.
## Description
This PR adds a basic language parser for the
[Elixir](https://elixir-lang.org/) programming language. The parser code
is based upon the approach outlined in
https://github.com/langchain-ai/langchain/pull/13318: it's using
`tree-sitter` under the hood and aligns with all the other `tree-sitter`
based parses added that PR.
The `CHUNK_QUERY` I'm using here is probably not the most sophisticated
one, but it worked for my application. It's a starting point to provide
"core" parsing support for Elixir in LangChain. It enables people to use
the language parser out in real world applications which may then lead
to further tweaking of the queries. I consider this PR just the ground
work.
- **Dependencies:** requires `tree-sitter` and `tree-sitter-languages`
from the extended dependencies
- **Twitter handle:**`@bitcrowd`
## Checklist
- [x] **PR title**: "package: description"
- [x] **Add tests and docs**
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified.
<!-- If no one reviews your PR within a few days, please @-mention one
of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. -->
The fact that we outsourced pgvector to another project has an
unintended effect. The mapping dictionary found by
`_get_builtin_translator()` cannot recognize the new version of pgvector
because it comes from another package.
`SelfQueryRetriever` no longer knows `PGVector`.
I propose to fix this by creating a global dictionary that can be
populated by various database implementations. Thus, importing
`langchain_postgres` will allow the registration of the `PGvector`
mapping.
But for the moment I'm just adding a lazy import
Furthermore, the implementation of _get_builtin_translator()
reconstructs the BUILTIN_TRANSLATORS variable with each invocation,
which is not very efficient. A global map would be an optimization.
- **Twitter handle:** pprados
@eyurtsev, can you review this PR? And unlock the PR [Add async mode for
pgvector](https://github.com/langchain-ai/langchain-postgres/pull/32)
and PR [community[minor]: Add SQL storage
implementation](https://github.com/langchain-ai/langchain/pull/22207)?
Are you in favour of a global dictionary-based implementation of
Translator?
## Description
This PR addresses a logging inconsistency in the `get_user_agent`
function. Previously, the function was using the root logger to log a
warning message when the "USER_AGENT" environment variable was not set.
This bypassed the custom logger `log` that was created at the start of
the module, leading to potential inconsistencies in logging behavior.
Changes:
- Replaced `logging.warning` with `log.warning` in the `get_user_agent`
function to ensure that the custom logger is used.
This change ensures that all logging in the `get_user_agent` function
respects the configurations of the custom logger, leading to more
consistent and predictable logging behavior.
## Dependencies
None
## Issue
None
## Tests and docs
☝🏻 see description
## `make format`, `make lint` & `cd libs/community; make test`
```shell
> make format
poetry run ruff format docs templates cookbook
1417 files left unchanged
poetry run ruff check --select I --fix docs templates cookbook
All checks passed!
```
```shell
> make lint
poetry run ruff check docs templates cookbook
All checks passed!
poetry run ruff format docs templates cookbook --diff
1417 files already formatted
poetry run ruff check --select I docs templates cookbook
All checks passed!
git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
```
~cd libs/community; make test~ too much dependencies for integration ...
```shell
> poetry run pytest tests/unit_tests
....
==== 884 passed, 466 skipped, 4447 warnings in 15.93s ====
```
I choose you randomly : @ccurme
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)
Corrected a typo in the AutoGPT example notebook. Changed "Needed synce
jupyter runs an async eventloop" to "Needed since Jupyter runs an async
event loop".
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.
removed an extra space before the period in the "Click **Create
codespace on master**." line.
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.
- [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>
Thank you for contributing to LangChain!
- [x] **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"
- [x] **PR message**:
- **Description:** This PR corrects the return type in the docstring of
the `docs/api_reference/create_api_rst.py/_load_package_modules`
function. The return type was previously described as a list of
Co-authored-by: suganthsolamanraja <suganth.solamanraja@techjays..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.
Corrected the phrase "complete done" to "completely done" for better
grammatical accuracy and clarity in the Agents section of the README.
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: ccurme <chester.curme@gmail.com>
More direct entrypoint for a common use-case. Meant to give people a
more hands-on intro to document loaders/loading data from different data
sources as well.
Some duplicate content for RAG and extraction (to show what you can do
with the loaded documents), but defers to the appropriate sections
rather than going too in-depth.
@baskaryan @hwchase17
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/
This PR adds deduplication of callback handlers in merge_configs.
Fix for this issue:
https://github.com/langchain-ai/langchain/issues/22227
The issue appears when the code is:
1) running python >=3.11
2) invokes a runnable from within a runnable
3) binds the callbacks to the child runnable from the parent runnable
using with_config
In this case, the same callbacks end up appearing twice: (1) the first
time from with_config, (2) the second time with langchain automatically
propagating them on behalf of the user.
Prior to this PR this will emit duplicate events:
```python
@tool
async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks
"""Ask question"""
template = ChatPromptTemplate.from_messages(
[
(
"human",
"'{question}"
)
]
)
chain = template | chat_model.with_config(
{
"callbacks": callbacks, # <-- Propagate callbacks
}
)
return await chain.ainvoke({"question": question})
```
Prior to this PR this will work work correctly (no duplicate events):
```python
@tool
async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks
"""Ask question"""
template = ChatPromptTemplate.from_messages(
[
(
"human",
"'{question}"
)
]
)
chain = template | chat_model
return await chain.ainvoke({"question": question}, {"callbacks": callbacks})
```
This will also work (as long as the user is using python >= 3.11) -- as
langchain will automatically propagate callbacks
```python
@tool
async def get_items(question: str,):
"""Ask question"""
template = ChatPromptTemplate.from_messages(
[
(
"human",
"'{question}"
)
]
)
chain = template | chat_model
return await chain.ainvoke({"question": question})
```
Thank you for contributing to LangChain!
**Description:** update to the Vectara / Langchain integration to
integrate new Vectara capabilities:
- Full RAG implemented as a Runnable with as_rag()
- Vectara chat supported with as_chat()
- Both support streaming response
- Updated documentation and example notebook to reflect all the changes
- Updated Vectara templates
**Twitter handle:** ofermend
**Add tests and docs**: no new tests or docs, but updated both existing
tests and existing docs
Thank you for contributing to LangChain!
- [x] **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"
- [x] **PR message**:
- **Description:** Updated dead link referencing chroma docs in Chroma
notebook under vectorstores
…s and Opensearch Semantic Cache
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>
- [ ] **Packages affected**:
- community: fix `cosine_similarity` to support simsimd beyond 3.7.7
- partners/milvus: fix `cosine_similarity` to support simsimd beyond
3.7.7
- partners/mongodb: fix `cosine_similarity` to support simsimd beyond
3.7.7
- partners/pinecone: fix `cosine_similarity` to support simsimd beyond
3.7.7
- partners/qdrant: fix `cosine_similarity` to support simsimd beyond
3.7.7
- [ ] **Broadcast operation failure while using simsimd beyond v3.7.7**:
- **Description:** I was using simsimd 4.3.1 and the unsupported operand
type issue popped up. When I checked out the repo and ran the tests,
they failed as well (have attached a screenshot for that). Looks like it
is a variant of https://github.com/langchain-ai/langchain/issues/18022 .
Prior to 3.7.7, simd.cdist returned an ndarray but now it returns
simsimd.DistancesTensor which is ineligible for a broadcast operation
with numpy. With this change, it also remove the need to explicitly cast
`Z` to numpy array
- **Issue:** #19905
- **Dependencies:** No
- **Twitter handle:** https://x.com/GetzJoydeep
<img width="1622" alt="Screenshot 2024-05-29 at 2 50 00 PM"
src="https://github.com/langchain-ai/langchain/assets/31132555/fb27b383-a9ae-4a6f-b355-6d503b72db56">
- [ ] **Considerations**:
1. I started with community but since similar changes were there in
Milvus, MongoDB, Pinecone, and QDrant so I modified their files as well.
If touching multiple packages in one PR is not the norm, then I can
remove them from this PR and raise separate ones
2. I have run and verified that the tests work. Since, only MongoDB had
tests, I ran theirs and verified it works as well. Screenshots attached
:
<img width="1573" alt="Screenshot 2024-05-29 at 2 52 13 PM"
src="https://github.com/langchain-ai/langchain/assets/31132555/ce87d1ea-19b6-4900-9384-61fbc1a30de9">
<img width="1614" alt="Screenshot 2024-05-29 at 3 33 51 PM"
src="https://github.com/langchain-ai/langchain/assets/31132555/6ce1d679-db4c-4291-8453-01028ab2dca5">
I have added a test for simsimd. I feel it may not go well with the
CI/CD setup as installing simsimd is not a dependency requirement. I
have just imported simsimd to ensure simsimd cosine similarity is
invoked. However, its not a good approach. Suggestions are welcome and I
can make the required changes on the PR. Please provide guidance on the
same as I am new to the community.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
### Description
Add tools implementation to `ChatEdenAI`:
- `bind_tools()`
- `with_structured_output()`
### Documentation
Updated `docs/docs/integrations/chat/edenai.ipynb`
### Notes
We don´t support stream with tools as of yet. If stream is called with
tools we directly yield the whole message from `generate` (implemented
the same way as Anthropic did).
- [x] **PR title**: Update docstrings for OpenAI base.py
-**Description:** Updated the docstring of few OpenAI functions for a
better understanding of the function.
- **Issue:** #21983
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Noticing errors logged in some situations when tracing with Langsmith:
```python
from langchain_core.pydantic_v1 import BaseModel
from langchain_anthropic import ChatAnthropic
class AnswerWithJustification(BaseModel):
"""An answer to the user question along with justification for the answer."""
answer: str
justification: str
llm = ChatAnthropic(model="claude-3-haiku-20240307")
structured_llm = llm.with_structured_output(AnswerWithJustification)
list(structured_llm.stream("What weighs more a pound of bricks or a pound of feathers"))
```
```
Error in LangChainTracer.on_chain_end callback: AttributeError("'NoneType' object has no attribute 'append'")
[AnswerWithJustification(answer='A pound of bricks and a pound of feathers weigh the same amount.', justification='This is because a pound is a unit of mass, not volume. By definition, a pound of any material, whether bricks or feathers, will weigh the same - one pound. The physical size or volume of the materials does not matter when measuring by mass. So a pound of bricks and a pound of feathers both weigh exactly one pound.')]
```
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.
The Vectorstore's API `as_retriever` doesn't expose explicitly the
parameters `search_type` and `search_kwargs` and so these are not well
documented.
This PR improves `as_retriever` for the Cassandra VectorStore by making
these parameters explicit.
NB: An alternative would have been to modify `as_retriever` in
`Vectorstore`. But there's probably a good reason these were not exposed
in the first place ? Is it because implementations may decide to not
support them and have fixed values when creating the
VectorStoreRetriever ?
- **Description:** Added support for using HuggingFacePipeline in
ChatHuggingFace (previously it was only usable with API endpoints,
probably by oversight).
- **Issue:** #19997
- **Dependencies:** none
- **Twitter handle:** none
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
This PR introduces namespace support for Upstash Vector Store, which
would allow users to partition their data in the vector index.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
- **Description:**
This PR fixes a rendering issue in the docs (Python notebook) of HANA
Cloud Vector Engine.
- **Issue:** N/A
- **Dependencies:** no new dependencies added
File of the fixed notebook:
`docs/docs/integrations/vectorstores/hanavector.ipynb`
## Description
This PR allows passing the HTMLSectionSplitter paths to xslt files. It
does so by fixing two trivial bugs with how passed paths were being
handled. It also changes the default value of the param `xslt_path` to
`None` so the special case where the file was part of the langchain
package could be handled.
## Issue
#22175
- [X] **PR title**: "community: added optional params to Airtable
table.all()"
- [X] **PR message**:
- **Description:** Add's **kwargs to AirtableLoader to allow for kwargs:
https://pyairtable.readthedocs.io/en/latest/api.html#pyairtable.Table.all
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** parakoopa88
- [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.
- [X] **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/
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>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
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"
"community/embeddings: update oracleai.py"
- [ ] **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!
Adding oracle VECTOR_ARRAY_T support.
- [ ] **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.
Tests are not impacted.
- [ ] **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/
Done.
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.
- **Description:** When I was running the SparkLLMTextEmbeddings,
app_id, api_key and api_secret are all correct, but it cannot run
normally using the current URL.
```python
# example
from langchain_community.embeddings import SparkLLMTextEmbeddings
embedding= SparkLLMTextEmbeddings(
spark_app_id="my-app-id",
spark_api_key="my-api-key",
spark_api_secret="my-api-secret"
)
embedding= "hello"
print(spark.embed_query(text1))
```
So I updated the url and request body parameters according to
[Embedding_api](https://www.xfyun.cn/doc/spark/Embedding_api.html), now
it is runnable.
**Description:** [IPEX-LLM](https://github.com/intel-analytics/ipex-llm)
is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local
PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low
latency. This PR adds ipex-llm integrations to langchain for BGE
embedding support on both Intel CPU and GPU.
**Dependencies:** `ipex-llm`, `sentence-transformers`
**Contribution maintainer**: @Oscilloscope98
**tests and docs**:
- langchain/docs/docs/integrations/text_embedding/ipex_llm.ipynb
- langchain/docs/docs/integrations/text_embedding/ipex_llm_gpu.ipynb
-
langchain/libs/community/tests/integration_tests/embeddings/test_ipex_llm.py
---------
Co-authored-by: Shengsheng Huang <shannie.huang@gmail.com>
Anthropic's streaming treats tool calls as different content parts
(streamed back with a different index) from normal content in the
`content`.
This means that we need to update our chunk-merging logic to handle
chunks with multi-part content. The alternative is coerceing Anthropic's
responses into a string, but we generally like to preserve model
provider responses faithfully when we can. This will also likely be
useful for multimodal outputs in the future.
This current PR does unfortunately make `index` a magic field within
content parts, but Anthropic and OpenAI both use it at the moment to
determine order anyway. To avoid cases where we have content arrays with
holes and to simplify the logic, I've also restricted merging to chunks
in order.
TODO: tests
CC @baskaryan @ccurme @efriis
- This fixes all the tracing issues with people still using
get_relevant_docs, and a change we need for 0.3 anyway
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.
- **Description:** The `ApifyWrapper` class expects `apify_api_token` to
be passed as a named parameter or set as an environment variable. But
the corresponding field was missing in the class definition causing the
argument to be ignored when passed as a named param. This patch fixes
that.
- This is a pattern that shows up occasionally in langgraph questions,
people chain a graph to something else after, and want to pass the graph
some kwargs (eg. stream_mode)
- [x] How to: use a vector store to retrieve data
- [ ] How to: generate multiple queries to retrieve data for
- [x] How to: use contextual compression to compress the data retrieved
- [x] How to: write a custom retriever class
- [x] How to: add similarity scores to retriever results
^ done last month
- [x] How to: combine the results from multiple retrievers
- [x] How to: reorder retrieved results to mitigate the "lost in the
middle" effect
- [x] How to: generate multiple embeddings per document
^ this PR
- [ ] How to: retrieve the whole document for a chunk
- [ ] How to: generate metadata filters
- [ ] How to: create a time-weighted retriever
- [ ] How to: use hybrid vector and keyword retrieval
^ todo
1/ added section at start with full code
2/ removed retriever tool (was just distracting)
3/ added section on starting a new conversation
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
LangSmith and LangChain context var handling evolved in parallel since
originally we didn't expect people to want to interweave the decorator
and langchain code.
Once we get a new langsmith release, this PR will let you seemlessly
hand off between @traceable context and runnable config context so you
can arbitrarily nest code.
It's expected that this fails right now until we get another release of
the SDK
### Issue: #22299
### descriptions
The documentation appears to be wrong. When the user actually sets this
parameter "asynchronous" to be True, it fails because the __init__
function of FAISS class doesn't allow this parameter. In fact, most of
the class/instance functions of this class have both the sync/async
version, so it looks like what we need is just to remove this parameter
from the doc.
Thank you for contributing to LangChain!
- [x] **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"
- [x] **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: Lifu Wu <lifu@nextbillion.ai>
- [x] Docs Update: Ollama
- llm/ollama
- Switched to using llama3 as model with reference to templating and
prompting
- Added concurrency notes to llm/ollama docs
- chat_models/ollama
- Added concurrency notes to llm/ollama docs
- text_embedding/ollama
- include example for specific embedding models from Ollama
- **Description:** This PR contains a bugfix which result in malfunction
of multi-turn conversation in QianfanChatEndpoint and adaption for
ToolCall and ToolMessage
ChatOpenAI supports a kwarg `stream_options` which can take values
`{"include_usage": True}` and `{"include_usage": False}`.
Setting include_usage to True adds a message chunk to the end of the
stream with usage_metadata populated. In this case the final chunk no
longer includes `"finish_reason"` in the `response_metadata`. This is
the current default and is not yet released. Because this could be
disruptive to workflows, here we remove this default. The default will
now be consistent with OpenAI's API (see parameter
[here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)).
Examples:
```python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI()
for chunk in llm.stream("hi"):
print(chunk)
```
```
content='' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='Hello' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='!' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='' response_metadata={'finish_reason': 'stop'} id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
```
```python
for chunk in llm.stream("hi", stream_options={"include_usage": True}):
print(chunk)
```
```
content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='Hello' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='!' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='' response_metadata={'finish_reason': 'stop'} id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}
```
```python
llm = ChatOpenAI().bind(stream_options={"include_usage": True})
for chunk in llm.stream("hi"):
print(chunk)
```
```
content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='Hello' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='!' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='' response_metadata={'finish_reason': 'stop'} id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}
```
Add kwargs in add_documents function
**langchain**: Add **kwargs in parent_document_retriever"
- **Add kwargs for `add_document` in `parent_document_retriever.py`**
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Issue: The `arXiv` page is missing the arxiv paper references from the
`langchain/cookbook`.
PR: Added the cookbook references.
Result: `Found 29 arXiv references in the 3 docs, 21 API Refs, 5
Templates, and 18 Cookbooks.` - much more references are visible now.
**Description:** Update langchainhub integration test dependency and add
an integration test for pulling private prompt
**Dependencies:** langchainhub 0.1.16
Change 'FIREWALL' to 'FIRECRAWL' as I believe this may have been in
error. Other docs refer to 'FIRECRAWL_API_KEY'.
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>
# Description
## Problem
`Runnable.get_graph` fails when `InputType` or `OutputType` property
raises `TypeError`.
-
003c98e5b4/libs/core/langchain_core/runnables/base.py (L250-L274)
-
003c98e5b4/libs/core/langchain_core/runnables/base.py (L394-L396)
This problem prevents getting a graph of `Runnable` objects whose
`InputType` or `OutputType` property raises `TypeError` but whose
`invoke` works well, such as `langchain.output_parsers.RegexParser`,
which I have already pointed out in #19792 that a `TypeError` would
occur.
## Solution
- Add `try-except` syntax to handle `TypeError` to the codes which get
`input_node` and `output_node`.
# Issue
- #19801
# Twitter Handle
- [hmdev3](https://twitter.com/hmdev3)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- [ ] **PR title**: "Fix list handling in Clova embeddings example
documentation"
- Description:
Fixes a bug in the Clova Embeddings example documentation where
document_text was incorrectly wrapped in an additional list.
- Rationale
The embed_documents method expects a list, but the previous example
wrapped document_text in an unnecessary additional list, causing an
error. The updated example correctly passes document_text directly to
the method, ensuring it functions as intended.
Added the missing verb "is" and a comma to the text in the Prompt
Templates description within the Build a Simple LLM Application tutorial
for more clarity.
- **Description:** updated documentation for llama, falcona and gemma on
Vertex AI Model garden
- **Issue:** NA
- **Dependencies:** NA
- **Twitter handle:** NA
@lkuligin for review
---------
Co-authored-by: adityarane@google.com <adityarane@google.com>
Thank you for contributing to LangChain!
- [x] **PR title**: community: Add Zep Cloud components + docs +
examples
- [x] **PR message**:
We have recently released our new zep-cloud sdks that are compatible
with Zep Cloud (not Zep Open Source). We have also maintained our Cloud
version of langchain components (ChatMessageHistory, VectorStore) as
part of our sdks. This PRs goal is to port these components to langchain
community repo, and close the gap with the existing Zep Open Source
components already present in community repo (added
ZepCloudMemory,ZepCloudVectorStore,ZepCloudRetriever).
Also added a ZepCloudChatMessageHistory components together with an
expression language example ported from our repo. We have left the
original open source components intact on purpose as to not introduce
any breaking changes.
- **Issue:** -
- **Dependencies:** Added optional dependency of our new cloud sdk
`zep-cloud`
- **Twitter handle:** @paulpaliychuk51
- [x] **Add tests and docs**
- [x] **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, hwchase17.
3 fixes of DuckDB vector store:
- unify defaults in constructor and from_texts (users no longer have to
specify `vector_key`).
- include search similarity into output metadata (fixes#20969)
- significantly improve performance of `from_documents`
Dependencies: added Pandas to speed up `from_documents`.
I was thinking about CSV and JSON options, but I expect trouble loading
JSON values this way and also CSV and JSON options require storing data
to disk.
Anyway, the poetry file for langchain-community already contains a
dependency on Pandas.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Generates release notes based on a `git log` command with title names
Aiming to improve to splitting out features vs. bugfixes using
conventional commits in the coming weeks.
Will work for any monorepo packages
- **Description:** this PR gives clickhouse client the ability to use a
secure connection to the clickhosue server
- **Issue:** fixes#22082
- **Dependencies:** -
- **Twitter handle:** `_codingcoffee_`
Signed-off-by: Ameya Shenoy <shenoy.ameya@gmail.com>
Co-authored-by: Shresth Rana <shresth@grapevine.in>
OpenAI recently added a `stream_options` parameter to its chat
completions API (see [release
notes](https://platform.openai.com/docs/changelog/added-chat-completions-stream-usage)).
When this parameter is set to `{"usage": True}`, an extra "empty"
message is added to the end of a stream containing token usage. Here we
propagate token usage to `AIMessage.usage_metadata`.
We enable this feature by default. Streams would now include an extra
chunk at the end, **after** the chunk with
`response_metadata={'finish_reason': 'stop'}`.
New behavior:
```
[AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='Hello', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='!', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde', usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17})]
```
Old behavior (accessible by passing `stream_options={"include_usage":
False}` into (a)stream:
```
[AIMessageChunk(content='', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='Hello', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='!', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-1312b971-c5ea-4d92-9015-e6604535f339')]
```
From what I can tell this is not yet implemented in Azure, so we enable
only for ChatOpenAI.
Thank you for contributing to LangChain!
- [X] **PR title**: community: Updated langchain-community PremAI
documentation
- [X] **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/
Hey, I'm Sasha. The SDK engineer from [Comet](https://comet.com).
This PR updates the CometTracer class.
Added metadata to CometTracerr. From now on, both chains and spans will
send it.
* Lint for usage of standard xml library
* Add forced opt-in for quip client
* Actual security issue is with underlying QuipClient not LangChain
integration (since the client is doing the parsing), but adding
enforcement at the LangChain level.
- **Description:** I've added a tab on embedding text with LangChain
using Hugging Face models to here:
https://python.langchain.com/v0.2/docs/how_to/embed_text/. HF was
mentioned in the running text, but not in the tabs, which I thought was
odd.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** No need, this is tiny :)
Also, I had a ton of issues with the poetry docs/lint install, so I
haven't linted this. Apologies for that.
cc @Jofthomas
- Tom Aarsen
If tool_use blocks and tool_calls with overlapping IDs are present,
prefer the values of the tool_calls. Allows for mutating AIMessages just
via tool_calls.
**PR message**:
Update `hub.pull("rlm/map-prompt")` to `hub.pull("rlm/reduce-prompt")`
in summarization.ipynb
**Description:**
Fix typo in prompt hub link from `reduce_prompt =
hub.pull("rlm/map-prompt")` to `reduce_prompt =
hub.pull("rlm/reduce-prompt")` following next issue
**Issue:** #22014
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
```python
class UsageMetadata(TypedDict):
"""Usage metadata for a message, such as token counts.
Attributes:
input_tokens: (int) count of input (or prompt) tokens
output_tokens: (int) count of output (or completion) tokens
total_tokens: (int) total token count
"""
input_tokens: int
output_tokens: int
total_tokens: int
```
```python
class AIMessage(BaseMessage):
...
usage_metadata: Optional[UsageMetadata] = None
"""If provided, token usage information associated with the message."""
...
```
- **Description:** When I was running the sparkllm, I found that the
default parameters currently used could no longer run correctly.
- original parameters & values:
- spark_api_url: "wss://spark-api.xf-yun.com/v3.1/chat"
- spark_llm_domain: "generalv3"
```python
# example
from langchain_community.chat_models import ChatSparkLLM
spark = ChatSparkLLM(spark_app_id="my_app_id",
spark_api_key="my_api_key", spark_api_secret="my_api_secret")
spark.invoke("hello")
```
So I updated them to 3.5 (same as sparkllm official website). After the
update, they can be used normally.
- new parameters & values:
- spark_api_url: "wss://spark-api.xf-yun.com/v3.5/chat"
- spark_llm_domain: "generalv3.5"
This pull request addresses and fixes exception handling in the
UpstageLayoutAnalysisParser and enhances the test coverage by adding
error exception tests for the document loader. These improvements ensure
robust error handling and increase the reliability of the system when
dealing with external API calls and JSON responses.
### Changes Made
1. Fix Request Exception Handling:
- Issue: The existing implementation of UpstageLayoutAnalysisParser did
not properly handle exceptions thrown by the requests library, which
could lead to unhandled exceptions and potential crashes.
- Solution: Added comprehensive exception handling for
requests.RequestException to catch any request-related errors. This
includes logging the error details and raising a ValueError with a
meaningful error message.
2. Add Error Exception Tests for Document Loader:
- New Tests: Introduced new test cases to verify the robustness of the
UpstageLayoutAnalysisLoader against various error scenarios. The tests
ensure that the loader gracefully handles:
- RequestException: Simulates network issues or invalid API requests to
ensure appropriate error handling and user feedback.
- JSONDecodeError: Simulates scenarios where the API response is not a
valid JSON, ensuring the system does not crash and provides clear error
messaging.
**Description:**
- Added propagation of document metadata from O365BaseLoader to
FileSystemBlobLoader (O365BaseLoader uses FileSystemBlobLoader under the
hood).
- This is done by passing dictionary `metadata_dict`: key=filename and
value=dictionary containing document's metadata
- Modified `FileSystemBlobLoader` to accept the `metadata_dict`, use
`mimetype` from it (if available) and pass metadata further into blob
loader.
**Issue:**
- `O365BaseLoader` under the hood downloads documents to temp folder and
then uses `FileSystemBlobLoader` on it.
- However metadata about the document in question is lost in this
process. In particular:
- `mime_type`: `FileSystemBlobLoader` guesses `mime_type` from the file
extension, but that does not work 100% of the time.
- `web_url`: this is useful to keep around since in RAG LLM we might
want to provide link to the source document. In order to work well with
document parsers, we pass the `web_url` as `source` (`web_url` is
ignored by parsers, `source` is preserved)
**Dependencies:**
None
**Twitter handle:**
@martintriska1
Please review @baskaryan
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Thank you for contributing to LangChain!
- [ ] **PR title**: "Add CloudBlobLoader"
- community: Add CloudBlobLoader
- [ ] **PR message**: Add cloud blob loader
- **Description:**
Langchain provides several approaches to read different file formats:
Specific loaders (`CVSLoader`) or blob-compatible loaders
(`FileSystemBlobLoader`). The only implementation proposed for
BlobLoader is `FileSystemBlobLoader`.
Many projects retrieve files from cloud storage. We propose a new
implementation of `BlobLoader` to read files from the three cloud
storage systems. The interface is strictly identical to
`FileSystemBlobLoader`. The only difference is the constructor, which
takes a cloud "url" object such as `s3://my-bucket`, `az://my-bucket`,
or `gs://my-bucket`.
By streamlining the process, this novel implementation eliminates the
requirement to pre-download files from cloud storage to local temporary
files (which are seldom removed).
The code relies on the
[CloudPathLib](https://cloudpathlib.drivendata.org/stable/) library to
interpret cloud URLs. This has been added as an optional dependency.
```Python
loader = CloudBlobLoader("s3://mybucket/id")
for blob in loader.yield_blobs():
print(blob)
```
- [X] **Dependencies:** CloudPathLib
- [X] **Twitter handle:** pprados
- [X] **Add tests and docs**: Add unit test, but it's easy to convert to
integration test, with some files in a cloud storage (see
`test_cloud_blob_loader.py`)
- [X] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified.
Hello from Paris @hwchase17. Can you review this PR?
---------
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
This PR contains 4 added functions:
- max_marginal_relevance_search_by_vector
- amax_marginal_relevance_search_by_vector
- max_marginal_relevance_search
- amax_marginal_relevance_search
I'm no langchain expert, but tried do inspect other vectorstore sources
like chroma, to build these functions for SurrealDB. If someone has some
changes for me, please let me know. Otherwise I would be happy, if these
changes are added to the repository, so that I can use the orignal repo
and not my local monkey patched version.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
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:https://github.com/arpitkumar980/langchain.git
- 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, hwchase17.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
- **Description:** Fixed `AzureSearchVectorStoreRetriever` to account
for search_kwargs. More explanation is in the mentioned issue.
- **Issue:** #21492
---------
Co-authored-by: MAC <mac@MACs-MacBook-Pro.local>
Co-authored-by: Massimiliano Pronesti <massimiliano.pronesti@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Thank you for contributing to LangChain!
- [X] **PR title**: "docs: Chroma docstrings update"
- 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"
- [X] **PR message**:
- **Description:** Added and updated Chroma docstrings
- **Issue:** https://github.com/langchain-ai/langchain/issues/21983
- [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.
- only docs
- [X] **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.
Description: This change adds args_schema (pydantic BaseModel) to
WikipediaQueryRun for correct schema formatting on LLM function calls
Issue: currently using WikipediaQueryRun with OpenAI function calling
returns the following error "TypeError: WikipediaQueryRun._run() got an
unexpected keyword argument '__arg1' ". This happens because the schema
sent to the LLM is "input: '{"__arg1":"Hunter x Hunter"}'" while the
method should be called with the "query" parameter.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Added [Scrapfly](https://scrapfly.io/) Web Loader integration. Scrapfly
is a web scraping API that allows extracting web page data into
accessible markdown or text datasets.
- __Description__: Added Scrapfly web loader for retrieving web page
data as markdown or text.
- Dependencies: scrapfly-sdk
- Twitter: @thealchemi1st
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Thank you for contributing to LangChain!
- [x] **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"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Updates Meilisearch vectorstore for compatibility
with v1.8. Adds [”showRankingScore”:
true”](https://www.meilisearch.com/docs/reference/api/search#ranking-score)
in the search parameters and replaces `_semanticScore` field with `
_rankingScore`
- [ ] **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.
- [x] **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.
**Description:**
- Extend AzureSearch with `maximal_marginal_relevance` (for vector and
hybrid search)
- Add construction `from_embeddings` - if the user has already embedded
the texts
- Add `add_embeddings`
- Refactor common parts (`_simple_search`, `_results_to_documents`,
`_reorder_results_with_maximal_marginal_relevance`)
- Add `vector_search_dimensions` as a parameter to the constructor to
avoid extra calls to `embed_query` (most of the time the user applies
the same model and knows the dimension)
**Issue:** none
**Dependencies:** none
- [x] **Add tests and docs**: The docstrings have been added to the new
functions, and unified for the existing ones. The example notebook is
great in illustrating the main usage of AzureSearch, adding the new
methods would only dilute the main content.
- [x] **Lint and test**
---------
Co-authored-by: Oleksii Pokotylo <oleksii.pokotylo@pwc.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Backwards compatible extension of the initialisation
interface of HanaDB to allow the user to specify
specific_metadata_columns that are used for metadata storage of selected
keys which yields increased filter performance. Any not-mentioned
metadata remains in the general metadata column as part of a JSON
string. Furthermore switched to executemany for batch inserts into
HanaDB.
**Issue:** N/A
**Dependencies:** no new dependencies added
**Twitter handle:** @sapopensource
---------
Co-authored-by: Martin Kolb <martin.kolb@sap.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Added extra functionality to `CharacterTextSplitter`,
`TextSplitter` classes.
The user can select whether to append the separator to the previous
chunk with `keep_separator='end' ` or else prepend to the next chunk.
Previous functionality prepended by default to next chunk.
**Issue:** Fixes#20908
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Integrate RankLLM reranker (https://github.com/castorini/rank_llm) into
LangChain
An example notebook is given in
`docs/docs/integrations/retrievers/rankllm-reranker.ipynb`
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Bug code**: In
langchain_community/document_loaders/csv_loader.py:100
- **Description**: currently, when 'CSVLoader' reads the column as None
in the 'csv' file, it will report an error because the 'CSVLoader' does
not verify whether the column is of str type and does not consider how
to handle the corresponding 'row_data' when the column is' None 'in the
csv. This pr provides a solution.
- **Issue:** Fix#20699
- **thinking:**
1. Refer to the processing method for
'langchain_community/document_loaders/csv_loader.py:100' when **'v'**
equals'None', and apply the same method to '**k**'.
(Reference`csv.DictReader` ,**'k'** will only be None when `
len(columns) < len(number_row_data)` is established)
2. **‘k’** equals None only holds when it is the last column, and its
corresponding **'v'** type is a list. Therefore, I referred to the data
format in 'Document' and used ',' to concatenated the elements in the
list.(But I'm not sure if you accept this form, if you have any other
ideas, communicate)
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description:** Added revision_example prompt template to include the
revision request and revision examples in the revision chain.
**Issue:** Not Applicable
**Dependencies:** Not Applicable
**Twitter handle:** @nithinjp09
## Description
The existing public interface for `langchain_community.emeddings` is
broken. In this file, `__all__` is statically defined, but is
subsequently overwritten with a dynamic expression, which type checkers
like pyright do not support. pyright actually gives the following
diagnostic on the line I am requesting we remove:
[reportUnsupportedDunderAll](https://github.com/microsoft/pyright/blob/main/docs/configuration.md#reportUnsupportedDunderAll):
```
Operation on "__all__" is not supported, so exported symbol list may be incorrect
```
Currently, I get the following errors when attempting to use publicablly
exported classes in `langchain_community.emeddings`:
```python
import langchain_community.embeddings
langchain_community.embeddings.HuggingFaceEmbeddings(...) # error: "HuggingFaceEmbeddings" is not exported from module "langchain_community.embeddings" (reportPrivateImportUsage)
```
This is solved easily by removing the dynamic expression.
Thank you for contributing to LangChain!
- [X] **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"
**Description:**
Fix ChatDatabricsk in case that streaming response doesn't have role
field in delta chunk
- [ ] **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.
- [X] **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, hwchase17.
---------
Signed-off-by: Weichen Xu <weichen.xu@databricks.com>
Updates docs so the example doesn't lead to a warning:
```
LangChainDeprecationWarning: Importing tools from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:
`from langchain_community.tools import WikipediaQueryRun`.
To install langchain-community run `pip install -U langchain-community`.
```
## 'raise_for_status' parameter of WebBaseLoader works in sync load but
not in async load.
In webBaseLoader:
Sync load is calling `_scrape` and has `raise_for_status` properly
handled.
```
def _scrape(
self,
url: str,
parser: Union[str, None] = None,
bs_kwargs: Optional[dict] = None,
) -> Any:
from bs4 import BeautifulSoup
if parser is None:
if url.endswith(".xml"):
parser = "xml"
else:
parser = self.default_parser
self._check_parser(parser)
html_doc = self.session.get(url, **self.requests_kwargs)
if self.raise_for_status:
html_doc.raise_for_status()
if self.encoding is not None:
html_doc.encoding = self.encoding
elif self.autoset_encoding:
html_doc.encoding = html_doc.apparent_encoding
return BeautifulSoup(html_doc.text, parser, **(bs_kwargs or {}))
```
Async load is calling `_fetch` but missing `raise_for_status` logic.
```
async def _fetch(
self, url: str, retries: int = 3, cooldown: int = 2, backoff: float = 1.5
) -> str:
async with aiohttp.ClientSession() as session:
for i in range(retries):
try:
async with session.get(
url,
headers=self.session.headers,
ssl=None if self.session.verify else False,
cookies=self.session.cookies.get_dict(),
) as response:
return await response.text()
```
Co-authored-by: kefan.you <darkfss@sina.com>
Thank you for contributing to LangChain!
- [x] **PR title**: "update IBM WatsonxLLM docs with deprecated
LLMChain"
- [x] **PR message**:
- **Description:** update IBM WatsonxLLM docs with deprecated LLMChain
- [x] **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/
**Title**: "langchain: OpenAI Assistants v2 api support"
***Descriptions***
- [x] "attachments" support added along with backward compatibility of
"file_ids"
- [x] "tool_resources" support added while creating new assistant
- [ ] "tool_choice" parameter support
- [ ] Streaming support
- **Dependencies:** OpenAI v2 API (openai>=1.23.0)
- **Twitter handle:** @skanta_rath
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- Updated docs to have an example to use Jamba instead of J2
---------
Co-authored-by: Asaf Gardin <asafg@ai21.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** Tongyi uses different client for chat model and
vision model. This PR chooses proper client based on model name to
support both chat model and vision model. Reference [tongyi
document](https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api?spm=a2c4g.11186623.0.0.27404c9a7upm11)
for details.
```
from langchain_core.messages import HumanMessage
from langchain_community.chat_models import ChatTongyi
llm = ChatTongyi(model_name='qwen-vl-max')
image_message = {
"image": "https://lilianweng.github.io/posts/2023-06-23-agent/agent-overview.png"
}
text_message = {
"text": "summarize this picture",
}
message = HumanMessage(content=[text_message, image_message])
llm.invoke([message])
```
- **Issue:** None
- **Dependencies:** None
- **Twitter handle:** None
- if tap_output_iter/aiter is called multiple times for the same run
issue events only once
- if chat model run is tapped don't issue duplicate on_llm_new_token
events
- if first chunk arrives after run has ended do not emit it as a stream
event
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
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.
- `llm_chain` becomes `Union[LLMChain, Runnable]`
- `.from_llm` creates a runnable
tested by verifying that docs/how_to/MultiQueryRetriever.ipynb runs
unchanged with sync/async invoke (and that it runs if we specifically
instantiate with LLMChain).
We add a tool and retriever for the [AskNews](https://asknews.app)
platform with example notebooks.
The retriever can be invoked with:
```py
from langchain_community.retrievers import AskNewsRetriever
retriever = AskNewsRetriever(k=3)
retriever.invoke("impact of fed policy on the tech sector")
```
To retrieve 3 documents in then news related to fed policy impacts on
the tech sector. The included notebook also includes deeper details
about controlling filters such as category and time, as well as
including the retriever in a chain.
The tool is quite interesting, as it allows the agent to decide how to
obtain the news by forming a query and deciding how far back in time to
look for the news:
```py
from langchain_community.tools.asknews import AskNewsSearch
from langchain import hub
from langchain.agents import AgentExecutor, create_openai_functions_agent
from langchain_openai import ChatOpenAI
tool = AskNewsSearch()
instructions = """You are an assistant."""
base_prompt = hub.pull("langchain-ai/openai-functions-template")
prompt = base_prompt.partial(instructions=instructions)
llm = ChatOpenAI(temperature=0)
asknews_tool = AskNewsSearch()
tools = [asknews_tool]
agent = create_openai_functions_agent(llm, tools, prompt)
agent_executor = AgentExecutor(
agent=agent,
tools=tools,
verbose=True,
)
agent_executor.invoke({"input": "How is the tech sector being affected by fed policy?"})
```
---------
Co-authored-by: Emre <e@emre.pm>
Please let me know if you see any possible areas of improvement. I would
very much appreciate your constructive criticism if time allows.
**Description:**
- Added a aerospike vector store integration that utilizes
[Aerospike-Vector-Search](https://aerospike.com/products/vector-database-search-llm/)
add-on.
- Added both unit tests and integration tests
- Added a docker compose file for spinning up a test environment
- Added a notebook
**Dependencies:** any dependencies required for this change
- aerospike-vector-search
**Twitter handle:**
- No twitter, you can use my GitHub handle or LinkedIn if you'd like
Thanks!
---------
Co-authored-by: Jesse Schumacher <jschumacher@aerospike.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Closes#20561
This PR fixes MLX LLM stream `AttributeError`.
Recently, `mlx-lm` changed the token decoding logic, which affected the
LC+MLX integration.
Additionally, I made minor fixes such as: docs example broken link and
enforcing pipeline arguments (max_tokens, temp and etc) for invoke.
- **Issue:** #20561
- **Twitter handle:** @Prince_Canuma
Related to #20085
@baskaryan
Thank you for contributing to LangChain!
community:sparkllm[patch]: standardized init args
updated `spark_api_key` so that aliased to `api_key`. Added integration
test for `sparkllm` to test that it continues to set the same underlying
attribute.
updated temperature with Pydantic Field, added to the integration test.
Ran `make format`,`make test`, `make lint`, `make spell_check`
UpTrain has a new dashboard now that makes it easier to view projects
and evaluations. Using this requires specifying both project_name and
evaluation_name when performing evaluations. I have updated the code to
support it.
Thank you for contributing to LangChain!
- [x] **PR title**: "community: enable SupabaseVectorStore to support
extended table fields"
- [x] **PR message**:
- Added extension fields to the function _add_vectors so that users can
add other custom fields when insert a record into the database. eg:
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description**:
- Reference to `Collection` object is set to `None` when deleting a
collection `delete_collection()`
- Added utility method `reset_collection()` to allow recreating the
collection
- Moved collection creation out of `__init__` into
`__ensure_collection()` to be reused by object init and
`reset_collection()`
- `_collection` is now a property to avoid breaking changes
**Issues**:
- chroma-core/chroma#2213
**Twitter**: @t_azarov
Example error message:
line 206, in _get_python_function_required_args
if is_function_type and required[0] == "self":
~~~~~~~~^^^
IndexError: list index out of range
Thank you for contributing to LangChain!
- [x] **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"
- [x] **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!
- [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.
- [x] **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, hwchase17.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
While integrating the xinference_embedding, we observed that the
downloaded dependency package is quite substantial in size. With a focus
on resource optimization and efficiency, if the project requirements are
limited to its vector processing capabilities, we recommend migrating to
the xinference_client package. This package is more streamlined,
significantly reducing the storage space requirements of the project and
maintaining a feature focus, making it particularly suitable for
scenarios that demand lightweight integration. Such an approach not only
boosts deployment efficiency but also enhances the application's
maintainability, rendering it an optimal choice for our current context.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Add `Origin/langchain` to Apify's client's user-agent
to attribute API activity to LangChain (at Apify, we aim to monitor our
integrations to evaluate whether we should invest more in the LangChain
integration regarding functionality and content)
**Issue:** None
**Dependencies:** None
**Twitter handle:** None
## Description
This PR implements local and dynamic mode in the Nomic Embed integration
using the inference_mode and device parameters. They work as documented
[here](https://docs.nomic.ai/reference/python-api/embeddings#local-inference).
<!-- If no one reviews your PR within a few days, please @-mention one
of baskaryan, efriis, eyurtsev, hwchase17. -->
---------
Co-authored-by: Erick Friis <erickfriis@gmail.com>
These packages all import `LangSmithParams` which was released in
langchain-core==0.2.0.
N.B. we will need to release `openai` and then bump `langchain-openai`
in `together` and `upstage`.
Thank you for contributing to LangChain!
- [x] **PR title**: "docs: update notebook for latest Pinecone API +
serverless"
- [x] **PR message**: Published notebook is incompatible with latest
`pinecone-client` and not runnable. Updated for use with latest Pinecone
Python SDK. Also updated to be compatible with serverless indexes (only
index type available on Pinecone free tier).
- [x] **Add tests and docs**: N/A (tested in Colab)
- [x] **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, hwchase17.
---
- To see the specific tasks where the Asana app for GitHub is being
used, see below:
- https://app.asana.com/0/0/1207328087952499
Thank you for contributing to LangChain!
- [x] **PR title**: "docs: update notebook for new Pinecone API +
serverless"
- [x] **PR message**: The published notebook is not runnable after
`pinecone-client` v2, which is deprecated. `langchain-pinecone` is not
compatible with the latest `pinecone-client` (v4), so I hardcoded it to
the last v3. Also updated for serverless indexes (only index type
available on Pinecone free plan).
- [x] **Add tests and docs**: N/A (tested in Colab)
- [x] **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, hwchase17.
---
- To see the specific tasks where the Asana app for GitHub is being
used, see below:
- https://app.asana.com/0/0/1207328087952500
This PR fixes two mistakes in the import paths from community for the
json data aiding the cli migration to 0.2.
It is intended as a quick follow-up to
https://github.com/langchain-ai/langchain/pull/21913 .
@nicoloboschi FYI
ChatOpenaAI --> ChatOpenAI
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, hwchase17.
Thank you for contributing to LangChain!
Remove unnecessary print from voyageai embeddings
- [x] **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/
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
- bind_tools interface is a better alternative.
- openai doesn't use functions but tools in its API now.
- the underlying content appears in some redirects, so will need to
investigate if we can remove.
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, hwchase17.
Check if event stream is closed in memory loop.
Using try/except here to avoid race condition, but this may incur a
small overhead in versions prios to 3.11
Update tool calling using prompts.
- Add required concepts
- Update names of tool invoking function.
- Add doc-string to function, and add information about `config` (which
users often forget)
- Remove steps that show how to use single function only. This makes the
how-to guide a bit shorter and more to the point.
- Add diagram from another how-to guide that shows how the thing works
overall.
Since the LangChain based on many research papers, the LC documentation
has several references to the arXiv papers. It would be beneficial to
create a single page with all referenced papers.
PR:
1. Developed code to search the arXiv references in the LangChain
Documentation and the LangChain code base. Those references are included
in a newly generated documentation page.
2. Page is linked to the Docs menu.
Controversial:
1. The `arxiv_references` page is automatically generated. But this
generation now started only manually. It is not included in the doc
generation scripts. The reason for this is simple. I don't want to
mangle into the current documentation refactoring. If you think, we need
to regenerate this page in each build, let me know. Note: This script
has a dependency on the `arxiv` package.
2. The link for this page in the menu is not obvious.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- **Code:** langchain_community/embeddings/baichuan.py:82
- **Description:** When I make an error using 'baichuan embeddings', the
printed error message is wrapped (there is actually no need to wrap)
```python
# example
from langchain_community.embeddings import BaichuanTextEmbeddings
# error key
BAICHUAN_API_KEY = "sk-xxxxxxxxxxxxx"
embeddings = BaichuanTextEmbeddings(baichuan_api_key=BAICHUAN_API_KEY)
text_1 = "今天天气不错"
query_result = embeddings.embed_query(text_1)
```
There are 2 issues fixed here:
* In the notebook pandas dataframes are formatted as HTML in the cells.
On the documentation site the renderer that converts notebooks
incorrectly displays the raw HTML. I can't find any examples of where
this is working and so I am formatting the dataframes as text.
* Some incorrect table names were referenced resulting in errors.
The only change is replacing the word "operators" with "operates," to
make the sentence grammatically correct.
Thank you for contributing to LangChain!
- [x] **PR title**: "docs: Made a grammatical correction in
streaming.ipynb to use the word "operates" instead of the word
"operators""
- [x] **PR message**:
- **Description:** The use of the word "operators" was incorrect, given
the context and grammar of the sentence. This PR updates the
documentation to use the word "operates" instead of the word
"operators".
- **Issue:** Makes the documentation more easily understandable.
- **Dependencies:** -no dependencies-
- **Twitter handle:** --
- [x] **Add tests and docs**: Since no new integration is being made, no
new tests/example notebooks are required.
- [x] **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/
- **No formatting changes made to the documentation**
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, hwchase17.
- Remove double implementations of functions. The single input is just
taking up space.
- Added tool specific information for `async + showing invoke vs.
ainvoke.
- Added more general information about about `async` (this should live
in a different place eventually since it's not specific to tools).
- Changed ordering of custom tools (StructuredTool is simpler and should
appear before the inheritance)
- Improved the error handling section (not convinced it should be here
though)
- Add information about naitve tool calling capabilities
- Add information about standard langchain interface for tool calling
- Update description for tools
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
This PR improves on the `CassandraCache` and `CassandraSemanticCache`
classes, mainly in the constructor signature, and also introduces
several minor improvements around these classes.
### Init signature
A (sigh) breaking change is tentatively introduced to the constructor.
To me, the advantages outweigh the possible discomfort: the new syntax
places the DB-connection objects `session` and `keyspace` later in the
param list, so that they can be given a default value. This is what
enables the pattern of _not_ specifying them, provided one has
previously initialized the Cassandra connection through the versatile
utility method `cassio.init(...)`.
In this way, a much less unwieldy instantiation can be done, such as
`CassandraCache()` and `CassandraSemanticCache(embedding=xyz)`,
everything else falling back to defaults.
A downside is that, compared to the earlier signature, this might turn
out to be breaking for those doing positional instantiation. As a way to
mitigate this problem, this PR typechecks its first argument trying to
detect the legacy usage.
(And to make this point less tricky in the future, most arguments are
left to be keyword-only).
If this is considered too harsh, I'd like guidance on how to further
smoothen this transition. **Our plan is to make the pattern of optional
session/keyspace a standard across all Cassandra classes**, so that a
repeatable strategy would be ideal. A possibility would be to keep
positional arguments for legacy reasons but issue a deprecation warning
if any of them is actually used, to later remove them with 0.2 - please
advise on this point.
### Other changes
- class docstrings: enriched, completely moved to class level, added
note on `cassio.init(...)` pattern, added tiny sample usage code.
- semantic cache: revised terminology to never mention "distance" (it is
in fact a similarity!). Kept the legacy constructor param with a
deprecation warning if used.
- `llm_caching` notebook: uniform flow with the Cassandra and Astra DB
separate cases; better and Cassandra-first description; all imports made
explicit and from community where appropriate.
- cache integration tests moved to community (incl. the imported tools),
env var bugfix for `CASSANDRA_CONTACT_POINTS`.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
## Patch Summary
community:openai[patch]: standardize init args
## Details
I made changes to the OpenAI Chat API wrapper test in the Langchain
open-source repository
- **File**: `libs/community/tests/unit_tests/chat_models/test_openai.py`
- **Changes**:
- Updated `max_retries` with Pydantic Field
- Updated the corresponding unit test
- **Related Issues**: #20085
- Updated max_retries with Pydantic Field, updated the unit test.
---------
Co-authored-by: JuHyung Son <sonju0427@gmail.com>
Thank you for contributing to LangChain!
- [x] **PR title**: "community: updated Browserbase loader"
- [x] **PR message**:
Updates the Browserbase loader with more options and improved docs.
- [x] **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/
Do not prefix function signature
---
* Reason for this is that information is already present with tool
calling models.
* This will save on tokens for those models, and makes it more obvious
what the description is!
* The @tool can get more parameters to allow a user to re-introduce the
the signature if we want
To permit proper coercion of objects like the following:
```python
class MyAsyncCallable:
async def __call__(self, foo):
return await ...
class MyAsyncGenerator:
async def __call__(self, foo):
await ...
yield
```
This PR introduces a v2 implementation of astream events that removes
intermediate abstractions and fixes some issues with v1 implementation.
The v2 implementation significantly reduces relevant code that's
associated with the astream events implementation together with
overhead.
After this PR, the astream events implementation:
- Uses an async callback handler
- No longer relies on BaseTracer
- No longer relies on json patch
As a result of this re-write, a number of issues were discovered with
the existing implementation.
## Changes in V2 vs. V1
### on_chat_model_end `output`
The outputs associated with `on_chat_model_end` changed depending on
whether it was within a chain or not.
As a root level runnable the output was:
```python
"data": {"output": AIMessageChunk(content="hello world!", id='some id')}
```
As part of a chain the output was:
```
"data": {
"output": {
"generations": [
[
{
"generation_info": None,
"message": AIMessageChunk(
content="hello world!", id=AnyStr()
),
"text": "hello world!",
"type": "ChatGenerationChunk",
}
]
],
"llm_output": None,
}
},
```
After this PR, we will always use the simpler representation:
```python
"data": {"output": AIMessageChunk(content="hello world!", id='some id')}
```
**NOTE** Non chat models (i.e., regular LLMs) are still associated with
the more verbose format.
### Remove some `_stream` events
`on_retriever_stream` and `on_tool_stream` events were removed -- these
were not real events, but created as an artifact of implementing on top
of astream_log.
The same information is already available in the `x_on_end` events.
### Propagating Names
Names of runnables have been updated to be more consistent
```python
model = GenericFakeChatModel(messages=infinite_cycle).configurable_fields(
messages=ConfigurableField(
id="messages",
name="Messages",
description="Messages return by the LLM",
)
)
```
Before:
```python
"name": "RunnableConfigurableFields",
```
After:
```python
"name": "GenericFakeChatModel",
```
### on_retriever_end
on_retriever_end will always return `output` which is a list of
documents (rather than a dict containing a key called "documents")
### Retry events
Removed the `on_retry` callback handler. It was incorrectly showing that
the failed function being retried has invoked `on_chain_end`
https://github.com/langchain-ai/langchain/pull/21638/files#diff-e512e3f84daf23029ebcceb11460f1c82056314653673e450a5831147d8cb84dL1394
- Where "package" is whichever of langchain, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes.
- Example: "core: add foobar LLM"
- 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
@@ -24,5 +24,6 @@ Additional guidelines:
- 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, eyurtsev, ccurme, vbarda, hwchase17.
If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Please see the following guides for migrating LangChain code:
## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
* Migrate to [LangChain v0.3](https://python.langchain.com/docs/versions/v0_3/)
* Migrate to [LangChain v0.2](https://python.langchain.com/docs/versions/v0_2/)
* Migrating from [LangChain 0.0.x Chains](https://python.langchain.com/docs/versions/migrating_chains/)
* Upgrade to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
This migration has already started, but we are remaining backwards compatible until 7/28.
On that date, we will remove functionality from `langchain`.
Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports.
This will be especially helpful if you're still on either version 0.0.x or 0.1.x of LangChain.
### Migrating to `langchain_experimental`
We are moving any experimental components of LangChain, or components with vulnerability issues, into `langchain_experimental`.
This guide covers how to migrate.
### Installation
Previously:
`pip install -U langchain`
Now (only if you want to access things in experimental):
Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out [`create_sql_query_chain`](https://github.com/langchain-ai/langchain/blob/master/docs/extras/use_cases/tabular/sql_query.ipynb)
[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
[<img src="https://github.com/codespaces/badge.svg" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
[](https://codespaces.new/langchain-ai/langchain)
> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
LangChain is a framework for building LLM-powered applications. It helps you chain
together interoperable components and third-party integrations to simplify AI
application development — all while future-proofing decisions as the underlying
technology evolves.
To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com).
[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications.
Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
## Quick Install
With pip:
```bash
pip install -U langchain
pip install langchain
```
To learn more about LangChain, check out
[the docs](https://python.langchain.com/docs/introduction/). If you’re looking for more
advanced customization or agent orchestration, check out
[LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building
controllable agent workflows.
With conda:
```bash
conda install langchain -c conda-forge
```
## Why use LangChain?
## 🤔 What is LangChain?
LangChain helps developers build applications powered by LLMs through a standard
interface for models, embeddings, vector stores, and more.
**LangChain** is a framework for developing applications powered by large language models (LLMs).
Use LangChain for:
- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and
external / internal systems, drawing from LangChain’s vast library of integrations with
model providers, tools, vector stores, retrievers, and more.
- **Model interoperability**. Swap models in and out as your engineering team
experiments to find the best choice for your application’s needs. As the industry
frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without
losing momentum.
For these applications, LangChain simplifies the entire application lifecycle:
## LangChain’s ecosystem
While the LangChain framework can be used standalone, it also integrates seamlessly
with any LangChain product, giving developers a full suite of tools when building LLM
applications.
- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
To improve your LLM application development, pair LangChain with:
### Open-source libraries
- **`langchain-core`**: Base abstractions and LangChain Expression Language.
- **`langchain-community`**: Third party integrations.
- Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
- **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
- [LangSmith](http://www.langchain.com/langsmith) - Helpful for agent evals and
observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain
visibility in production, and improve performance over time.
- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can
reliably handle complex tasks with LangGraph, our low-level agent orchestration
framework. LangGraph offers customizable architecture, long-term memory, and
human-in-the-loop workflows — and is trusted in production by companies like LinkedIn,
- **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
## Additional resources
-[Tutorials](https://python.langchain.com/docs/tutorials/): Simple walkthroughs with
guided examples on getting started with LangChain.
snippets for topics such as tool calling, RAG use cases, and more.
- [Conceptual Guides](https://python.langchain.com/docs/concepts/): Explanations of key
concepts behind the LangChain framework.
- [API Reference](https://python.langchain.com/api_reference/): Detailed reference on
navigating base packages and integrations for LangChain.
### Deployment:
-**[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
- End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
And much more! Head to the [Tutorials](https://python.langchain.com/v0.2/docs/tutorials/) section of the docs for more.
## 🚀 How does LangChain help?
The main value props of the LangChain libraries are:
1.**Components**: composable building blocks, tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
2.**Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones.
## LangChain Expression Language (LCEL)
LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
- **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
- **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
- **[Primitives](https://python.langchain.com/v0.2/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
- **[Cheatsheet](https://python.langchain.com/v0.2/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
## Components
Components fall into the following **modules**:
**📃 Model I/O**
This includes [prompt management](https://python.langchain.com/v0.2/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/v0.2/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/v0.2/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/v0.2/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/v0.2/docs/concepts/#output-parsers).
**📚 Retrieval**
Retrieval Augmented Generation involves [loading data](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/v0.2/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/v0.2/docs/concepts/#retrievers) it for use in the generation step.
**🤖 Agents**
Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom agents.
## 📖 Documentation
Please see [here](https://python.langchain.com) for full documentation, which includes:
- [Introduction](https://python.langchain.com/v0.2/docs/introduction/): Overview of the framework and the structure of the docs.
- [Tutorials](https://python.langchain.com/docs/use_cases/): If you're looking to build something specific or are more of a hands-on learner, check out our tutorials. This is the best place to get started.
- [How-to guides](https://python.langchain.com/v0.2/docs/how_to/): Answers to “How do I….?” type questions. These guides are goal-oriented and concrete; they're meant to help you complete a specific task.
- [Conceptual guide](https://python.langchain.com/v0.2/docs/concepts/): Conceptual explanations of the key parts of the framework.
- [API Reference](https://api.python.langchain.com): Thorough documentation of every class and method.
## 🌐 Ecosystem
- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
- [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
## 💁 Contributing
As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
For detailed information on how to contribute, see [here](https://python.langchain.com/v0.2/docs/contributing/).
LangChain has a large ecosystem of integrations with various external resources like local and remote file systems, APIs and databases. These integrations allow developers to create versatile applications that combine the power of LLMs with the ability to access, interact with and manipulate external resources.
## Best practices
When building such applications developers should remember to follow good security practices:
* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc. as appropriate for your application.
* **Anticipate Potential Misuse**: Just as humans can err, so can Large Language Models (LLMs). Always assume that any system access or credentials may be used in any way allowed by the permissions they are assigned. For example, if a pair of database credentials allows deleting data, it’s safest to assume that any LLM able to use those credentials may in fact delete data.
* [**Defense in Depth**](https://en.wikipedia.org/wiki/Defense_in_depth_(computing)): No security technique is perfect. Fine-tuning and good chain design can reduce, but not eliminate, the odds that a Large Language Model (LLM) may make a mistake. It’s best to combine multiple layered security approaches rather than relying on any single layer of defense to ensure security. For example: use both read-only permissions and sandboxing to ensure that LLMs are only able to access data that is explicitly meant for them to use.
Risks of not doing so include, but are not limited to:
* Data corruption or loss.
* Unauthorized access to confidential information.
* Compromised performance or availability of critical resources.
Example scenarios with mitigation strategies:
* A user may ask an agent with access to the file system to delete files that should not be deleted or read the content of files that contain sensitive information. To mitigate, limit the agent to only use a specific directory and only allow it to read or write files that are safe to read or write. Consider further sandboxing the agent by running it in a container.
* A user may ask an agent with write access to an external API to write malicious data to the API, or delete data from that API. To mitigate, give the agent read-only API keys, or limit it to only use endpoints that are already resistant to such misuse.
* A user may ask an agent with access to a database to drop a table or mutate the schema. To mitigate, scope the credentials to only the tables that the agent needs to access and consider issuing READ-ONLY credentials.
If you're building applications that access external resources like file systems, APIs
or databases, consider speaking with your company's security team to determine how to best
design and secure your applications.
## Reporting OSS Vulnerabilities
LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide
@@ -39,7 +14,7 @@ Before reporting a vulnerability, please review:
1) In-Scope Targets and Out-of-Scope Targets below.
2) The [langchain-ai/langchain](https://python.langchain.com/docs/contributing/repo_structure) monorepo structure.
3) The [Best practicies](#best-practices) above to
3) LangChain [security guidelines](https://python.langchain.com/docs/security) to
understand what we consider to be a security vulnerability vs. developer
responsibility.
@@ -58,13 +33,13 @@ The following packages and repositories are eligible for bug bounties:
All out of scope targets defined by huntr as well as:
- **langchain-experimental**: This repository is for experimental code and is not
eligible for bug bounties (see [package warning](https://pypi.org/project/langchain-experimental/)), bug reports to it will be marked as interesting or waste of
eligible for bug bounties, bug reports to it will be marked as interesting or waste of
time and published with no bounty attached.
- **tools**: Tools in either langchain or langchain-community are not eligible for bug
bounties. This includes the following directories
-libs/langchain/langchain/tools
-libs/community/langchain_community/tools
- Please review the [best practices](#best-practices)
"Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint is ready, you need to copy its number."
"Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint it ready, you need to copy its number."
@@ -4,8 +4,6 @@ Example code for building applications with LangChain, with an emphasis on more
Notebook | Description
:- | :-
[agent_fireworks_ai_langchain_mongodb.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/agent_fireworks_ai_langchain_mongodb.ipynb) | Build an AI Agent With Memory Using MongoDB, LangChain and FireWorksAI.
[mongodb-langchain-cache-memory.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/mongodb-langchain-cache-memory.ipynb) | Build a RAG Application with Semantic Cache Using MongoDB and LangChain.
[LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
[Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
[Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
@@ -21,6 +19,7 @@ Notebook | Description
[code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
[custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
[deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
[elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.
[extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Tools
@@ -37,7 +36,6 @@ Notebook | Description
[llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
[meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
[multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
[multi_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
[multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
[multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
[multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
@@ -49,7 +47,7 @@ Notebook | Description
[press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
[program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
[qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
[rag_upstage_document_parse_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_document_parse_groundedness_check.ipynb) | End-to-end RAG example using Upstage Document Parse and Groundedness Check.
[rag_upstage_layout_analysis_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb) | End-to-end RAG example using Upstage Layout Analysis and Groundedness Check.
[retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
[sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
[self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -59,8 +57,4 @@ Notebook | Description
[two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
[two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
[wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
[rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.
[oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
" description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
" ),\n",
" Tool(\n",
" name=\"ruff_qa_system\",\n",
" name=\"Ruff QA System\",\n",
" func=ruff.run,\n",
" description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
" Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
"Action: State of Union QA System\n",
"Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_message = {\n",
" \"role\": \"user\",\n",
" \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
"}\n",
"\n",
"for step in agent.stream(\n",
" {\"messages\": [input_message]},\n",
" stream_mode=\"values\",\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
"agent.run(\n",
" \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
"execution_count": 47,
"id": "4e91b811",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Why use ruff over flake8?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"There are a few reasons why someone might choose to use Ruff over Flake8:\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
"Action: Ruff QA System\n",
"Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
"\n",
"1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
"\n",
"2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
"\n",
"3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
"\n",
"4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
"\n",
"Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\n",
"You might choose to use Ruff over Flake8 for several reasons:\n",
"\n",
"1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
"2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
"3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
"4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
"\n",
"Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_message = {\n",
" \"role\": \"user\",\n",
" \"content\": \"Why use ruff over flake8?\",\n",
"}\n",
"\n",
"for step in agent.stream(\n",
" {\"messages\": [input_message]},\n",
" stream_mode=\"values\",\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
"agent.run(\"Why use ruff over flake8?\")"
]
},
{
@@ -324,20 +296,20 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 48,
"id": "f59b377e",
"metadata": {},
"outputs": [],
"source": [
"tools = [\n",
" Tool(\n",
" name=\"state_of_union_qa_system\",\n",
" name=\"Stateof Union QA System\",\n",
" func=state_of_union.run,\n",
" description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
" return_direct=True,\n",
" ),\n",
" Tool(\n",
" name=\"ruff_qa_system\",\n",
" name=\"Ruff QA System\",\n",
" func=ruff.run,\n",
" description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
" Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
"Action: State of Union QA System\n",
"Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_message = {\n",
" \"role\": \"user\",\n",
" \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
"}\n",
"\n",
"for step in agent.stream(\n",
" {\"messages\": [input_message]},\n",
" stream_mode=\"values\",\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
"agent.run(\n",
" \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "88f08d86-7972-4148-8128-3ac8898ad68a",
"execution_count": 51,
"id": "edfd0a1a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"================================\u001b[1m Human Message \u001b[0m=================================\n",
"\n",
"Why use ruff over flake8?\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
" Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
"Action: Ruff QA System\n",
"Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_message = {\n",
" \"role\": \"user\",\n",
" \"content\": \"Why use ruff over flake8?\",\n",
"}\n",
"\n",
"for step in agent.stream(\n",
" {\"messages\": [input_message]},\n",
" stream_mode=\"values\",\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
"agent.run(\"Why use ruff over flake8?\")"
]
},
{
@@ -447,19 +417,19 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": 57,
"id": "d397a233",
"metadata": {},
"outputs": [],
"source": [
"tools = [\n",
" Tool(\n",
" name=\"state_of_union_qa_system\",\n",
" name=\"Stateof Union QA System\",\n",
" func=state_of_union.run,\n",
" description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
" ),\n",
" Tool(\n",
" name=\"ruff_qa_system\",\n",
" name=\"Ruff QA System\",\n",
" func=ruff.run,\n",
" description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
" No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks, and if the president mentioned it in the state of the union.\n",
"Action: Ruff QA System\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.html\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now need to find out if the president mentioned this tool in the state of the union.\n",
"Action: State of Union QA System\n",
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"\n",
"Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'No, the president did not mention nbQA in the state of the union.'"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"input_message = {\n",
" \"role\": \"user\",\n",
" \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
"}\n",
"\n",
"for step in agent.stream(\n",
" {\"messages\": [input_message]},\n",
" stream_mode=\"values\",\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
"agent.run(\n",
" \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\"\n",
"`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"# from langchain_community.vectorstores import DeepLake\n",
"You can also specify user defined functions using [Deep Lake filters](https://docs.deeplake.ai/en/latest/deeplake.core.dataset.html#deeplake.core.dataset.Dataset.filter)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"def filter(x):\n",
" # filter based on source code\n",
" if \"something\" in x[\"text\"].data()[\"value\"]:\n",
"This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",
"It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."
]
},
{
"cell_type": "markdown",
"id": "0076d072",
"metadata": {},
"source": [
"## Installation and Setup"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "739b489b",
"metadata": {},
"outputs": [],
"source": [
"!pip install databricks-sql-connector"
]
},
{
"cell_type": "markdown",
"id": "73113163",
"metadata": {},
"source": [
"## Connecting to Databricks\n",
"\n",
"You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",
"\n",
"### Syntax\n",
"```python\n",
"SQLDatabase.from_databricks(\n",
" catalog: str,\n",
" schema: str,\n",
" host: Optional[str] = None,\n",
" api_token: Optional[str] = None,\n",
" warehouse_id: Optional[str] = None,\n",
" cluster_id: Optional[str] = None,\n",
" engine_args: Optional[dict] = None,\n",
" **kwargs: Any)\n",
"```\n",
"### Required Parameters\n",
"* `catalog`: The catalog name in the Databricks database.\n",
"* `schema`: The schema name in the catalog.\n",
"\n",
"### Optional Parameters\n",
"There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",
"* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",
"* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",
"* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",
"* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",
"* `engine_args`: The arguments to be used when connecting Databricks.\n",
"* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."
]
},
{
"cell_type": "markdown",
"id": "b11c7e48",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "8102bca0",
"metadata": {},
"outputs": [],
"source": [
"# Connecting to Databricks with SQLDatabase wrapper\n",
"This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."
"Answer:\u001b[32;1m\u001b[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db_chain.run(\n",
" \"What is the average duration of taxi rides that start between midnight and 6am?\"\n",
")"
]
},
{
"cell_type": "markdown",
"id": "e496d5e5",
"metadata": {},
"source": [
"### SQL Database Agent example\n",
"\n",
"This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database."
"Thought:\u001b[32;1m\u001b[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",
"Thought:\u001b[32;1m\u001b[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",
"Action: query_checker_sql_db\n",
"Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",
"Action: query_sql_db\n",
"Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
"PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
"\n",
"Unless told to do not query for all the columns from a specific index, only ask for a few relevant columns given the question.\n",
"Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
"\n",
"Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
"* Use of multimodal embeddings (such as [CLIP](https://openai.com/research/clip)) to embed images and text\n",
"* Use of [VDMS](https://github.com/IntelLabs/vdms/blob/master/README.md) as a vector store with support for multi-modal\n",
"* Retrieval of both images and text using similarity search\n",
"* Passing raw images and text chunks to a multimodal LLM for answer synthesis "
]
},
{
"cell_type": "markdown",
"id": "2498a0a1",
"metadata": {},
"source": [
"* Passing raw images and text chunks to a multimodal LLM for answer synthesis \n",
"\n",
"\n",
"## Packages\n",
"\n",
"For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
"docker: Error response from daemon: Conflict. The container name \"/vdms_rag_nb\" is already in use by container \"0c19ed281463ac10d7efe07eb815643e3e534ddf24844357039453ad2b0c27e8\". You have to remove (or rename) that container to be able to reuse that name.\n",
"See 'docker run --help'.\n"
]
}
],
@@ -84,11 +70,22 @@
"! docker run --rm -d -p 55559:55555 --name vdms_rag_nb intellabs/vdms:latest\n",
"# from dotenv import load_dotenv, find_dotenv\n",
"# load_dotenv(find_dotenv(), override=True);"
]
},
{
"cell_type": "markdown",
"id": "1e94b3fb-8e3e-4736-be0a-ad881626c7bd",
@@ -98,9 +95,14 @@
"\n",
"### Partition PDF text and images\n",
" \n",
"Let's use famous photographs from the PDF version of Library of Congress Magazine in this example.\n",
"Let's look at an example pdf containing interesting images.\n",
"\n",
"We can use `partition_pdf` from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
"We can use `partition_pdf` below from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
"In this section, we initialize the VDMS vector store for both text and images. For better performance, we use model `ViT-g-14` from [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
"The images are stored as base64 encoded strings with `vectorstore.add_images`.\n"
"We will use [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
"\n",
"We use a larger model for better performance (set in `langchain_experimental.open_clip.py`).\n",
"contemporary criticism of the less-than- thoughtful circumstances under which Lange photographed Thomson, the picture’s power to engage has not diminished. Artists in other countries have appropriated the image, changing the mother’s features into those of other ethnicities, but keeping her expression and the positions of her clinging children. Long after anyone could help the Thompson family, this picture has resonance in another time of national crisis, unemployment and food shortages.\n",
"\n",
"A striking, but very different picture is a 1900 portrait of the legendary Hin-mah-too-yah- lat-kekt (Chief Joseph) of the Nez Percé people. The Bureau of American Ethnology in Washington, D.C., regularly arranged for its photographer, De Lancey Gill, to photograph Native American delegations that came to the capital to confer with officials about tribal needs and concerns. Although Gill described Chief Joseph as having “an air of gentleness and quiet reserve,” the delegate skeptically appraises the photographer, which is not surprising given that the United States broke five treaties with Chief Joseph and his father between 1855 and 1885.\n",
"\n",
"More than a glance, second looks may reveal new knowledge into complex histories.\n",
"\n",
"Anne Wilkes Tucker is the photography curator emeritus of the Museum of Fine Arts, Houston and curator of the “Not an Ostrich” exhibition.\n",
"\n",
"28\n",
"\n",
"28 LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"LIBRARY OF CONGRESS MAGAZINE\n",
"THEYRE WILLING TO HAVE MEENTERTAIN THEM DURING THE DAY,BUT AS SOON AS IT STARTSGETTING DARK, THEY ALLGO OFF, AND LEAVE ME! \n",
"ROSA PARKS: IN HER OWN WORDS\n",
"\n",
"COMIC ART: 120 YEARS OF PANELS AND PAGES\n",
"\n",
"SHALL NOT BE DENIED: WOMEN FIGHT FOR THE VOTE\n",
"\n",
"More information loc.gov/exhibits\n",
"Nuestra Sefiora de las Iguanas\n",
"\n",
"Graciela Iturbide’s 1979 portrait of Zobeida Díaz in the town of Juchitán in southeastern Mexico conveys the strength of women and reflects their important contributions to the economy. Díaz, a merchant, was selling iguanas to cook and eat, carrying them on her head, as is customary.\n",
"Iturbide requested permission to take a photograph, but this proved challenging because the iguanas were constantly moving, causing Díaz to laugh. The result, however, was a brilliant portrait that the inhabitants of Juchitán claimed with pride. They have reproduced it on posters and erected a statue honoring Díaz and her iguanas. The photo now appears throughout the world, inspiring supporters of feminism, women’s rights and gender equality.\n",
"\n",
"—Adam Silvia is a curator in the Prints and Photographs Division.\n",
"\n",
"6\n",
"\n",
"6 LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"‘Migrant Mother’ is Florence Owens Thompson\n",
"\n",
"The iconic portrait that became the face of the Great Depression is also the most famous photograph in the collections of the Library of Congress.\n",
"\n",
"The Library holds the original source of the photo — a nitrate negative measuring 4 by 5 inches. Do you see a faint thumb in the bottom right? The photographer, Dorothea Lange, found the thumb distracting and after a few years had the negative altered to make the thumb almost invisible. Lange’s boss at the Farm Security Administration, Roy Stryker, criticized her action because altering a negative undermines the credibility of a documentary photo.\n",
"Shrimp Picker\n",
"\n",
"The photos and evocative captions of Lewis Hine served as source material for National Child Labor Committee reports and exhibits exposing abusive child labor practices in the United States in the first decades of the 20th century.\n",
"\n",
"LEWIS WICKES HINE. “MANUEL, THE YOUNG SHRIMP-PICKER, FIVE YEARS OLD, AND A MOUNTAIN OF CHILD-LABOR OYSTER SHELLS BEHIND HIM. HE WORKED LAST YEAR. UNDERSTANDS NOT A WORD OF ENGLISH. DUNBAR, LOPEZ, DUKATE COMPANY. LOCATION: BILOXI, MISSISSIPPI.” FEBRUARY 1911. NATIONAL CHILD LABOR COMMITTEE COLLECTION. PRINTS AND PHOTOGRAPHS DIVISION.\n",
"\n",
"For 15 years, Hine\n",
"\n",
"crisscrossed the country, documenting the practices of the worst offenders. His effective use of photography made him one of the committee's greatest publicists in the campaign for legislation to ban child labor.\n",
"\n",
"Hine was a master at taking photos that catch attention and convey a message and, in this photo, he framed Manuel in a setting that drove home the boy’s small size and unsafe environment.\n",
"\n",
"Captions on photos of other shrimp pickers emphasized their long working hours as well as one hazard of the job: The acid from the shrimp made pickers’ hands sore and “eats the shoes off your feet.”\n",
"\n",
"Such images alerted viewers to all that workers, their families and the nation sacrificed when children were part of the labor force. The Library holds paper records of the National Child Labor Committee as well as over 5,000 photographs.\n",
"\n",
"—Barbara Natanson is head of the Reference Section in the Prints and Photographs Division.\n",
"\n",
"8\n",
"\n",
"LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"Intergenerational Portrait\n",
"\n",
"Raised on the Apsáalooke (Crow) reservation in Montana, photographer Wendy Red Star created her “Apsáalooke Feminist” self-portrait series with her daughter Beatrice. With a dash of wry humor, mother and daughter are their own first-person narrators.\n",
"\n",
"Red Star explains the significance of their appearance: “The dress has power: You feel strong and regal wearing it. In my art, the elk tooth dress specifically symbolizes Crow womanhood and the matrilineal line connecting me to my ancestors. As a mother, I spend hours searching for the perfect elk tooth dress materials to make a prized dress for my daughter.”\n",
"\n",
"In a world that struggles with cultural identities, this photograph shows us the power and beauty of blending traditional and contemporary styles.\n",
"Gordon Parks created an iconic image with this 1942 photograph of cleaning woman Ella Watson.\n",
"\n",
"Snow blankets the U.S. Capitol in this classic image by Ernest L. Crandall.\n",
"\n",
"Start your new year out right with a poster promising good reading for months to come.\n",
"\n",
"▪ Order online: loc.gov/shop ▪ Order by phone: 888.682.3557\n",
"\n",
"26\n",
"\n",
"LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"LIBRARY OF CONGRESS MAGAZINE\n",
"\n",
"SUPPORT\n",
"\n",
"A PICTURE OF PHILANTHROPY Annenberg Foundation Gives $1 Million and a Photographic Collection to the Library.\n",
"\n",
"A major gift by Wallis Annenberg and the Annenberg Foundation in Los Angeles will support the effort to reimagine the visitor experience at the Library of Congress. The foundation also is donating 1,000 photographic prints from its Annenberg Space for Photography exhibitions to the Library.\n",
"\n",
"The Library is pursuing a multiyear plan to transform the experience of its nearly 2 million annual visitors, share more of its treasures with the public and show how Library collections connect with visitors’ own creativity and research. The project is part of a strategic plan established by Librarian of Congress Carla Hayden to make the Library more user-centered for Congress, creators and learners of all ages.\n",
"\n",
"A 2018 exhibition at the Annenberg Space for Photography in Los Angeles featured over 400 photographs from the Library. The Library is planning a future photography exhibition, based on the Annenberg-curated show, along with a documentary film on the Library and its history, produced by the Annenberg Space for Photography.\n",
"\n",
"“The nation’s library is honored to have the strong support of Wallis Annenberg and the Annenberg Foundation as we enhance the experience for our visitors,” Hayden said. “We know that visitors will find new connections to the Library through the incredible photography collections and countless other treasures held here to document our nation’s history and creativity.”\n",
"\n",
"To enhance the Library’s holdings, the foundation is giving the Library photographic prints for long-term preservation from 10 other exhibitions hosted at the Annenberg Space for Photography. The Library holds one of the world’s largest photography collections, with about 14 million photos and over 1 million images digitized and available online.\n",
"18 LIBRARY OF CONGRESS MAGAZINE\n"
]
}
],
"source": [
@@ -559,14 +452,6 @@
" print(doc.page_content)"
]
},
{
"cell_type": "markdown",
"id": "15e9b54d",
"metadata": {},
"source": [
"Now let's use the `multi_modal_rag_chain` to process the same query and display the response."
]
},
{
"cell_type": "code",
"execution_count": 11,
@@ -577,17 +462,10 @@
"name": "stdout",
"output_type": "stream",
"text": [
" The image is a black and white photograph by Dorothea Lange titled \"Destitute Pea Pickers in California. Mother of Seven Children. Age Thirty-Two. Nipomo, California.\" It was taken in March 1936 as part of the Farm Security Administration-Office of War Information Collection.\n",
"\n",
"The photograph features a woman with seven children, who appear to be in a state of poverty and hardship. The woman is seated, looking directly at the camera, while three of her children are standing behind her. They all seem to be dressed in ragged clothing, indicative of their impoverished condition.\n",
"\n",
"The historical context of this image is related to the Great Depression, which was a period of economic hardship in the United States that lasted from 1929 to 1939. During this time, many people struggled to make ends meet, and poverty was widespread. This photograph captures the plight of one such family during this difficult period.\n",
"\n",
"The symbolism of the image is multifaceted. The woman's direct gaze at the camera can be seen as a plea for help or an expression of desperation. The ragged clothing of the children serves as a stark reminder of the poverty and hardship experienced by many during this time.\n",
"\n",
"In terms of connections to the related text, it is mentioned that Florence Owens Thompson, the woman in the photograph, initially regretted having her picture taken. However, she later came to appreciate the importance of the image as a representation of the struggles faced by many during the Great Depression. The mention of Helena Zinkham suggests that she may have played a role in the creation or distribution of this photograph.\n",
"\n",
"Overall, this image is a powerful depiction of poverty and hardship during the Great Depression, capturing the resilience and struggles of one family amidst difficult times. \n"
"1. Detailed description of the visual elements in the image: The image features a woman with children, likely a mother and her family, standing together outside. They appear to be poor or struggling financially, as indicated by their attire and surroundings.\n",
"2. Historical and cultural context of the image: The photo was taken in 1936 during the Great Depression, when many families struggled to make ends meet. Dorothea Lange, a renowned American photographer, took this iconic photograph that became an emblem of poverty and hardship experienced by many Americans at that time.\n",
"3. Interpretation of the image's symbolism and meaning: The image conveys a sense of unity and resilience despite adversity. The woman and her children are standing together, displaying their strength as a family unit in the face of economic challenges. The photograph also serves as a reminder of the importance of empathy and support for those who are struggling.\n",
"4. Connections between the image and the related text: The text provided offers additional context about the woman in the photo, her background, and her feelings towards the photograph. It highlights the historical backdrop of the Great Depression and emphasizes the significance of this particular image as a representation of that time period.\n"
"In this cookbook, we use langchain tools and open source models to execute locally on CPU. This notebook has been validated to run on Intel Xeon 8480+ CPU. Here we implement a RAG pipeline for Llama2 model to answer questions about Intel Q1 2024 earnings release."
]
},
{
"cell_type": "markdown",
"id": "acadbcec-3468-4926-8ce5-03b678041c0a",
"metadata": {},
"source": [
"**Create a conda or virtualenv environment with python >=3.10 and install following libraries**\n",
"Document(metadata={'source': 'intel_q1_2024_earnings.pdf', 'page': 0}, page_content='Intel Corporation\\n2200 Mission College Blvd.\\nSanta Clara, CA 95054-1549\\n \\nNews Release\\n Intel Reports First -Quarter 2024 Financial Results\\nNEWS SUMMARY\\n▪First-quarter revenue of $12.7 billion , up 9% year over year (YoY).\\n▪First-quarter GAAP earnings (loss) per share (EPS) attributable to Intel was $(0.09) ; non-GAAP EPS \\nattributable to Intel was $0.18 .')"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"all_splits[0]"
]
},
{
"cell_type": "markdown",
"id": "b88d2632-7c1b-49ef-a691-c0eb67d23e6a",
"metadata": {},
"source": [
"**One of the major step in RAG is to convert each split of document into embeddings and store in a vector database such that searching relevant documents are efficient.** <br>\n",
"**For that, importing Chroma vector database from langchain. Also, importing open source GPT4All for embedding models**"
"**In next step, we will download one of the most popular embedding model \"all-MiniLM-L6-v2\". Find more details of the model at this link https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2**"
"**Look at the first retrieved document from the vector database**"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "43a6d94f-b5c4-47b0-a353-2db4c3d24d9c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(metadata={'page': 1, 'source': 'intel_q1_2024_earnings.pdf'}, page_content='Client Computing Group (CCG) $7.5 billion up31%\\nData Center and AI (DCAI) $3.0 billion up5%\\nNetwork and Edge (NEX) $1.4 billion down 8%\\nTotal Intel Products revenue $11.9 billion up17%\\nIntel Foundry $4.4 billion down 10%\\nAll other:\\nAltera $342 million down 58%\\nMobileye $239 million down 48%\\nOther $194 million up17%\\nTotal all other revenue $775 million down 46%\\nIntersegment eliminations $(4.4) billion\\nTotal net revenue $12.7 billion up9%\\nIntel Products Highlights')"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs[0]"
]
},
{
"cell_type": "markdown",
"id": "64ba074f-4b36-442e-b7e2-b26d6e2815c3",
"metadata": {},
"source": [
"**Download Lllama-2 model from Huggingface and store locally** <br>\n",
"**You can download different quantization variant of Lllama-2 model from the link below. We are using Q8 version here (7.16GB).** <br>\n",
"**Now let's ask the same question to Llama model without showing them the earnings release.**"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "1033dd82-5532-437d-a548-27695e109589",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"?\n",
"(NASDAQ:INTC)\n",
"Intel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year."
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"llama_print_timings: load time = 131.20 ms\n",
"llama_print_timings: sample time = 16.05 ms / 68 runs ( 0.24 ms per token, 4236.76 tokens per second)\n",
"llama_print_timings: prompt eval time = 131.14 ms / 16 tokens ( 8.20 ms per token, 122.01 tokens per second)\n",
"llama_print_timings: eval time = 3225.00 ms / 67 runs ( 48.13 ms per token, 20.78 tokens per second)\n",
"llama_print_timings: total time = 3466.40 ms / 83 tokens\n"
]
},
{
"data": {
"text/plain": [
"\"?\\n(NASDAQ:INTC)\\nIntel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year.\""
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm.invoke(question)"
]
},
{
"cell_type": "markdown",
"id": "75f5cb10-746f-4e37-9386-b85a4d2b84ef",
"metadata": {},
"source": [
"**As you can see, model is giving wrong information. Correct asnwer is CCG revenue in Q1 2024 is $7.5B. Now let's apply RAG using the earning release document**"
]
},
{
"cell_type": "markdown",
"id": "0f4150ec-5692-4756-b11a-22feb7ab88ff",
"metadata": {},
"source": [
"**in RAG, we modify the input prompt by adding relevent documents with the question. Here, we use one of the popular RAG prompt**"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "226c14b0-f43e-4a1f-a1e4-04731d467ec4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['context', 'question'], template=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: {question} \\nContext: {context} \\nAnswer:\"))]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain import hub\n",
"\n",
"rag_prompt = hub.pull(\"rlm/rag-prompt\")\n",
"rag_prompt.messages"
]
},
{
"cell_type": "markdown",
"id": "77deb6a0-0950-450a-916a-f2a029676c20",
"metadata": {},
"source": [
"**Appending all retreived documents in a single document**"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "2dbc3327-6ef3-4c1f-8797-0c71964b0921",
"metadata": {},
"outputs": [],
"source": [
"def format_docs(docs):\n",
" return \"\\n\\n\".join(doc.page_content for doc in docs)"
]
},
{
"cell_type": "markdown",
"id": "2e2d9f18-49d0-43a3-bea8-78746ffa86b7",
"metadata": {},
"source": [
"**The last step is to create a chain using langchain tool that will create an e2e pipeline. It will take question and context as an input.**"
"**Now we see the results are correct as it is mentioned in earnings release.** <br>\n",
"**To further automate, we will create a chain that will take input as question and retriever so that we don't need to retrieve documents separately**"
"# RAG using Upstage Document Parse and Groundedness Check\n",
"This example illustrates RAG using [Upstage](https://python.langchain.com/docs/integrations/providers/upstage/) Document Parse and Groundedness Check."
"# RAG using Upstage Layout Analysis and Groundedness Check\n",
"This example illustrates RAG using [Upstage](https://python.langchain.com/docs/integrations/providers/upstage/) Layout Analysis and Groundedness Check."
_DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. Unless the user specifies in his question a specific number of examples he wishes to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.
Never query for all the columns from a specific table, only ask for a few relevant columns given the question.
Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
Pay attention to use only the column names that you can see in the schema description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
@@ -740,7 +740,7 @@ Even this relatively large model will most likely fail to generate more complica
```bash
poetry run pip install pyyaml langchain_chroma
poetry run pip install pyyaml chromadb
import yaml
```
@@ -994,7 +994,7 @@ from langchain.prompts import FewShotPromptTemplate, PromptTemplate
from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
from langchain_huggingface import HuggingFaceEmbeddings
from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
from langchain_chroma import Chroma
from langchain_community.vectorstores import Chroma
For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/how_to/documentation)
For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/documentation)
* master color map. Only the colors that actually differ between light and dark
* themes are specified separately.
*
* To see the full list of colors see https://www.figma.com/file/rUrrHGhUBBIAAjQ82x6pz9/PyData-Design-system---proposal-for-implementation-(2)?node-id=1234%3A765&t=ifcFT1JtnrSshGfi-1
File diff suppressed because one or more lines are too long
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
