Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Added support for streaming in AI21 Jamba Model
- **Twitter handle:** https://github.com/AI21Labs
- [x] **Add tests and docs**: If you're adding a new integration, please
include
- [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.
---------
Co-authored-by: Asaf Gardin <asafg@ai21.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Chester Curme <chester.curme@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"
**Description:** Update docs content on agent memory
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
`ChatAnthropic` can get `stop_reason` from the resulting `AIMessage` in
`invoke` and `ainvoke`, but not in `stream` and `astream`.
This is a different behavior from `ChatOpenAI`.
It is possible to get `stop_reason` from `stream` as well, since it is
needed to determine the next action after the LLM call. This would be
easier to handle in situations where only `stop_reason` is needed.
- Issue: NA
- Dependencies: NA
- Twitter handle: https://x.com/kiarina37
- **Description:** Fix some issues in MiniMaxChat
- Fix `minimax_api_host` not in `values` error
- Remove `minimax_group_id` from reading environment variables, the
`minimax_group_id` no longer use in MiniMaxChat
- Invoke callback prior to yielding token, the issus #16913
The prompt template variable detection only worked for singly-nested
sections because we just kept track of whether we were in a section and
then set that to false as soon as we encountered an end block. i.e. the
following:
```
{{#outerSection}}
{{variableThatShouldntShowUp}}
{{#nestedSection}}
{{nestedVal}}
{{/nestedSection}}
{{anotherVariableThatShouldntShowUp}}
{{/outerSection}}
```
Would yield `['outerSection', 'anotherVariableThatShouldntShowUp']` as
input_variables (whereas it should just yield `['outerSection']`). This
fixes that by keeping track of the current depth and using a stack.
When `model_kwargs={"tools": tools}` are passed to `ChatLiteLLM`, they
are executed, but the response is not recognized correctly
Let's add `tool_calls` to the `additional_kwargs`
Thank you for contributing to LangChain!
## ChatAnthropic
I used the following example to verify the output of llm with tools:
```python
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_anthropic import ChatAnthropic
class GetWeather(BaseModel):
'''Get the current weather in a given location'''
location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
class GetPopulation(BaseModel):
'''Get the current population in a given location'''
location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
llm = ChatAnthropic(model="claude-3-sonnet-20240229")
llm_with_tools = llm.bind_tools([GetWeather, GetPopulation])
ai_msg = llm_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")
print(ai_msg.tool_calls)
```
I get the following response:
```json
[{'name': 'GetWeather', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_01UfDA89knrhw3vFV9X47neT'}, {'name': 'GetWeather', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01NrYVRYae7m7z7tBgyPb3Gd'}, {'name': 'GetPopulation', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_01EPFEpDgzL6vV2dTpD9SVP5'}, {'name': 'GetPopulation', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01B5J6tPJXgwwfhQX9BHP2dt'}]
```
## LiteLLM
Based on https://litellm.vercel.app/docs/completion/function_call
```python
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.utils.function_calling import convert_to_openai_tool
import litellm
class GetWeather(BaseModel):
'''Get the current weather in a given location'''
location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
class GetPopulation(BaseModel):
'''Get the current population in a given location'''
location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
prompt = "Which city is hotter today and which is bigger: LA or NY?"
tools = [convert_to_openai_tool(GetWeather), convert_to_openai_tool(GetPopulation)]
response = litellm.completion(model="claude-3-sonnet-20240229", messages=[{'role': 'user', 'content': prompt}], tools=tools)
print(response.choices[0].message.tool_calls)
```
```python
[ChatCompletionMessageToolCall(function=Function(arguments='{"location": "Los Angeles, CA"}', name='GetWeather'), id='toolu_01HeDWV5vP7BDFfytH5FJsja', type='function'), ChatCompletionMessageToolCall(function=Function(arguments='{"location": "New York, NY"}', name='GetWeather'), id='toolu_01EiLesUSEr3YK1DaE2jxsQv', type='function'), ChatCompletionMessageToolCall(function=Function(arguments='{"location": "Los Angeles, CA"}', name='GetPopulation'), id='toolu_01Xz26zvkBDRxEUEWm9pX6xa', type='function'), ChatCompletionMessageToolCall(function=Function(arguments='{"location": "New York, NY"}', name='GetPopulation'), id='toolu_01SDqKnsLjvUXuBsgAZdEEpp', type='function')]
```
## ChatLiteLLM
When I try the following
```python
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.utils.function_calling import convert_to_openai_tool
from langchain_community.chat_models import ChatLiteLLM
class GetWeather(BaseModel):
'''Get the current weather in a given location'''
location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
class GetPopulation(BaseModel):
'''Get the current population in a given location'''
location: str = Field(..., description="The city and state, e.g. San Francisco, CA")
prompt = "Which city is hotter today and which is bigger: LA or NY?"
tools = [convert_to_openai_tool(GetWeather), convert_to_openai_tool(GetPopulation)]
llm = ChatLiteLLM(model="claude-3-sonnet-20240229", model_kwargs={"tools": tools})
ai_msg = llm.invoke(prompt)
print(ai_msg)
print(ai_msg.tool_calls)
```
```python
content="Okay, let's find out the current weather and populations for Los Angeles and New York City:" response_metadata={'token_usage': Usage(prompt_tokens=329, completion_tokens=193, total_tokens=522), 'model': 'claude-3-sonnet-20240229', 'finish_reason': 'tool_calls'} id='run-748b7a84-84f4-497e-bba1-320bd4823937-0'
[]
```
---
When I apply the changes of this PR, the output is
```json
[{'name': 'GetWeather', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_017D2tGjiaiakB1HadsEFZ4e'}, {'name': 'GetWeather', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01WrDpJfVqLkPejWzonPCbLW'}, {'name': 'GetPopulation', 'args': {'location': 'Los Angeles, CA'}, 'id': 'toolu_016UKyYrVAV9Pz99iZGgGU7V'}, {'name': 'GetPopulation', 'args': {'location': 'New York, NY'}, 'id': 'toolu_01Sgv1imExFX1oiR1Cw88zKy'}]
```
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Co-authored-by: Igor Drozdov <idrozdov@gitlab.com>
Description:
1. partners/HuggingFace module support reading params from env. Not
adjust langchain_community/.../huggingfaceXX modules since they are
deprecated.
2. pydantic 2 @root_validator migration.
Issue: #22448#22819
---------
Co-authored-by: gongwn1 <gongwn1@lenovo.com>
**Description**: Milvus vectorstore supports both `add_documents` via
the base class and `upsert` method which deletes and re-adds documents
based on their ids
**Issue**: Due to mismatch in the interfaces the ids used by `upsert`
are neglected in `add_documents`, as `ids` are passed as argument in
`upsert` but via `kwargs` is `add_documents`
This caused exceptions and inconsistency in the DB, tested with
`auto_id=False`
**Fix**: pass `ids` via `kwargs` to `add_documents`
added pre-filtering documentation
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:** added filter vector search
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:**: n/a
- [x] **Add tests and docs**: If you're adding a new integration, please
include - No need for tests, just a simple doc update
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.
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.
# Fix streaming in mistral with ainvoke
- [x] **PR title**
- [x] **PR message**
- [x] **Add tests and docs**:
1. [x] Added a test for the fixed integration.
2. [x] An example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [x] **Lint and test**: Ran `make format`, `make lint` and `make test`
from the root of the package(s) I've modified.
Hello
* I Identified an issue in the mistral package where the callback
streaming (see on_llm_new_token) was not functioning correctly when the
streaming parameter was set to True and call with `ainvoke`.
* The root cause of the problem was the streaming not taking into
account. ( I think it's an oversight )
* To resolve the issue, I added the `streaming` attribut.
* Now, the callback with streaming works as expected when the streaming
parameter is set to True.
## How to reproduce
```
from langchain_mistralai.chat_models import ChatMistralAI
chain = ChatMistralAI(streaming=True)
# Add a callback
chain.ainvoke(..)
# Oberve on_llm_new_token
# Now, the callback is given as streaming tokens, before it was in grouped format.
```
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR implements a BaseContent object from which Document and Blob
objects will inherit proposed here:
https://github.com/langchain-ai/langchain/pull/23544
Alternative: Create a base object that only has an identifier and no
metadata.
For now decided against it, since that refactor can be done at a later
time. It also feels a bit odd since our IDs are optional at the moment.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This fix is for #21726. When having other packages installed that
require the `openai_api_base` environment variable, users are not able
to instantiate the AzureChatModels or AzureEmbeddings.
This PR adds a new value `ignore_openai_api_base` which is a bool. When
set to True, it sets `openai_api_base` to `None`
Two new tests were added for the `test_azure` and a new file
`test_azure_embeddings`
A different approach may be better for this. If you can think of better
logic, let me know and I can adjust it.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Fix#23716
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: Eugene Yurtsev <eyurtsev@gmail.com>
This PR introduces a maxsize parameter for the InMemoryCache class,
allowing users to specify the maximum number of items to store in the
cache. If the cache exceeds the specified maximum size, the oldest items
are removed. Additionally, comprehensive unit tests have been added to
ensure all functionalities are thoroughly tested. The tests are written
using pytest and cover both synchronous and asynchronous methods.
Twitter: @spyrosavl
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Fix LLM string representation for serializable objects.
Fix for issue: https://github.com/langchain-ai/langchain/issues/23257
The llm string of serializable chat models is the serialized
representation of the object. LangChain serialization dumps some basic
information about non serializable objects including their repr() which
includes an object id.
This means that if a chat model has any non serializable fields (e.g., a
cache), then any new instantiation of the those fields will change the
llm representation of the chat model and cause chat misses.
i.e., re-instantiating a postgres cache would result in cache misses!
**Description:** In the chat_models module of the language model, the
import statement for BaseModel has been moved from the conditionally
imported section to the main import area, fixing `NameError `.
**Issue:** fix `NameError `
- Description: Modified the prompt created by the function
`create_unstructured_prompt` (which is called for LLMs that do not
support function calling) by adding conditional checks that verify if
restrictions on entity types and rel_types should be added to the
prompt. If the user provides a sufficiently large text, the current
prompt **may** fail to produce results in some LLMs. I have first seen
this issue when I implemented a custom LLM class that did not support
Function Calling and used Gemini 1.5 Pro, but I was able to replicate
this issue using OpenAI models.
By loading a sufficiently large text
```python
from langchain_community.llms import Ollama
from langchain_openai import ChatOpenAI, OpenAI
from langchain_core.prompts import PromptTemplate
import re
from langchain_experimental.graph_transformers import LLMGraphTransformer
from langchain_core.documents import Document
with open("texto-longo.txt", "r") as file:
full_text = file.read()
partial_text = full_text[:4000]
documents = [Document(page_content=partial_text)] # cropped to fit GPT 3.5 context window
```
And using the chat class (that has function calling)
```python
chat_openai = ChatOpenAI(model="gpt-3.5-turbo", model_kwargs={"seed": 42})
chat_gpt35_transformer = LLMGraphTransformer(llm=chat_openai)
graph_from_chat_gpt35 = chat_gpt35_transformer.convert_to_graph_documents(documents)
```
It works:
```
>>> print(graph_from_chat_gpt35[0].nodes)
[Node(id="Jesu, Joy of Man's Desiring", type='Music'), Node(id='Godel', type='Person'), Node(id='Johann Sebastian Bach', type='Person'), Node(id='clever way of encoding the complicated expressions as numbers', type='Concept')]
```
But if you try to use the non-chat LLM class (that does not support
function calling)
```python
openai = OpenAI(
model="gpt-3.5-turbo-instruct",
max_tokens=1000,
)
gpt35_transformer = LLMGraphTransformer(llm=openai)
graph_from_gpt35 = gpt35_transformer.convert_to_graph_documents(documents)
```
It uses the prompt that has issues and sometimes does not produce any
result
```
>>> print(graph_from_gpt35[0].nodes)
[]
```
After implementing the changes, I was able to use both classes more
consistently:
```shell
>>> chat_gpt35_transformer = LLMGraphTransformer(llm=chat_openai)
>>> graph_from_chat_gpt35 = chat_gpt35_transformer.convert_to_graph_documents(documents)
>>> print(graph_from_chat_gpt35[0].nodes)
[Node(id="Jesu, Joy Of Man'S Desiring", type='Music'), Node(id='Johann Sebastian Bach', type='Person'), Node(id='Godel', type='Person')]
>>> gpt35_transformer = LLMGraphTransformer(llm=openai)
>>> graph_from_gpt35 = gpt35_transformer.convert_to_graph_documents(documents)
>>> print(graph_from_gpt35[0].nodes)
[Node(id='I', type='Pronoun'), Node(id="JESU, JOY OF MAN'S DESIRING", type='Song'), Node(id='larger memory', type='Memory'), Node(id='this nice tree structure', type='Structure'), Node(id='how you can do it all with the numbers', type='Process'), Node(id='JOHANN SEBASTIAN BACH', type='Composer'), Node(id='type of structure', type='Characteristic'), Node(id='that', type='Pronoun'), Node(id='we', type='Pronoun'), Node(id='worry', type='Verb')]
```
The results are a little inconsistent because the GPT 3.5 model may
produce incomplete json due to the token limit, but that could be solved
(or mitigated) by checking for a complete json when parsing it.
This PR adds a part of the indexing API proposed in this RFC
https://github.com/langchain-ai/langchain/pull/23544/files.
It allows rolling out `get_by_ids` which should be uncontroversial to
existing vectorstores without introducing new abstractions.
The semantics for this method depend on the ability of identifying
returned documents using the new optional ID field on documents:
https://github.com/langchain-ai/langchain/pull/23411
Alternatives are:
1. Relax the sequence requirement
```python
def get_by_ids(self, ids: Iterable[str], /) -> Iterable[Document]:
```
Rejected:
- implementations are more likley to start batching with bad defaults
- users would need to call list() or we'd need to introduce another
convenience method
2. Support more kwargs
```python
def get_by_ids(self, ids: Sequence[str], /, **kwargs) -> List[Document]:
...
```
Rejected:
- No need for `batch` parameter since IDs is a sequence
- Output cannot be customized since `Document` is fixed. (e.g.,
parameters could be useful to grab extra metadata like the vector that
was indexed with the Document or to project a part of the document)
**Description:** LanceDB didn't allow querying the database using
similarity score thresholds because the metrics value was missing. This
PR simply fixes that bug.
**Issue:** not applicable
**Dependencies:** none
**Twitter handle:** not available
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
