I also added LANGCHAIN_COMET_TRACING to enable the CometLLM tracing
integration similar to other tracing integrations. This is easier for
end-users to enable it rather than importing the callback and pass it
manually.
(This is the same content as
https://github.com/langchain-ai/langchain/pull/14650 but rebased and
squashed as something seems to confuse Github Action).
- **Description:** At the moment it's not possible to include in the
same project langchain-google-vertexai and boto3 (e.g. use bedrock and
vertex in the same application) because of the dependency resolutions
conflict. boto3 is still using urllib3 1.x, meanwhile
langchain-google-vertexai -> types-requests depends on urllib3 2.x. [the
last version of types-requests that allows urllib3 1.x is
2.31.0.6](https://pypi.org/project/types-requests/#description).
In this PR I allow the vertexai package to get that version also.
- **Twitter handle:** nicoloboschi
Description: Added support for asynchronous streaming in the Bedrock
class and corresponding tests.
Primarily:
async def aprepare_output_stream
async def _aprepare_input_and_invoke_stream
async def _astream
async def _acall
I've ensured that the code adheres to the project's linting and
formatting standards by running make format, make lint, and make test.
Issue: #12054, #11589
Dependencies: None
Tag maintainer: @baskaryan
Twitter handle: @dominic_lovric
---------
Co-authored-by: Piyush Jain <piyushjain@duck.com>
Replace this entire comment with:
- **Description:** allow user to define tVector length in PGVector when
creating the embedding store, this allows for later indexing
- **Issue:** #16132
- **Dependencies:** None
**Description:** Add support for querying TigerGraph databases through
the InquiryAI service.
**Issue**: N/A
**Dependencies:** N/A
**Twitter handle:** @TigerGraphDB
there is a case where "coords" does not exist in the "sentence"
therefore, the "split(";")" will lead to error.
we can fix that by adding "if sentence.get("coords") is not None:"
the resulting empty "sbboxes" from this scenario will raise error at
"sbboxes[0]["page"]" because sbboxes are empty.
the PDF from https://pubmed.ncbi.nlm.nih.gov/23970373/ can replicate
those errors.
This pull request integrates the TiDB database into LangChain for
storing message history, marking one of several steps towards a
comprehensive integration of TiDB with LangChain.
A simple usage
```python
from datetime import datetime
from langchain_community.chat_message_histories import TiDBChatMessageHistory
history = TiDBChatMessageHistory(
connection_string="mysql+pymysql://<host>:<PASSWORD>@<host>:4000/<db>?ssl_ca=/etc/ssl/cert.pem&ssl_verify_cert=true&ssl_verify_identity=true",
session_id="code_gen",
earliest_time=datetime.utcnow(), # Optional to set earliest_time to load messages after this time point.
)
history.add_user_message("hi! How's feature going?")
history.add_ai_message("It's almot done")
```
- **Description:** add support for kwargs in`MlflowEmbeddings`
`embed_document()` and `embed_query()` so that all the arguments
required by Cohere API (and others?) can be passed down to the server.
- **Issue:** #15234
- **Dependencies:** MLflow with MLflow Deployments (`pip install
mlflow[genai]`)
**Tests**
Now this code [adapted from the
docs](https://python.langchain.com/docs/integrations/providers/mlflow#embeddings-example)
for the Cohere API works locally.
```python
"""
Setup
-----
export COHERE_API_KEY=...
mlflow deployments start-server --config-path examples/deployments/cohere/config.yaml
Run
---
python /path/to/this/file.py
"""
embeddings = MlflowCohereEmbeddings(target_uri="http://127.0.0.1:5000", endpoint="embeddings")
print(embeddings.embed_query("hello")[:3])
print(embeddings.embed_documents(["hello", "world"])[0][:3])
```
Output
```
[0.060455322, 0.028793335, -0.025848389]
[0.031707764, 0.021057129, -0.009361267]
```
Titan Express model was not supported as a chat model because LangChain
messages were not "translated" to a text prompt.
Co-authored-by: Guillem Orellana Trullols <guillem.orellana_trullols@siemens.com>
Adjusted `deprecate` decorator to make sure decorated async functions
are still recognized as "coroutinefunction" by `inspect`.
Before change, functions such as `LLMChain.acall` which are decorated as
deprecated are not recognized as coroutine functions. After the change,
they are recognized:
```python
import inspect
from langchain import LLMChain
# Is false before change but true after.
inspect.iscoroutinefunction(LLMChain.acall)
```
- **Description:** I removed two queries to the database and left just
one whose results were formatted afterward into other type of schema
(avoided two calls to DB)
- **Issue:** /
- **Dependencies:** /
- **Twitter handle:** @supe_katarina
Enable max inner product for approximate retrieval strategy. For exact
strategy we lack the necessary `maxInnerProduct` function in the
Painless scripting language, this is why we do not add it there.
Similarity docs:
https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Joe McElroy <joseph.mcelroy@elastic.co>
Implement similarity function selector for ElasticsearchStore. The
scores coming back from Elasticsearch are already similarities (not
distances) and they are already normalized (see
[docs](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params)).
Hence we leave the scores untouched and just forward them.
This fixes#11539.
However, in hybrid mode (when keyword search and vector search are
involved) Elasticsearch currently returns no scores. This PR adds an
error message around this fact. We need to think a bit more to come up
with a solution for this case.
This PR also corrects a small error in the Elasticsearch integration
test.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Issue:** This is a PR about #16340
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
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.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Co-authored-by: yuhei.tsunoda <yuhei.tsunoda@brainpad.co.jp>
**Description:**
In this PR, I am adding a `PolygonLastQuote` Tool, which can be used to
get the latest price quote for a given ticker / stock.
Additionally, I've added a Polygon Toolkit, which we can use to
encapsulate future tools that we build for Polygon.
**Twitter handle:** [@virattt](https://twitter.com/virattt)
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- Used to be None, now is just the last chunk
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
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.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
fixed multi-query template for Vectara
added self-query template for Vectara
Also added prompt_name parameter to summarization
CC @efriis
**Twitter handle:** @ofermend
Add a version parameter while the method is in beta phase.
The idea is to make it possible to minimize making breaking changes for users while we're iterating on schema.
Once the API is stable we can assign a default version requirement.
- **Description:** Adds a text splitter based on
[Konlpy](https://konlpy.org/en/latest/#start) which is a Python package
for natural language processing (NLP) of the Korean language. (It is
like Spacy or NLTK for Korean)
- **Dependencies:** Konlpy would have to be installed before this
splitter is used,
- **Twitter handle:** @untilhamza
- **Description:** Some text-generation models on huggingface repeat the
prompt in their generated response, but not all do! The tests use "gpt2"
which DOES repeat the prompt and as such, the HuggingFaceHub class is
hardcoded to remove the first few characters of the response (to match
the len(prompt)). However, if you are using a model (such as the very
popular "meta-llama/Llama-2-7b-chat-hf") that DOES NOT repeat the prompt
in it's generated text, then the beginning of the generated text will be
cut off. This code change fixes that bug by first checking whether the
prompt is repeated in the generated response and removing it
conditionally.
- **Issue:** #16232
- **Dependencies:** N/A
- **Twitter handle:** N/A
This PR adds `astream_events` method to Runnables to make it easier to
stream data from arbitrary chains.
* Streaming only works properly in async right now
* One should use `astream()` with if mixing in imperative code as might
be done with tool implementations
* Astream_log has been modified with minimal additive changes, so no
breaking changes are expected
* Underlying callback code / tracing code should be refactored at some
point to handle things more consistently (OK for now)
- ~~[ ] verify event for on_retry~~ does not work until we implement
streaming for retry
- ~~[ ] Any rrenaming? Should we rename "event" to "hook"?~~
- [ ] Any other feedback from community?
- [x] throw NotImplementedError for `RunnableEach` for now
## Example
See this [Example
Notebook](dbbc7fa0d6/docs/docs/modules/agents/how_to/streaming_events.ipynb)
for an example with streaming in the context of an Agent
## Event Hooks Reference
Here is a reference table that shows some events that might be emitted
by the various Runnable objects.
Definitions for some of the Runnable are included after the table.
| event | name | chunk | input | output |
|----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------|
| on_chat_model_start | [model name] | | {"messages": [[SystemMessage,
HumanMessage]]} | |
| on_chat_model_stream | [model name] | AIMessageChunk(content="hello")
| | |
| on_chat_model_end | [model name] | | {"messages": [[SystemMessage,
HumanMessage]]} | {"generations": [...], "llm_output": None, ...} |
| on_llm_start | [model name] | | {'input': 'hello'} | |
| on_llm_stream | [model name] | 'Hello' | | |
| on_llm_end | [model name] | | 'Hello human!' |
| on_chain_start | format_docs | | | |
| on_chain_stream | format_docs | "hello world!, goodbye world!" | | |
| on_chain_end | format_docs | | [Document(...)] | "hello world!,
goodbye world!" |
| on_tool_start | some_tool | | {"x": 1, "y": "2"} | |
| on_tool_stream | some_tool | {"x": 1, "y": "2"} | | |
| on_tool_end | some_tool | | | {"x": 1, "y": "2"} |
| on_retriever_start | [retriever name] | | {"query": "hello"} | |
| on_retriever_chunk | [retriever name] | {documents: [...]} | | |
| on_retriever_end | [retriever name] | | {"query": "hello"} |
{documents: [...]} |
| on_prompt_start | [template_name] | | {"question": "hello"} | |
| on_prompt_end | [template_name] | | {"question": "hello"} |
ChatPromptValue(messages: [SystemMessage, ...]) |
Here are declarations associated with the events shown above:
`format_docs`:
```python
def format_docs(docs: List[Document]) -> str:
'''Format the docs.'''
return ", ".join([doc.page_content for doc in docs])
format_docs = RunnableLambda(format_docs)
```
`some_tool`:
```python
@tool
def some_tool(x: int, y: str) -> dict:
'''Some_tool.'''
return {"x": x, "y": y}
```
`prompt`:
```python
template = ChatPromptTemplate.from_messages(
[("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})
```
