github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-04-20 05:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into clickhouse-community

Browse Source
This commit is contained in:
Erick Friis
2024-03-25 12:17:04 -07:00
parent b5d8b9dc1f e1a6341940
commit a12ef0252e
436 changed files with 17239 additions and 6458 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
.github/scripts/get_min_versions.py vendored
View File

@@ -4,7 +4,12 @@ import tomllib
from packaging.version import parse as parse_version
import re
MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain", "langchain-text-splitters"]
MIN_VERSION_LIBS = [
"langchain-core",
"langchain-community",
"langchain",
"langchain-text-splitters",
]
def get_min_version(version: str) -> str:
@@ -56,12 +61,13 @@ def get_min_version_from_toml(toml_path: str):
return min_versions
# Get the TOML file path from the command line argument
toml_file = sys.argv[1]
if __name__ == "__main__":
# Get the TOML file path from the command line argument
toml_file = sys.argv[1]
# Call the function to get the minimum versions
min_versions = get_min_version_from_toml(toml_file)
# Call the function to get the minimum versions
min_versions = get_min_version_from_toml(toml_file)
print(
" ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
) # noqa: T201
print(
" ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
) # noqa: T201

1
.github/workflows/_integration_test.yml vendored
View File

@@ -75,6 +75,7 @@ jobs:
ES_API_KEY: ${{ secrets.ES_API_KEY }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
run: |
make integration_tests

43
.github/workflows/_release.yml vendored
View File

@@ -55,7 +55,7 @@ jobs:
working-directory: ${{ inputs.working-directory }}
- name: Upload build
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: dist
path: ${{ inputs.working-directory }}/dist/
@@ -157,6 +157,24 @@ jobs:
run: make tests
working-directory: ${{ inputs.working-directory }}
- name: Get minimum versions
working-directory: ${{ inputs.working-directory }}
id: min-version
run: |
poetry run pip install packaging
min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
echo "min-versions=$min_versions"
- name: Run unit tests with minimum dependency versions
if: ${{ steps.min-version.outputs.min-versions != '' }}
env:
MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
run: |
poetry run pip install $MIN_VERSIONS
make tests
working-directory: ${{ inputs.working-directory }}
- name: 'Authenticate to Google Cloud'
id: 'auth'
uses: google-github-actions/auth@v2
@@ -196,27 +214,10 @@ jobs:
ES_API_KEY: ${{ secrets.ES_API_KEY }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
run: make integration_tests
working-directory: ${{ inputs.working-directory }}
- name: Get minimum versions
working-directory: ${{ inputs.working-directory }}
id: min-version
run: |
poetry run pip install packaging
min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
echo "min-versions=$min_versions"
- name: Run unit tests with minimum dependency versions
if: ${{ steps.min-version.outputs.min-versions != '' }}
env:
MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
run: |
poetry run pip install $MIN_VERSIONS
make tests
working-directory: ${{ inputs.working-directory }}
publish:
needs:
- build
@@ -246,7 +247,7 @@ jobs:
working-directory: ${{ inputs.working-directory }}
cache-key: release
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
name: dist
path: ${{ inputs.working-directory }}/dist/
@@ -285,7 +286,7 @@ jobs:
working-directory: ${{ inputs.working-directory }}
cache-key: release
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
name: dist
path: ${{ inputs.working-directory }}/dist/

4
.github/workflows/_test_release.yml vendored
View File

@@ -48,7 +48,7 @@ jobs:
working-directory: ${{ inputs.working-directory }}
- name: Upload build
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: test-dist
path: ${{ inputs.working-directory }}/dist/
@@ -76,7 +76,7 @@ jobs:
steps:
- uses: actions/checkout@v4
- uses: actions/download-artifact@v3
- uses: actions/download-artifact@v4
with:
name: test-dist
path: ${{ inputs.working-directory }}/dist/

24
.github/workflows/check-broken-links.yml vendored Normal file
View File

@@ -0,0 +1,24 @@
name: Check Broken Links
on:
workflow_dispatch:
schedule:
- cron: '0 13 * * *'
jobs:
check-links:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Use Node.js 18.x
uses: actions/setup-node@v3
with:
node-version: 18.x
cache: "yarn"
cache-dependency-path: ./docs/yarn.lock
- name: Install dependencies
run: yarn install --immutable --mode=skip-build
working-directory: ./docs
- name: Check broken links
run: yarn check-broken-links
working-directory: ./docs

1
.gitignore vendored
View File

@@ -116,6 +116,7 @@ celerybeat.pid
.env
.envrc
.venv*
venv*
env/
ENV/
env.bak/

2
Makefile
View File

@@ -30,7 +30,7 @@ api_docs_build:
cd docs/api_reference && poetry run make html
api_docs_clean:
rm -f docs/api_reference/api_reference.rst
find ./docs/api_reference -name '*_api_reference.rst' -delete
cd docs/api_reference && poetry run make clean
api_docs_linkcheck:

61
SECURITY.md
View File

@@ -1,6 +1,61 @@
# Security Policy
## Reporting a Vulnerability
## Reporting OSS Vulnerabilities
Please report security vulnerabilities by email to `security@langchain.dev`.
This email is an alias to a subset of our maintainers, and will ensure the issue is promptly triaged and acted upon as needed.
LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide
a bounty program for our open source projects.
Please report security vulnerabilities associated with the LangChain
open source projects by visiting the following link:
[https://huntr.com/bounties/disclose/](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true)
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) LangChain [security guidelines](https://python.langchain.com/docs/security) to
understand what we consider to be a security vulnerability vs. developer
responsibility.
### In-Scope Targets
The following packages and repositories are eligible for bug bounties:
- langchain-core
- langchain (see exceptions)
- langchain-community (see exceptions)
- langgraph
- langserve
### Out of Scope Targets
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, 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
- langchain/tools
- langchain-community/tools
- Please review our [security guidelines](https://python.langchain.com/docs/security)
for more details, but generally tools interact with the real world. Developers are
expected to understand the security implications of their code and are responsible
for the security of their tools.
- Code documented with security notices. This will be decided done on a case by
case basis, but likely will not be eligible for a bounty as the code is already
documented with guidelines for developers that should be followed for making their
application secure.
- Any LangSmith related repositories or APIs see below.
## Reporting LangSmith Vulnerabilities
Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
- LangSmith site: https://smith.langchain.com
- SDK client: https://github.com/langchain-ai/langsmith-sdk
### Other Security Concerns
For any other security concerns, please contact us at `security@langchain.dev`.

2
cookbook/rewrite.ipynb
View File

@@ -245,7 +245,7 @@
"\n",
"\n",
"def _parse(text):\n",
" return text.strip(\"**\")"
" return text.strip('\"').strip(\"**\")"
]
},
{

4
cookbook/together_ai.ipynb
View File

@@ -9,7 +9,7 @@
" \n",
"[Together AI](https://python.langchain.com/docs/integrations/llms/together) has a broad set of OSS LLMs via inference API.\n",
"\n",
"See [here](https://api.together.xyz/playground). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
"See [here](https://docs.together.ai/docs/inference-models). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
"\n",
"Download the paper:\n",
"https://arxiv.org/pdf/2401.04088.pdf"
@@ -148,7 +148,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
"version": "3.9.6"
}
},
"nbformat": 4,

76
docs/docs/contributing/integrations.mdx
View File

@@ -14,19 +14,20 @@ For the most part, new integrations should be added to the Community package. Pa
In the following sections, we'll walk through how to contribute to each of these packages from a fake company, `Parrot Link AI`.
## Community Package
## Community package
The `langchain-community` package is in `libs/community` and contains most integrations.
It is installed by users with `pip install langchain-community`, and exported members can be imported with code like
It can be installed with `pip install langchain-community`, and exported members can be imported with code like
```python
from langchain_community.chat_models import ParrotLinkLLM
from langchain_community.llms import ChatParrotLink
from langchain_community.chat_models import ChatParrotLink
from langchain_community.llms import ParrotLinkLLM
from langchain_community.vectorstores import ParrotLinkVectorStore
```
The community package relies on manually-installed dependent packages, so you will see errors if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
The `community` package relies on manually-installed dependent packages, so you will see errors
if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
Let's say we wanted to implement a chat model for Parrot Link AI. We would create a new file in `libs/community/langchain_community/chat_models/parrot_link.py` with the following code:
@@ -39,7 +40,7 @@ class ChatParrotLink(BaseChatModel):
Example:
.. code-block:: python
from langchain_parrot_link import ChatParrotLink
from langchain_community.chat_models import ChatParrotLink
model = ChatParrotLink()
"""
@@ -56,9 +57,16 @@ And add documentation to:
- `docs/docs/integrations/chat/parrot_link.ipynb`
## Partner Packages
## Partner package in LangChain repo
Partner packages are in `libs/partners/*` and are installed by users with `pip install langchain-{partner}`, and exported members can be imported with code like
Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
Partner package in the `LangChain` repo is placed in `libs/partners/{partner}`
and the package source code is in `libs/partners/{partner}/langchain_{partner}`.
A package is
installed by users with `pip install langchain-{partner}`, and the package members
can be imported with code like:
```python
from langchain_{partner} import X
@@ -123,13 +131,49 @@ By default, this will include stubs for a Chat Model, an LLM, and/or a Vector St
### Write Unit and Integration Tests
Some basic tests are generated in the tests/ directory. You should add more tests to cover your package's functionality.
Some basic tests are presented in the `tests/` directory. You should add more tests to cover your package's functionality.
For information on running and implementing tests, see the [Testing guide](./testing).
### Write documentation
Documentation is generated from Jupyter notebooks in the `docs/` directory. You should move the generated notebooks to the relevant `docs/docs/integrations` directory in the monorepo root.
Documentation is generated from Jupyter notebooks in the `docs/` directory. You should place the notebooks with examples
to the relevant `docs/docs/integrations` directory in the monorepo root.
### (If Necessary) Deprecate community integration
Note: this is only necessary if you're migrating an existing community integration into
a partner package. If the component you're integrating is net-new to LangChain (i.e.
not already in the `community` package), you can skip this step.
Let's pretend we migrated our `ChatParrotLink` chat model from the community package to
the partner package. We would need to deprecate the old model in the community package.
We would do that by adding a `@deprecated` decorator to the old model as follows, in
`libs/community/langchain_community/chat_models/parrot_link.py`.
Before our change, our chat model might look like this:
```python
class ChatParrotLink(BaseChatModel):
...
```
After our change, it would look like this:
```python
from langchain_core._api.deprecation import deprecated
@deprecated(
since="0.0.<next community version>",
removal="0.2.0",
alternative_import="langchain_parrot_link.ChatParrotLink"
)
class ChatParrotLink(BaseChatModel):
...
```
You should do this for *each* component that you're migrating to the partner package.
### Additional steps
@@ -143,3 +187,15 @@ Maintainer steps (Contributors should **not** do these):
- [ ] set up pypi and test pypi projects
- [ ] add credential secrets to Github Actions
- [ ] add package to conda-forge
## Partner package in external repo
If you are creating a partner package in an external repo, you should follow the same steps as above,
but you will need to set up your own CI/CD and package management.
Name your package as `langchain-{partner}-{integration}`.
Still, you have to create the `libs/partners/{partner}-{integration}` folder in the `LangChain` monorepo
and add a `README.md` file with a link to the external repo.
See this [example](https://github.com/langchain-ai/langchain/tree/master/libs/partners/google-genai).
This allows keeping track of all the partner packages in the `LangChain` documentation.

4
docs/docs/expression_language/cookbook/multiple_chains.ipynb
View File

@@ -20,9 +20,11 @@
]
},
{
"cell_type": "raw",
"cell_type": "code",
"id": "0f316b5c",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain langchain-openai"
]

4
docs/docs/expression_language/cookbook/sql_db.ipynb
View File

@@ -20,9 +20,11 @@
]
},
{
"cell_type": "raw",
"cell_type": "code",
"id": "b3121aa8",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain langchain-openai"
]

4
docs/docs/expression_language/streaming.ipynb
View File

@@ -55,7 +55,7 @@
"id": "9eb73e8b",
"metadata": {},
"source": [
"We will show examples of streaming using the chat model from [Anthropic](https://python.langchain.com/docs/integrations/platforms/anthropic). To use the model, you will need to install the `langchain-anthropic` package. You can do this with the following command:"
"We will show examples of streaming using the chat model from [Anthropic](/docs/integrations/platforms/anthropic). To use the model, you will need to install the `langchain-anthropic` package. You can do this with the following command:"
]
},
{
@@ -658,7 +658,7 @@
"\n",
"This is a **beta API**, and we're almost certainly going to make some changes to it.\n",
"\n",
"This version parameter will allow us to mimimize such breaking changes to your code. \n",
"This version parameter will allow us to minimize such breaking changes to your code. \n",
"\n",
"In short, we are annoying you now, so we don't have to annoy you later.\n",
":::"

4
docs/docs/expression_language/why.ipynb
View File

@@ -36,9 +36,11 @@
]
},
{
"cell_type": "raw",
"cell_type": "code",
"execution_count": null,
"id": "b99b47ec",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain-core langchain-openai langchain-anthropic"
]

3
docs/docs/get_started/quickstart.mdx
View File

@@ -286,7 +286,7 @@ embeddings = OllamaEmbeddings()
</TabItem>
<TabItem value="cohere" label="Cohere (API)" default>
Make sure you have the `cohere` package installed an the appropriate environment variables set (these are the same as needed for the LLM).
Make sure you have the `cohere` package installed and the appropriate environment variables set (these are the same as needed for the LLM).
```python
from langchain_community.embeddings import CohereEmbeddings
@@ -563,7 +563,6 @@ from langchain_community.vectorstores import FAISS
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.tools.retriever import create_retriever_tool
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_openai import ChatOpenAI
from langchain import hub
from langchain.agents import create_openai_functions_agent
from langchain.agents import AgentExecutor

2
docs/docs/guides/evaluation/index.mdx
View File

@@ -23,7 +23,7 @@ We also are working to share guides and cookbooks that demonstrate how to use th
## LangSmith Evaluation
LangSmith provides an integrated evaluation and tracing framework that allows you to check for regressions, compare systems, and easily identify and fix any sources of errors and performance issues. Check out the docs on [LangSmith Evaluation](https://docs.smith.langchain.com/category/testing--evaluation) and additional [cookbooks](https://docs.smith.langchain.com/category/langsmith-cookbook) for more detailed information on evaluating your applications.
LangSmith provides an integrated evaluation and tracing framework that allows you to check for regressions, compare systems, and easily identify and fix any sources of errors and performance issues. Check out the docs on [LangSmith Evaluation](https://docs.smith.langchain.com/evaluation) and additional [cookbooks](https://docs.smith.langchain.com/cookbook) for more detailed information on evaluating your applications.
## LangChain benchmarks

2
docs/docs/guides/evaluation/string/json.ipynb
View File

@@ -7,7 +7,7 @@
"source": [
"# JSON Evaluators\n",
"\n",
"Evaluating [extraction](https://python.langchain.com/docs/use_cases/extraction) and function calling applications often comes down to validation that the LLM's string output can be parsed correctly and how it compares to a reference object. The following `JSON` validators provide functionality to check your model's output consistently.\n",
"Evaluating [extraction](/docs/use_cases/extraction) and function calling applications often comes down to validation that the LLM's string output can be parsed correctly and how it compares to a reference object. The following `JSON` validators provide functionality to check your model's output consistently.\n",
"\n",
"## JsonValidityEvaluator\n",
"\n",

2
docs/docs/guides/privacy/presidio_data_anonymization/qa_privacy_protection.ipynb
View File

@@ -24,7 +24,7 @@
"<img src=\"/img/qa_privacy_protection.png\" width=\"900\"/>\n",
"\n",
"\n",
"In the following notebook, we will not go into the details of how the anonymizer works. If you are interested, please visit [this part of the documentation](https://python.langchain.com/docs/guides/privacy/presidio_data_anonymization/).\n",
"In the following notebook, we will not go into the details of how the anonymizer works. If you are interested, please visit [this part of the documentation](/docs/guides/privacy/presidio_data_anonymization/).\n",
"\n",
"## Quickstart\n",
"\n",

2
docs/docs/integrations/callbacks/infino.ipynb
View File

@@ -129,7 +129,7 @@
"Who was famed for their Christian spirit?\n",
"Who assimilted the Roman language?\n",
"Who ruled the country of Normandy?\n",
"What principality did William the conquerer found?\n",
"What principality did William the conqueror found?\n",
"What is the original meaning of the word Norman?\n",
"When was the Latin version of the word Norman first recorded?\n",
"What name comes from the English words Normans/Normanz?\"\"\"\n",

2
docs/docs/integrations/callbacks/promptlayer.ipynb
View File

@@ -9,7 +9,7 @@
"\n",
">[PromptLayer](https://docs.promptlayer.com/introduction) is a platform for prompt engineering. It also helps with the LLM observability to visualize requests, version prompts, and track usage.\n",
">\n",
">While `PromptLayer` does have LLMs that integrate directly with LangChain (e.g. [`PromptLayerOpenAI`](https://python.langchain.com/docs/integrations/llms/promptlayer_openai)), using a callback is the recommended way to integrate `PromptLayer` with LangChain.\n",
">While `PromptLayer` does have LLMs that integrate directly with LangChain (e.g. [`PromptLayerOpenAI`](/docs/integrations/llms/promptlayer_openai)), using a callback is the recommended way to integrate `PromptLayer` with LangChain.\n",
"\n",
"In this guide, we will go over how to setup the `PromptLayerCallbackHandler`. \n",
"\n",

2
docs/docs/integrations/callbacks/trubrics.ipynb
View File

@@ -124,7 +124,7 @@
"tags": []
},
"source": [
"Here are two examples of how to use the `TrubricsCallbackHandler` with Langchain [LLMs](https://python.langchain.com/docs/modules/model_io/llms/) or [Chat Models](https://python.langchain.com/docs/modules/model_io/chat/). We will use OpenAI models, so set your `OPENAI_API_KEY` key here:"
"Here are two examples of how to use the `TrubricsCallbackHandler` with Langchain [LLMs](/docs/modules/model_io/llms/) or [Chat Models](/docs/modules/model_io/chat/). We will use OpenAI models, so set your `OPENAI_API_KEY` key here:"
]
},
{

50
docs/docs/integrations/chat/cohere.ipynb
View File

@@ -40,18 +40,10 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 1,
"id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"········\n"
]
}
],
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
@@ -90,7 +82,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 3,
"id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
"metadata": {
"tags": []
@@ -103,7 +95,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 4,
"id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
"metadata": {
"tags": []
@@ -115,7 +107,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 5,
"id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
"metadata": {
"tags": []
@@ -124,22 +116,22 @@
{
"data": {
"text/plain": [
"AIMessage(content=\"Who's there?\")"
"AIMessage(content=\"4! That's one, two, three, four. Keep adding and we'll reach new heights!\", response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 73, 'response_tokens': 21, 'total_tokens': 94, 'billed_tokens': 25}})"
]
},
"execution_count": 3,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"messages = [HumanMessage(content=\"knock knock\")]\n",
"messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
"chat.invoke(messages)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 6,
"id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
"metadata": {
"tags": []
@@ -148,10 +140,10 @@
{
"data": {
"text/plain": [
"AIMessage(content=\"Who's there?\")"
"AIMessage(content='4! According to the rules of addition, 1 + 2 equals 3, and 3 + 3 equals 6.', response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 73, 'response_tokens': 28, 'total_tokens': 101, 'billed_tokens': 32}})"
]
},
"execution_count": 4,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
@@ -162,7 +154,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 7,
"id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
"metadata": {
"tags": []
@@ -172,7 +164,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Who's there?"
"4! It's a pleasure to be of service in this mathematical game."
]
}
],
@@ -183,17 +175,17 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 8,
"id": "064288e4-f184-4496-9427-bcf148fa055e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[AIMessage(content=\"Who's there?\")]"
"[AIMessage(content='4! According to the rules of addition, 1 + 2 equals 3, and 3 + 3 equals 6.', response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 73, 'response_tokens': 28, 'total_tokens': 101, 'billed_tokens': 32}})]"
]
},
"execution_count": 6,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -214,7 +206,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 9,
"id": "0851b103",
"metadata": {},
"outputs": [],
@@ -227,17 +219,17 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 10,
"id": "ae950c0f-1691-47f1-b609-273033cae707",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"Why did the bear go to the chiropractor?\\n\\nBecause she was feeling a bit grizzly!\\n\\nHope you found that joke about bears to be a little bit amusing! If you'd like to hear another one, just let me know. In the meantime, if you have any other questions or need assistance with a different topic, feel free to let me know. \\n\\nJust remember, even if you have a sore back like the bear, it's always best to consult a licensed professional for injuries or pain you may be experiencing. \\n\\nWould you like me to tell you another joke?\")"
"AIMessage(content='What do you call a bear with no teeth? A gummy bear!', response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'token_count': {'prompt_tokens': 72, 'response_tokens': 14, 'total_tokens': 86, 'billed_tokens': 20}})"
]
},
"execution_count": 8,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -263,7 +255,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.11.7"
}
},
"nbformat": 4,

155
docs/docs/integrations/chat/dappier.ipynb Normal file
View File

@@ -0,0 +1,155 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Dappier AI"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Dappier: Powering AI with Dynamic, Real-Time Data Models**\n",
"\n",
"Dappier offers a cutting-edge platform that grants developers immediate access to a wide array of real-time data models spanning news, entertainment, finance, market data, weather, and beyond. With our pre-trained data models, you can supercharge your AI applications, ensuring they deliver precise, up-to-date responses and minimize inaccuracies.\n",
"\n",
"Dappier data models help you build next-gen LLM apps with trusted, up-to-date content from the world's leading brands. Unleash your creativity and enhance any GPT App or AI workflow with actionable, proprietary, data through a simple API. Augment your AI with proprietary data from trusted sources is the best way to ensure factual, up-to-date, responses with fewer hallucinations no matter the question.\n",
"\n",
"For Developers, By Developers\n",
"Designed with developers in mind, Dappier simplifies the journey from data integration to monetization, providing clear, straightforward paths to deploy and earn from your AI models. Experience the future of monetization infrastructure for the new internet at **https://dappier.com/**."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This example goes over how to use LangChain to interact with Dappier AI models\n",
"\n",
"-----------------------------------------------------------------------------------"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To use one of our Dappier AI Data Models, you will need an API key. Please visit Dappier Platform (https://platform.dappier.com/) to log in and create an API key in your profile.\n",
"\n",
"\n",
"You can find more details on the API reference : https://docs.dappier.com/introduction"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To work with our Dappier Chat Model you can pass the key directly through the parameter named dappier_api_key when initiating the class\n",
"or set as an environment variable.\n",
"\n",
"```bash\n",
"export DAPPIER_API_KEY=\"...\"\n",
"```\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.chat_models.dappier import ChatDappierAI\n",
"from langchain_core.messages import HumanMessage"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"chat = ChatDappierAI(\n",
" dappier_endpoint=\"https://api.dappier.com/app/datamodelconversation\",\n",
" dappier_model=\"dm_01hpsxyfm2fwdt2zet9cg6fdxt\",\n",
" dappier_api_key=\"...\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Hey there! The Kansas City Chiefs won Super Bowl LVIII in 2024. They beat the San Francisco 49ers in overtime with a final score of 25-22. It was quite the game! 🏈')"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"messages = [HumanMessage(content=\"Who won the super bowl in 2024?\")]\n",
"chat.invoke(messages)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='The Kansas City Chiefs won Super Bowl LVIII in 2024! 🏈')"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"await chat.ainvoke(messages)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.15"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

4
docs/docs/integrations/chat/huggingface.ipynb
View File

@@ -10,7 +10,7 @@
"\n",
"In particular, we will:\n",
"1. Utilize the [HuggingFaceTextGenInference](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/huggingface_text_gen_inference.py), [HuggingFaceEndpoint](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/huggingface_endpoint.py), or [HuggingFaceHub](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/huggingface_hub.py) integrations to instantiate an `LLM`.\n",
"2. Utilize the `ChatHuggingFace` class to enable any of these LLMs to interface with LangChain's [Chat Messages](https://python.langchain.com/docs/modules/model_io/chat/#messages) abstraction.\n",
"2. Utilize the `ChatHuggingFace` class to enable any of these LLMs to interface with LangChain's [Chat Messages](/docs/modules/model_io/chat/#messages) abstraction.\n",
"3. Demonstrate how to use an open-source LLM to power an `ChatAgent` pipeline\n",
"\n",
"\n",
@@ -280,7 +280,7 @@
"source": [
"## 3. Take it for a spin as an agent!\n",
"\n",
"Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. The example below is taken from [here](https://python.langchain.com/docs/modules/agents/agent_types/react#using-chat-models).\n",
"Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. The example below is taken from [here](/docs/modules/agents/agent_types/react#using-chat-models).\n",
"\n",
"> Note: To run this section, you'll need to have a [SerpAPI Token](https://serpapi.com/) saved as an environment variable: `SERPAPI_API_KEY`"
]

379
docs/docs/integrations/chat/llama2_chat.ipynb
View File

@@ -17,9 +17,9 @@
"source": [
"# Llama2Chat\n",
"\n",
"This notebook shows how to augment Llama-2 `LLM`s with the `Llama2Chat` wrapper to support the [Llama-2 chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2). Several `LLM` implementations in LangChain can be used as interface to Llama-2 chat models. These include [HuggingFaceTextGenInference](https://python.langchain.com/docs/integrations/llms/huggingface_textgen_inference), [LlamaCpp](https://python.langchain.com/docs/use_cases/question_answering/how_to/local_retrieval_qa), [GPT4All](https://python.langchain.com/docs/integrations/llms/gpt4all), ..., to mention a few examples. \n",
"This notebook shows how to augment Llama-2 `LLM`s with the `Llama2Chat` wrapper to support the [Llama-2 chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2). Several `LLM` implementations in LangChain can be used as interface to Llama-2 chat models. These include [ChatHuggingFace](/docs/integrations/chat/huggingface), [LlamaCpp](/docs/use_cases/question_answering/local_retrieval_qa), [GPT4All](/docs/integrations/llms/gpt4all), ..., to mention a few examples. \n",
"\n",
"`Llama2Chat` is a generic wrapper that implements `BaseChatModel` and can therefore be used in applications as [chat model](https://python.langchain.com/docs/modules/model_io/models/chat/). `Llama2Chat` converts a list of [chat messages](https://python.langchain.com/docs/modules/model_io/models/chat/#messages) into the [required chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2) and forwards the formatted prompt as `str` to the wrapped `LLM`."
"`Llama2Chat` is a generic wrapper that implements `BaseChatModel` and can therefore be used in applications as [chat model](/docs/modules/model_io/chat/). `Llama2Chat` converts a list of Messages into the [required chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2) and forwards the formatted prompt as `str` to the wrapped `LLM`."
]
},
{
@@ -77,7 +77,7 @@
"id": "2ff99380",
"metadata": {},
"source": [
"A [HuggingFaceTextGenInference](https://python.langchain.com/docs/integrations/llms/huggingface_textgen_inference) LLM encapsulates access to a [text-generation-inference](https://github.com/huggingface/text-generation-inference) server. In the following example, the inference server serves a [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model. It can be started locally with:\n",
"A HuggingFaceTextGenInference LLM encapsulates access to a [text-generation-inference](https://github.com/huggingface/text-generation-inference) server. In the following example, the inference server serves a [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model. It can be started locally with:\n",
"\n",
"```bash\n",
"docker run \\\n",
@@ -220,380 +220,17 @@
"id": "52c1a0b9",
"metadata": {},
"source": [
"For using a Llama-2 chat model with a [LlamaCPP](https://python.langchain.com/docs/integrations/llms/llamacpp) `LMM`, install the `llama-cpp-python` library using [these installation instructions](https://python.langchain.com/docs/integrations/llms/llamacpp#installation). The following example uses a quantized [llama-2-7b-chat.Q4_0.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_0.gguf) model stored locally at `~/Models/llama-2-7b-chat.Q4_0.gguf`. \n",
"For using a Llama-2 chat model with a [LlamaCPP](/docs/integrations/llms/llamacpp) `LMM`, install the `llama-cpp-python` library using [these installation instructions](/docs/integrations/llms/llamacpp#installation). The following example uses a quantized [llama-2-7b-chat.Q4_0.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_0.gguf) model stored locally at `~/Models/llama-2-7b-chat.Q4_0.gguf`. \n",
"\n",
"After creating a `LlamaCpp` instance, the `llm` is again wrapped into `Llama2Chat`"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "07c0d04e",
"execution_count": null,
"id": "18d10bc3-ede6-4410-a867-7c623a0efdb8",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from /home/martin/Models/llama-2-7b-chat.Q4_0.gguf (version GGUF V2)\n",
"llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 4096, 32000, 1, 1 ]\n",
"llama_model_loader: - tensor 1: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 2: blk.0.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 3: blk.0.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 4: blk.0.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 5: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 6: blk.0.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 7: blk.0.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 8: blk.0.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 9: blk.0.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 10: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 11: blk.1.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 12: blk.1.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 13: blk.1.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 14: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 15: blk.1.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 16: blk.1.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 17: blk.1.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 18: blk.1.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 19: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 20: blk.10.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 21: blk.10.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 22: blk.10.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 23: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 24: blk.10.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 25: blk.10.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 26: blk.10.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 27: blk.10.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 28: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 29: blk.11.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 30: blk.11.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 31: blk.11.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 32: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 33: blk.11.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 34: blk.11.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 35: blk.11.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 36: blk.11.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 37: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 38: blk.12.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 39: blk.12.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 40: blk.12.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 41: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 42: blk.12.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 43: blk.12.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 44: blk.12.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 45: blk.12.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 46: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 47: blk.13.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 48: blk.13.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 49: blk.13.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 50: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 51: blk.13.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 52: blk.13.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 53: blk.13.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 54: blk.13.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 55: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 56: blk.14.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 57: blk.14.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 58: blk.14.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 59: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 60: blk.14.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 61: blk.14.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 62: blk.14.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 63: blk.14.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 64: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 65: blk.15.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 66: blk.15.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 67: blk.15.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 68: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 69: blk.15.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 70: blk.15.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 71: blk.15.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 72: blk.15.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 73: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 74: blk.16.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 75: blk.16.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 76: blk.16.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 77: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 78: blk.16.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 79: blk.16.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 80: blk.16.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 81: blk.16.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 82: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 83: blk.17.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 84: blk.17.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 85: blk.17.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 86: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 87: blk.17.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 88: blk.17.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 89: blk.17.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 90: blk.17.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 91: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 92: blk.18.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 93: blk.18.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 94: blk.18.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 95: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 96: blk.18.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 97: blk.18.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 98: blk.18.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 99: blk.18.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 100: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 101: blk.19.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 102: blk.19.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 103: blk.19.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 104: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 105: blk.19.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 106: blk.19.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 107: blk.19.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 108: blk.19.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 109: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 110: blk.2.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 111: blk.2.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 112: blk.2.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 113: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 114: blk.2.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 115: blk.2.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 116: blk.2.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 117: blk.2.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 118: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 119: blk.20.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 120: blk.20.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 121: blk.20.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 122: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 123: blk.20.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 124: blk.20.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 125: blk.20.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 126: blk.20.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 127: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 128: blk.21.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 129: blk.21.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 130: blk.21.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 131: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 132: blk.21.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 133: blk.21.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 134: blk.21.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 135: blk.21.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 136: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 137: blk.22.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 138: blk.22.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 139: blk.22.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 140: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 141: blk.22.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 142: blk.22.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 143: blk.22.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 144: blk.22.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 145: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 146: blk.23.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 147: blk.23.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 148: blk.23.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 149: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 150: blk.23.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 151: blk.23.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 152: blk.23.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 153: blk.23.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 154: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 155: blk.3.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 156: blk.3.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 157: blk.3.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 158: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 159: blk.3.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 160: blk.3.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 161: blk.3.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 162: blk.3.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 163: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 164: blk.4.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 165: blk.4.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 166: blk.4.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 167: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 168: blk.4.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 169: blk.4.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 170: blk.4.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 171: blk.4.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 172: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 173: blk.5.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 174: blk.5.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 175: blk.5.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 176: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 177: blk.5.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 178: blk.5.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 179: blk.5.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 180: blk.5.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 181: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 182: blk.6.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 183: blk.6.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 184: blk.6.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 185: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 186: blk.6.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 187: blk.6.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 188: blk.6.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 189: blk.6.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 190: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 191: blk.7.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 192: blk.7.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 193: blk.7.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 194: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 195: blk.7.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 196: blk.7.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 197: blk.7.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 198: blk.7.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 199: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 200: blk.8.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 201: blk.8.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 202: blk.8.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 203: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 204: blk.8.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 205: blk.8.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 206: blk.8.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 207: blk.8.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 208: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 209: blk.9.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 210: blk.9.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 211: blk.9.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 212: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 213: blk.9.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 214: blk.9.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 215: blk.9.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 216: blk.9.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 217: output.weight q6_K [ 4096, 32000, 1, 1 ]\n",
"llama_model_loader: - tensor 218: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 219: blk.24.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 220: blk.24.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 221: blk.24.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 222: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 223: blk.24.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 224: blk.24.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 225: blk.24.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 226: blk.24.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 227: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 228: blk.25.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 229: blk.25.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 230: blk.25.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 231: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 232: blk.25.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 233: blk.25.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 234: blk.25.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 235: blk.25.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 236: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 237: blk.26.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 238: blk.26.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 239: blk.26.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 240: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 241: blk.26.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 242: blk.26.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 243: blk.26.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 244: blk.26.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 245: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 246: blk.27.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 247: blk.27.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 248: blk.27.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 249: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 250: blk.27.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 251: blk.27.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 252: blk.27.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 253: blk.27.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 254: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 255: blk.28.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 256: blk.28.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 257: blk.28.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 258: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 259: blk.28.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 260: blk.28.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 261: blk.28.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 262: blk.28.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 263: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 264: blk.29.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 265: blk.29.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 266: blk.29.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 267: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 268: blk.29.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 269: blk.29.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 270: blk.29.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 271: blk.29.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 272: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 273: blk.30.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 274: blk.30.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 275: blk.30.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 276: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 277: blk.30.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 278: blk.30.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 279: blk.30.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 280: blk.30.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 281: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 282: blk.31.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 283: blk.31.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 284: blk.31.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]\n",
"llama_model_loader: - tensor 285: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - tensor 286: blk.31.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 287: blk.31.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 288: blk.31.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 289: blk.31.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]\n",
"llama_model_loader: - tensor 290: output_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
"llama_model_loader: - kv 0: general.architecture str \n",
"llama_model_loader: - kv 1: general.name str \n",
"llama_model_loader: - kv 2: llama.context_length u32 \n",
"llama_model_loader: - kv 3: llama.embedding_length u32 \n",
"llama_model_loader: - kv 4: llama.block_count u32 \n",
"llama_model_loader: - kv 5: llama.feed_forward_length u32 \n",
"llama_model_loader: - kv 6: llama.rope.dimension_count u32 \n",
"llama_model_loader: - kv 7: llama.attention.head_count u32 \n",
"llama_model_loader: - kv 8: llama.attention.head_count_kv u32 \n",
"llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 \n",
"llama_model_loader: - kv 10: general.file_type u32 \n",
"llama_model_loader: - kv 11: tokenizer.ggml.model str \n",
"llama_model_loader: - kv 12: tokenizer.ggml.tokens arr \n",
"llama_model_loader: - kv 13: tokenizer.ggml.scores arr \n",
"llama_model_loader: - kv 14: tokenizer.ggml.token_type arr \n",
"llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 \n",
"llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 \n",
"llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32 \n",
"llama_model_loader: - kv 18: general.quantization_version u32 \n",
"llama_model_loader: - type f32: 65 tensors\n",
"llama_model_loader: - type q4_0: 225 tensors\n",
"llama_model_loader: - type q6_K: 1 tensors\n",
"llm_load_vocab: special tokens definition check successful ( 259/32000 ).\n",
"llm_load_print_meta: format = GGUF V2\n",
"llm_load_print_meta: arch = llama\n",
"llm_load_print_meta: vocab type = SPM\n",
"llm_load_print_meta: n_vocab = 32000\n",
"llm_load_print_meta: n_merges = 0\n",
"llm_load_print_meta: n_ctx_train = 4096\n",
"llm_load_print_meta: n_embd = 4096\n",
"llm_load_print_meta: n_head = 32\n",
"llm_load_print_meta: n_head_kv = 32\n",
"llm_load_print_meta: n_layer = 32\n",
"llm_load_print_meta: n_rot = 128\n",
"llm_load_print_meta: n_gqa = 1\n",
"llm_load_print_meta: f_norm_eps = 0.0e+00\n",
"llm_load_print_meta: f_norm_rms_eps = 1.0e-06\n",
"llm_load_print_meta: f_clamp_kqv = 0.0e+00\n",
"llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
"llm_load_print_meta: n_ff = 11008\n",
"llm_load_print_meta: rope scaling = linear\n",
"llm_load_print_meta: freq_base_train = 10000.0\n",
"llm_load_print_meta: freq_scale_train = 1\n",
"llm_load_print_meta: n_yarn_orig_ctx = 4096\n",
"llm_load_print_meta: rope_finetuned = unknown\n",
"llm_load_print_meta: model type = 7B\n",
"llm_load_print_meta: model ftype = mostly Q4_0\n",
"llm_load_print_meta: model params = 6.74 B\n",
"llm_load_print_meta: model size = 3.56 GiB (4.54 BPW) \n",
"llm_load_print_meta: general.name = LLaMA v2\n",
"llm_load_print_meta: BOS token = 1 '<s>'\n",
"llm_load_print_meta: EOS token = 2 '</s>'\n",
"llm_load_print_meta: UNK token = 0 '<unk>'\n",
"llm_load_print_meta: LF token = 13 '<0x0A>'\n",
"llm_load_tensors: ggml ctx size = 0.11 MB\n",
"llm_load_tensors: mem required = 3647.97 MB\n",
"..................................................................................................\n",
"llama_new_context_with_model: n_ctx = 512\n",
"llama_new_context_with_model: freq_base = 10000.0\n",
"llama_new_context_with_model: freq_scale = 1\n",
"llama_new_context_with_model: kv self size = 256.00 MB\n",
"llama_build_graph: non-view tensors processed: 740/740\n",
"llama_new_context_with_model: compute buffer total size = 2.66 MB\n",
"AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | \n"
]
}
],
"outputs": [],
"source": [
"from os.path import expanduser\n",
"\n",
@@ -731,7 +368,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.11.8"
}
},
"nbformat": 4,

1
docs/docs/integrations/chat/maritalk.ipynb
View File

@@ -65,6 +65,7 @@
"from langchain_core.output_parsers import StrOutputParser\n",
"\n",
"llm = ChatMaritalk(\n",
" model=\"sabia-2-medium\", # Available models: sabia-2-small and sabia-2-medium\n",
" api_key=\"\", # Insert your API key here\n",
" temperature=0.7,\n",
" max_tokens=100,\n",

2
docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb
View File

@@ -1005,7 +1005,7 @@
"id": "79efa62d"
},
"source": [
"Like any other integration, ChatNVIDIA is fine to support chat utilities like conversation buffers by default. Below, we show the [LangChain ConversationBufferMemory](https://python.langchain.com/docs/modules/memory/types/buffer) example applied to the `mixtral_8x7b` model."
"Like any other integration, ChatNVIDIA is fine to support chat utilities like conversation buffers by default. Below, we show the [LangChain ConversationBufferMemory](/docs/modules/memory/types/buffer) example applied to the `mixtral_8x7b` model."
]
},
{

6
docs/docs/integrations/chat/ollama.ipynb
View File

@@ -107,7 +107,7 @@
"\n",
"# using LangChain Expressive Language chain syntax\n",
"# learn more about the LCEL on\n",
"# https://python.langchain.com/docs/expression_language/why\n",
"# /docs/expression_language/why\n",
"chain = prompt | llm | StrOutputParser()\n",
"\n",
"# for brevity, response is printed in terminal\n",
@@ -235,7 +235,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Take a look at the [LangChain Expressive Language (LCEL) Interface](https://python.langchain.com/docs/expression_language/interface) for the other available interfaces for use when a chain is created.\n",
"Take a look at the [LangChain Expressive Language (LCEL) Interface](/docs/expression_language/interface) for the other available interfaces for use when a chain is created.\n",
"\n",
"## Building from source\n",
"\n",
@@ -250,7 +250,7 @@
" \n",
"Use the latest version of Ollama and supply the [`format`](https://github.com/jmorganca/ollama/blob/main/docs/api.md#json-mode) flag. The `format` flag will force the model to produce the response in JSON.\n",
"\n",
"> **Note:** You can also try out the experimental [OllamaFunctions](https://python.langchain.com/docs/integrations/chat/ollama_functions) wrapper for convenience."
"> **Note:** You can also try out the experimental [OllamaFunctions](/docs/integrations/chat/ollama_functions) wrapper for convenience."
]
},
{

14
docs/docs/integrations/chat/yuan2.ipynb
View File

@@ -4,7 +4,7 @@
"cell_type": "raw",
"source": [
"---\n",
"sidebar_label: YUAN2\n",
"sidebar_label: Yuan2.0\n",
"---"
],
"metadata": {
@@ -22,7 +22,7 @@
}
},
"source": [
"# YUAN2.0\n",
"# Yuan2.0\n",
"\n",
"This notebook shows how to use [YUAN2 API](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/docs/inference_server.md) in LangChain with the langchain.chat_models.ChatYuan2.\n",
"\n",
@@ -96,9 +96,9 @@
},
"source": [
"### Setting Up Your API server\n",
"Setting up your OpenAI compatible API server following [yuan2 openai api server](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/README-EN.md).\n",
"If you deployed api server locally, you can simply set `api_key=\"EMPTY\"` or anything you want.\n",
"Just make sure, the `api_base` is set correctly."
"Setting up your OpenAI compatible API server following [yuan2 openai api server](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/docs/Yuan2_fastchat.md).\n",
"If you deployed api server locally, you can simply set `yuan2_api_key=\"EMPTY\"` or anything you want.\n",
"Just make sure, the `yuan2_api_base` is set correctly."
]
},
{
@@ -187,7 +187,7 @@
},
"outputs": [],
"source": [
"print(chat(messages))"
"print(chat.invoke(messages))"
]
},
{
@@ -247,7 +247,7 @@
},
"outputs": [],
"source": [
"chat(messages)"
"chat.invoke(messages)"
]
},
{

4
docs/docs/integrations/document_loaders/airbyte_cdk.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte CDK"
"# Airbyte CDK (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: `AirbyteCDKLoader` is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"A lot of source connectors are implemented using the [Airbyte CDK](https://docs.airbyte.com/connector-development/cdk-python/). This loader allows to run any of these connectors and return the data as documents."

4
docs/docs/integrations/document_loaders/airbyte_gong.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Gong"
"# Airbyte Gong (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: This connector-specific loader is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Gong connector as a document loader, allowing you to load various Gong objects as documents."

4
docs/docs/integrations/document_loaders/airbyte_hubspot.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Hubspot"
"# Airbyte Hubspot (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: `AirbyteHubspotLoader` is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Hubspot connector as a document loader, allowing you to load various Hubspot objects as documents."

4
docs/docs/integrations/document_loaders/airbyte_json.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte JSON"
"# Airbyte JSON (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: `AirbyteJSONLoader` is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases."
]
},

4
docs/docs/integrations/document_loaders/airbyte_salesforce.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Salesforce"
"# Airbyte Salesforce (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: This connector-specific loader is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Salesforce connector as a document loader, allowing you to load various Salesforce objects as documents."

4
docs/docs/integrations/document_loaders/airbyte_shopify.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Shopify"
"# Airbyte Shopify (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: This connector-specific loader is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Shopify connector as a document loader, allowing you to load various Shopify objects as documents."

4
docs/docs/integrations/document_loaders/airbyte_stripe.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Stripe"
"# Airbyte Stripe (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: This connector-specific loader is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Stripe connector as a document loader, allowing you to load various Stripe objects as documents."

4
docs/docs/integrations/document_loaders/airbyte_typeform.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Typeform"
"# Airbyte Typeform (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: This connector-specific loader is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Typeform connector as a document loader, allowing you to load various Typeform objects as documents."

4
docs/docs/integrations/document_loaders/airbyte_zendesk_support.ipynb
View File

@@ -5,7 +5,7 @@
"id": "1f3a5ebf",
"metadata": {},
"source": [
"# Airbyte Zendesk Support"
"# Airbyte Zendesk Support (Deprecated)"
]
},
{
@@ -13,6 +13,8 @@
"id": "35ac77b1-449b-44f7-b8f3-3494d55c286e",
"metadata": {},
"source": [
"Note: This connector-specific loader is deprecated. Please use [`AirbyteLoader`](/docs/integrations/document_loaders/airbyte) instead.\n",
"\n",
">[Airbyte](https://github.com/airbytehq/airbyte) is a data integration platform for ELT pipelines from APIs, databases & files to warehouses & lakes. It has the largest catalog of ELT connectors to data warehouses and databases.\n",
"\n",
"This loader exposes the Zendesk Support connector as a document loader, allowing you to load various objects as documents."

5
docs/docs/integrations/document_loaders/bilibili.ipynb
View File

@@ -9,7 +9,7 @@
"\n",
">[Bilibili](https://www.bilibili.tv/) is one of the most beloved long-form video sites in China.\n",
"\n",
"This loader utilizes the [bilibili-api](https://github.com/MoyuScript/bilibili-api) to fetch the text transcript from `Bilibili`.\n",
"This loader utilizes the [bilibili-api](https://github.com/Nemo2011/bilibili-api) to fetch the text transcript from `Bilibili`.\n",
"\n",
"With this BiliBiliLoader, users can easily obtain the transcript of their desired video content on the platform."
]
@@ -58,9 +58,6 @@
"id": "3470dadf",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
},
"pycharm": {
"name": "#%%\n"
}

12
docs/docs/integrations/document_loaders/docugami.ipynb
View File

@@ -22,7 +22,7 @@
"outputs": [],
"source": [
"# You need the dgml-utils package to use the DocugamiLoader (run pip install directly without \"poetry run\" if you are not using poetry)\n",
"!poetry run pip install dgml-utils==0.3.0 --upgrade --quiet"
"!poetry run pip install docugami-langchain dgml-utils==0.3.0 --upgrade --quiet"
]
},
{
@@ -56,7 +56,7 @@
"source": [
"import os\n",
"\n",
"from langchain_community.document_loaders import DocugamiLoader"
"from docugami_langchain.document_loaders import DocugamiLoader"
]
},
{
@@ -118,7 +118,7 @@
"\n",
"1. You can set min and max chunk size, which the system tries to adhere to with minimal truncation. You can set `loader.min_text_length` and `loader.max_text_length` to control these.\n",
"2. By default, only the text for chunks is returned. However, Docugami's XML knowledge graph has additional rich information including semantic tags for entities inside the chunk. Set `loader.include_xml_tags = True` if you want the additional xml metadata on the returned chunks.\n",
"3. In addition, you can set `loader.parent_hierarchy_levels` if you want Docugami to return parent chunks in the chunks it returns. The child chunks point to the parent chunks via the `loader.parent_id_key` value. This is useful e.g. with the [MultiVector Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. See detailed example later in this notebook."
"3. In addition, you can set `loader.parent_hierarchy_levels` if you want Docugami to return parent chunks in the chunks it returns. The child chunks point to the parent chunks via the `loader.parent_id_key` value. This is useful e.g. with the [MultiVector Retriever](/docs/modules/data_connection/retrievers/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. See detailed example later in this notebook."
]
},
{
@@ -457,7 +457,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Documents are inherently semi-structured and the DocugamiLoader is able to navigate the semantic and structural contours of the document to provide parent chunk references on the chunks it returns. This is useful e.g. with the [MultiVector Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval.\n",
"Documents are inherently semi-structured and the DocugamiLoader is able to navigate the semantic and structural contours of the document to provide parent chunk references on the chunks it returns. This is useful e.g. with the [MultiVector Retriever](/docs/modules/data_connection/retrievers/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval.\n",
"\n",
"To get parent chunk references, you can set `loader.parent_hierarchy_levels` to a non-zero value."
]
@@ -470,7 +470,7 @@
"source": [
"from typing import Dict, List\n",
"\n",
"from langchain_community.document_loaders import DocugamiLoader\n",
"from docugami_langchain.document_loaders import DocugamiLoader\n",
"from langchain_core.documents import Document\n",
"\n",
"loader = DocugamiLoader(docset_id=\"zo954yqy53wp\")\n",
@@ -655,7 +655,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.1"
"version": "3.9.18"
}
},
"nbformat": 4,

26
docs/docs/integrations/document_loaders/dropbox.ipynb
View File

File diff suppressed because one or more lines are too long

2
docs/docs/integrations/document_loaders/geopandas.ipynb
View File

@@ -47,7 +47,7 @@
"id": "04981332",
"metadata": {},
"source": [
"Create a GeoPandas dataframe from [`Open City Data`](https://python.langchain.com/docs/integrations/document_loaders/open_city_data) as an example input."
"Create a GeoPandas dataframe from [`Open City Data`](/docs/integrations/document_loaders/open_city_data) as an example input."
]
},
{

2
docs/docs/integrations/document_loaders/google_bigtable.ipynb
View File

@@ -8,7 +8,7 @@
"\n",
"> [Bigtable](https://cloud.google.com/bigtable) is a key-value and wide-column store, ideal for fast access to structured, semi-structured, or unstructured data. Extend your database application to build AI-powered experiences leveraging Bigtable's Langchain integrations.\n",
"\n",
"This notebook goes over how to use [Bigtable](https://cloud.google.com/bigtable) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `BigtableLoader` and `BigtableSaver`.\n",
"This notebook goes over how to use [Bigtable](https://cloud.google.com/bigtable) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `BigtableLoader` and `BigtableSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-bigtable-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/google_cloud_sql_mssql.ipynb
View File

@@ -8,7 +8,7 @@
"\n",
"> [Cloud SQL](https://cloud.google.com/sql) is a fully managed relational database service that offers high performance, seamless integration, and impressive scalability. It offers [MySQL](https://cloud.google.com/sql/mysql), [PostgreSQL](https://cloud.google.com/sql/postgres), and [SQL Server](https://cloud.google.com/sql/sqlserver) database engines. Extend your database application to build AI-powered experiences leveraging Cloud SQL's Langchain integrations.\n",
"\n",
"This notebook goes over how to use [Cloud SQL for SQL server](https://cloud.google.com/sql/sqlserver) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `MSSQLLoader` and `MSSQLDocumentSaver`.\n",
"This notebook goes over how to use [Cloud SQL for SQL server](https://cloud.google.com/sql/sqlserver) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `MSSQLLoader` and `MSSQLDocumentSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-cloud-sql-mssql-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/google_cloud_sql_mysql.ipynb
View File

@@ -8,7 +8,7 @@
"\n",
"> [Cloud SQL](https://cloud.google.com/sql) is a fully managed relational database service that offers high performance, seamless integration, and impressive scalability. It offers [MySQL](https://cloud.google.com/sql/mysql), [PostgreSQL](https://cloud.google.com/sql/postgresql), and [SQL Server](https://cloud.google.com/sql/sqlserver) database engines. Extend your database application to build AI-powered experiences leveraging Cloud SQL's Langchain integrations.\n",
"\n",
"This notebook goes over how to use [Cloud SQL for MySQL](https://cloud.google.com/sql/mysql) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `MySQLLoader` and `MySQLDocumentSaver`.\n",
"This notebook goes over how to use [Cloud SQL for MySQL](https://cloud.google.com/sql/mysql) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `MySQLLoader` and `MySQLDocumentSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-cloud-sql-mysql-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/google_datastore.ipynb
View File

@@ -8,7 +8,7 @@
"\n",
"> [Firestore in Datastore Mode](https://cloud.google.com/datastore) is a NoSQL document database built for automatic scaling, high performance and ease of application development. Extend your database application to build AI-powered experiences leveraging Datastore's Langchain integrations.\n",
"\n",
"This notebook goes over how to use [Firestore in Datastore Mode](https://cloud.google.com/datastore) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `DatastoreLoader` and `DatastoreSaver`.\n",
"This notebook goes over how to use [Firestore in Datastore Mode](https://cloud.google.com/datastore) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `DatastoreLoader` and `DatastoreSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-datastore-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/google_el_carro.ipynb
View File

@@ -18,7 +18,7 @@
"by leveraging the El Carro Langchain integration.\n",
"\n",
"This guide goes over how to use El Carro Langchain integration to\n",
"[save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/)\n",
"[save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/)\n",
"with `ElCarroLoader` and `ElCarroDocumentSaver`. This integration works for any Oracle database, regardless of where it is running.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-el-carro-python/).\n",

2
docs/docs/integrations/document_loaders/google_firestore.ipynb
View File

@@ -8,7 +8,7 @@
"\n",
"> [Firestore](https://cloud.google.com/firestore) is a serverless document-oriented database that scales to meet any demand. Extend your database application to build AI-powered experiences leveraging Firestore's Langchain integrations.\n",
"\n",
"This notebook goes over how to use [Firestore](https://cloud.google.com/firestore) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `FirestoreLoader` and `FirestoreSaver`.\n",
"This notebook goes over how to use [Firestore](https://cloud.google.com/firestore) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `FirestoreLoader` and `FirestoreSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-firestore-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/google_memorystore_redis.ipynb
View File

@@ -10,7 +10,7 @@
"\n",
"> [Google Memorystore for Redis](https://cloud.google.com/memorystore/docs/redis/memorystore-for-redis-overview) is a fully-managed service that is powered by the Redis in-memory data store to build application caches that provide sub-millisecond data access. Extend your database application to build AI-powered experiences leveraging Memorystore for Redis's Langchain integrations.\n",
"\n",
"This notebook goes over how to use [Memorystore for Redis](https://cloud.google.com/memorystore/docs/redis/memorystore-for-redis-overview) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `MemorystoreDocumentLoader` and `MemorystoreDocumentSaver`.\n",
"This notebook goes over how to use [Memorystore for Redis](https://cloud.google.com/memorystore/docs/redis/memorystore-for-redis-overview) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `MemorystoreDocumentLoader` and `MemorystoreDocumentSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-memorystore-redis-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/google_spanner.ipynb
View File

@@ -8,7 +8,7 @@
"\n",
"> [Spanner](https://cloud.google.com/spanner) is a highly scalable database that combines unlimited scalability with relational semantics, such as secondary indexes, strong consistency, schemas, and SQL providing 99.999% availability in one easy solution.\n",
"\n",
"This notebook goes over how to use [Spanner](https://cloud.google.com/spanner) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `SpannerLoader` and `SpannerDocumentSaver`.\n",
"This notebook goes over how to use [Spanner](https://cloud.google.com/spanner) to [save, load and delete langchain documents](/docs/modules/data_connection/document_loaders/) with `SpannerLoader` and `SpannerDocumentSaver`.\n",
"\n",
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-spanner-python/).\n",
"\n",

2
docs/docs/integrations/document_loaders/grobid.ipynb
View File

@@ -16,7 +16,7 @@
"---\n",
"The best approach is to install Grobid via docker, see https://grobid.readthedocs.io/en/latest/Grobid-docker/. \n",
"\n",
"(Note: additional instructions can be found [here](https://python.langchain.com/docs/docs/integrations/providers/grobid.mdx).)\n",
"(Note: additional instructions can be found [here](/docs/integrations/providers/grobid).)\n",
"\n",
"Once grobid is up-and-running you can interact as described below. \n"
]

48
docs/docs/integrations/document_loaders/tomarkdown.ipynb
View File

@@ -39,9 +39,7 @@
"metadata": {},
"outputs": [],
"source": [
"loader = ToMarkdownLoader(\n",
" url=\"https://python.langchain.com/docs/get_started/introduction\", api_key=api_key\n",
")"
"loader = ToMarkdownLoader(url=\"/docs/get_started/introduction\", api_key=api_key)"
]
},
{
@@ -72,9 +70,9 @@
"This framework consists of several parts.\n",
"\n",
"- **LangChain Libraries**: The Python and JavaScript libraries. Contains interfaces and integrations for a myriad of components, a basic run time for combining these components into chains and agents, and off-the-shelf implementations of chains and agents.\n",
"- **[LangChain Templates](https://python.langchain.com/docs/templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.\n",
"- **[LangServe](https://python.langchain.com/docs/langserve)**: A library for deploying LangChain chains as a REST API.\n",
"- **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.\n",
"- **[LangChain Templates](/docs/templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.\n",
"- **[LangServe](/docs/langserve)**: A library for deploying LangChain chains as a REST API.\n",
"- **[LangSmith](/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.\n",
"\n",
"![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](https://python.langchain.com/assets/images/langchain_stack-f21828069f74484521f38199910007c1.svg)\n",
"\n",
@@ -101,11 +99,11 @@
"\n",
"## Get started [​](\\#get-started \"Direct link to Get started\")\n",
"\n",
"[Here’s](https://python.langchain.com/docs/get_started/installation) how to install LangChain, set up your environment, and start building.\n",
"[Here’s](/docs/get_started/installation) how to install LangChain, set up your environment, and start building.\n",
"\n",
"We recommend following our [Quickstart](https://python.langchain.com/docs/get_started/quickstart) guide to familiarize yourself with the framework by building your first LangChain application.\n",
"We recommend following our [Quickstart](/docs/get_started/quickstart) guide to familiarize yourself with the framework by building your first LangChain application.\n",
"\n",
"Read up on our [Security](https://python.langchain.com/docs/security) best practices to make sure you're developing safely with LangChain.\n",
"Read up on our [Security](/docs/security) best practices to make sure you're developing safely with LangChain.\n",
"\n",
"note\n",
"\n",
@@ -115,43 +113,43 @@
"\n",
"LCEL 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.\n",
"\n",
"- **[Overview](https://python.langchain.com/docs/expression_language/)**: LCEL and its benefits\n",
"- **[Interface](https://python.langchain.com/docs/expression_language/interface)**: The standard interface for LCEL objects\n",
"- **[How-to](https://python.langchain.com/docs/expression_language/how_to)**: Key features of LCEL\n",
"- **[Cookbook](https://python.langchain.com/docs/expression_language/cookbook)**: Example code for accomplishing common tasks\n",
"- **[Overview](/docs/expression_language/)**: LCEL and its benefits\n",
"- **[Interface](/docs/expression_language/interface)**: The standard interface for LCEL objects\n",
"- **[How-to](/docs/expression_language/how_to)**: Key features of LCEL\n",
"- **[Cookbook](/docs/expression_language/cookbook)**: Example code for accomplishing common tasks\n",
"\n",
"## Modules [​](\\#modules \"Direct link to Modules\")\n",
"\n",
"LangChain provides standard, extendable interfaces and integrations for the following modules:\n",
"\n",
"#### [Model I/O](https://python.langchain.com/docs/modules/model_io/) [​](\\#model-io \"Direct link to model-io\")\n",
"#### [Model I/O](/docs/modules/model_io/) [​](\\#model-io \"Direct link to model-io\")\n",
"\n",
"Interface with language models\n",
"\n",
"#### [Retrieval](https://python.langchain.com/docs/modules/data_connection/) [​](\\#retrieval \"Direct link to retrieval\")\n",
"#### [Retrieval](/docs/modules/data_connection/) [​](\\#retrieval \"Direct link to retrieval\")\n",
"\n",
"Interface with application-specific data\n",
"\n",
"#### [Agents](https://python.langchain.com/docs/modules/agents/) [​](\\#agents \"Direct link to agents\")\n",
"#### [Agents](/docs/modules/agents/) [​](\\#agents \"Direct link to agents\")\n",
"\n",
"Let models choose which tools to use given high-level directives\n",
"\n",
"## Examples, ecosystem, and resources [​](\\#examples-ecosystem-and-resources \"Direct link to Examples, ecosystem, and resources\")\n",
"\n",
"### [Use cases](https://python.langchain.com/docs/use_cases/question_answering/) [​](\\#use-cases \"Direct link to use-cases\")\n",
"### [Use cases](/docs/use_cases/question_answering/) [​](\\#use-cases \"Direct link to use-cases\")\n",
"\n",
"Walkthroughs and techniques for common end-to-end use cases, like:\n",
"\n",
"- [Document question answering](https://python.langchain.com/docs/use_cases/question_answering/)\n",
"- [Chatbots](https://python.langchain.com/docs/use_cases/chatbots/)\n",
"- [Analyzing structured data](https://python.langchain.com/docs/use_cases/sql/)\n",
"- [Document question answering](/docs/use_cases/question_answering/)\n",
"- [Chatbots](/docs/use_cases/chatbots/)\n",
"- [Analyzing structured data](/docs/use_cases/sql/)\n",
"- and much more...\n",
"\n",
"### [Integrations](https://python.langchain.com/docs/integrations/providers/) [​](\\#integrations \"Direct link to integrations\")\n",
"### [Integrations](/docs/integrations/providers/) [​](\\#integrations \"Direct link to integrations\")\n",
"\n",
"LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](https://python.langchain.com/docs/integrations/providers/).\n",
"LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/providers/).\n",
"\n",
"### [Guides](https://python.langchain.com/docs/guides/debugging) [​](\\#guides \"Direct link to guides\")\n",
"### [Guides](/docs/guides/debugging) [​](\\#guides \"Direct link to guides\")\n",
"\n",
"Best practices for developing with LangChain.\n",
"\n",
@@ -159,11 +157,11 @@
"\n",
"Head to the reference section for full documentation of all classes and methods in the LangChain and LangChain Experimental Python packages.\n",
"\n",
"### [Developer's guide](https://python.langchain.com/docs/contributing) [​](\\#developers-guide \"Direct link to developers-guide\")\n",
"### [Developer's guide](/docs/contributing) [​](\\#developers-guide \"Direct link to developers-guide\")\n",
"\n",
"Check out the developer's guide for guidelines on contributing and help getting your dev environment set up.\n",
"\n",
"Head to the [Community navigator](https://python.langchain.com/docs/community) to find places to ask questions, share feedback, meet other developers, and dream about the future of LLM’s.\n"
"Head to the [Community navigator](/docs/community) to find places to ask questions, share feedback, meet other developers, and dream about the future of LLM’s.\n"
]
}
],

13
docs/docs/integrations/llms/baseten.ipynb
View File

@@ -7,7 +7,7 @@
"source": [
"# Baseten\n",
"\n",
"[Baseten](https://baseten.co) is a [Provider](https://python.langchain.com/docs/integrations/providers/baseten) in the LangChain ecosystem that implements the LLMs component.\n",
"[Baseten](https://baseten.co) is a [Provider](/docs/integrations/providers/baseten) in the LangChain ecosystem that implements the LLMs component.\n",
"\n",
"This example demonstrates using an LLM — Mistral 7B hosted on Baseten — with LangChain."
]
@@ -83,7 +83,7 @@
"\n",
"We can chain together multiple calls to one or multiple models, which is the whole point of Langchain!\n",
"\n",
"For example, we can replace GPT with Mistral in this [demo of terminal emulation](https://python.langchain.com/docs/modules/agents/how_to/chatgpt_clone)."
"For example, we can replace GPT with Mistral in this demo of terminal emulation."
]
},
{
@@ -167,7 +167,7 @@
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@@ -181,10 +181,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
},
"orig_nbformat": 4
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}

6
docs/docs/integrations/llms/fireworks.ipynb
View File

@@ -54,6 +54,8 @@
"import getpass\n",
"import os\n",
"\n",
"from langchain_fireworks import Fireworks\n",
"\n",
"if \"FIREWORKS_API_KEY\" not in os.environ:\n",
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
"\n",
@@ -181,7 +183,7 @@
],
"source": [
"from langchain.prompts import PromptTemplate\n",
"from langchain_community.llms.fireworks import Fireworks\n",
"from langchain_fireworks import Fireworks\n",
"\n",
"llm = Fireworks(\n",
" model=\"accounts/fireworks/models/mixtral-8x7b-instruct\",\n",
@@ -249,7 +251,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.9.6"
}
},
"nbformat": 4,

2
docs/docs/integrations/llms/google_ai.ipynb
View File

@@ -25,7 +25,7 @@
"id": "bead5ede-d9cc-44b9-b062-99c90a10cf40",
"metadata": {},
"source": [
"A guide on using [Google Generative AI](https://developers.generativeai.google/) models with Langchain. Note: It's separate from Google Cloud Vertex AI [integration](https://python.langchain.com/docs/integrations/llms/google_vertex_ai_palm)."
"A guide on using [Google Generative AI](https://developers.generativeai.google/) models with Langchain. Note: It's separate from Google Cloud Vertex AI [integration](/docs/integrations/llms/google_vertex_ai_palm)."
]
},
{

8
docs/docs/integrations/llms/huggingface_pipelines.ipynb
View File

@@ -256,7 +256,7 @@
"metadata": {},
"outputs": [],
"source": [
"!optimum-cli export openvino --model gpt2 ov_model"
"!optimum-cli export openvino --model gpt2 ov_model_dir"
]
},
{
@@ -274,9 +274,9 @@
"metadata": {},
"outputs": [],
"source": [
"!optimum-cli export openvino --model gpt2 --weight-format int8 ov_model # for 8-bit quantization\n",
"!optimum-cli export openvino --model gpt2 --weight-format int8 ov_model_dir # for 8-bit quantization\n",
"\n",
"!optimum-cli export openvino --model gpt2 --weight-format int4 ov_model # for 4-bit quantization"
"!optimum-cli export openvino --model gpt2 --weight-format int4 ov_model_dir # for 4-bit quantization"
]
},
{
@@ -287,7 +287,7 @@
"outputs": [],
"source": [
"ov_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"ov_model\",\n",
" model_id=\"ov_model_dir\",\n",
" task=\"text-generation\",\n",
" backend=\"openvino\",\n",
" model_kwargs={\"device\": \"CPU\", \"ov_config\": ov_config},\n",

22
docs/docs/integrations/llms/llamacpp.ipynb
View File

@@ -208,11 +208,9 @@
},
"outputs": [],
"source": [
"from langchain.callbacks.manager import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"from langchain.chains import LLMChain\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain_community.llms import LlamaCpp"
"from langchain_community.llms import LlamaCpp\n",
"from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler\n",
"from langchain_core.prompts import PromptTemplate"
]
},
{
@@ -329,10 +327,10 @@
}
],
"source": [
"prompt = \"\"\"\n",
"question = \"\"\"\n",
"Question: A rap battle between Stephen Colbert and John Oliver\n",
"\"\"\"\n",
"llm.invoke(prompt)"
"llm.invoke(question)"
]
},
{
@@ -360,7 +358,7 @@
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
"llm_chain = prompt | llm"
]
},
{
@@ -406,7 +404,7 @@
],
"source": [
"question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
"llm_chain.run(question)"
"llm_chain.invoke({\"question\": question})"
]
},
{
@@ -488,9 +486,9 @@
}
],
"source": [
"llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
"llm_chain = prompt | llm\n",
"question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
"llm_chain.run(question)"
"llm_chain.invoke({\"question\": question})"
]
},
{
@@ -710,7 +708,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.6"
"version": "3.9.1"
},
"vscode": {
"interpreter": {

2
docs/docs/integrations/llms/llamafile.ipynb
View File

@@ -105,7 +105,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"To learn more about the LangChain Expressive Language and the available methods on an LLM, see the [LCEL Interface](https://python.langchain.com/docs/expression_language/interface)"
"To learn more about the LangChain Expressive Language and the available methods on an LLM, see the [LCEL Interface](/docs/expression_language/interface)"
]
}
],

4
docs/docs/integrations/llms/llm_caching.ipynb
View File

@@ -1357,7 +1357,9 @@
{
"cell_type": "markdown",
"source": [
"## Azure Cosmos DB Semantic Cache"
"## Azure Cosmos DB Semantic Cache\n",
"\n",
"You can use this integrated [vector database](https://learn.microsoft.com/en-us/azure/cosmos-db/vector-database) for caching."
],
"metadata": {
"collapsed": false

2
docs/docs/integrations/llms/ollama.ipynb
View File

@@ -175,7 +175,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"To learn more about the LangChain Expressive Language and the available methods on an LLM, see the [LCEL Interface](https://python.langchain.com/docs/expression_language/interface)"
"To learn more about the LangChain Expressive Language and the available methods on an LLM, see the [LCEL Interface](/docs/expression_language/interface)"
]
},
{

249
docs/docs/integrations/llms/openvino.ipynb Normal file
View File

@@ -0,0 +1,249 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "959300d4",
"metadata": {},
"source": [
"# OpenVINO Local Pipelines\n",
"\n",
"[OpenVINO™](https://github.com/openvinotoolkit/openvino) is an open-source toolkit for optimizing and deploying AI inference. The OpenVINO™ Runtime can infer models on different hardware [devices](https://github.com/openvinotoolkit/openvino?tab=readme-ov-file#supported-hardware-matrix). It can help to boost deep learning performance in computer vision, automatic speech recognition, natural language processing and other common tasks.\n",
"\n",
"OpenVINO models can be run locally through the `HuggingFacePipeline` [class](https://python.langchain.com/docs/integrations/llms/huggingface_pipeline). To deploy a model with OpenVINO, you can specify the `backend=\"openvino\"` parameter to trigger OpenVINO as backend inference framework."
]
},
{
"cell_type": "markdown",
"id": "4c1b8450-5eaf-4d34-8341-2d785448a1ff",
"metadata": {
"tags": []
},
"source": [
"To use, you should have the ``optimum-intel`` with OpenVINO Accelerator python [package installed](https://github.com/huggingface/optimum-intel?tab=readme-ov-file#installation)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d772b637-de00-4663-bd77-9bc96d798db2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%pip install --upgrade-strategy eager \"optimum[openvino,nncf]\" --quiet"
]
},
{
"cell_type": "markdown",
"id": "91ad075f-71d5-4bc8-ab91-cc0ad5ef16bb",
"metadata": {},
"source": [
"### Model Loading\n",
"\n",
"Models can be loaded by specifying the model parameters using the `from_model_id` method.\n",
"\n",
"If you have an Intel GPU, you can specify `model_kwargs={\"device\": \"GPU\"}` to run inference on it."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "165ae236-962a-4763-8052-c4836d78a5d2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline\n",
"\n",
"ov_config = {\"PERFORMANCE_HINT\": \"LATENCY\", \"NUM_STREAMS\": \"1\", \"CACHE_DIR\": \"\"}\n",
"\n",
"ov_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"gpt2\",\n",
" task=\"text-generation\",\n",
" backend=\"openvino\",\n",
" model_kwargs={\"device\": \"CPU\", \"ov_config\": ov_config},\n",
" pipeline_kwargs={\"max_new_tokens\": 10},\n",
")"
]
},
{
"cell_type": "markdown",
"id": "00104b27-0c15-4a97-b198-4512337ee211",
"metadata": {},
"source": [
"They can also be loaded by passing in an existing `optimum-intel` pipeline directly"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7f426a4f",
"metadata": {},
"outputs": [],
"source": [
"from optimum.intel.openvino import OVModelForCausalLM\n",
"from transformers import AutoTokenizer, pipeline\n",
"\n",
"model_id = \"gpt2\"\n",
"device = \"CPU\"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
"ov_model = OVModelForCausalLM.from_pretrained(\n",
" model_id, device=device, ov_config=ov_config\n",
")\n",
"ov_pipe = pipeline(\n",
" \"text-generation\", model=ov_model, tokenizer=tokenizer, max_new_tokens=10\n",
")\n",
"hf = HuggingFacePipeline(pipeline=ov_pipe)"
]
},
{
"cell_type": "markdown",
"id": "60e7ba8d",
"metadata": {},
"source": [
"### Create Chain\n",
"\n",
"With the model loaded into memory, you can compose it with a prompt to\n",
"form a chain."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3acf0069",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"\n",
"template = \"\"\"Question: {question}\n",
"\n",
"Answer: Let's think step by step.\"\"\"\n",
"prompt = PromptTemplate.from_template(template)\n",
"\n",
"chain = prompt | ov_llm\n",
"\n",
"question = \"What is electroencephalography?\"\n",
"\n",
"print(chain.invoke({\"question\": question}))"
]
},
{
"cell_type": "markdown",
"id": "12524837-e9ab-455a-86be-66b95f4f893a",
"metadata": {},
"source": [
"### Inference with local OpenVINO model\n",
"\n",
"It is possible to [export your model](https://github.com/huggingface/optimum-intel?tab=readme-ov-file#export) to the OpenVINO IR format with the CLI, and load the model from local folder.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d1104a2-79c7-43a6-aa1c-8076a5ad7747",
"metadata": {},
"outputs": [],
"source": [
"!optimum-cli export openvino --model gpt2 ov_model_dir"
]
},
{
"cell_type": "markdown",
"id": "0f7a6d21",
"metadata": {},
"source": [
"It is recommended to apply 8 or 4-bit weight quantization to reduce inference latency and model footprint using `--weight-format`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "97088ea0",
"metadata": {},
"outputs": [],
"source": [
"!optimum-cli export openvino --model gpt2 --weight-format int8 ov_model_dir # for 8-bit quantization\n",
"\n",
"!optimum-cli export openvino --model gpt2 --weight-format int4 ov_model_dir # for 4-bit quantization"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ac71e60d-5595-454e-8602-03ebb0248205",
"metadata": {},
"outputs": [],
"source": [
"ov_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"ov_model_dir\",\n",
" task=\"text-generation\",\n",
" backend=\"openvino\",\n",
" model_kwargs={\"device\": \"CPU\", \"ov_config\": ov_config},\n",
" pipeline_kwargs={\"max_new_tokens\": 10},\n",
")\n",
"\n",
"ov_chain = prompt | ov_llm\n",
"\n",
"question = \"What is electroencephalography?\"\n",
"\n",
"print(ov_chain.invoke({\"question\": question}))"
]
},
{
"cell_type": "markdown",
"id": "a2c5726c",
"metadata": {},
"source": [
"You can get additional inference speed improvement with Dynamic Quantization of activations and KV-cache quantization. These options can be enabled with `ov_config` as follows:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a1f9c2c5",
"metadata": {},
"outputs": [],
"source": [
"ov_config = {\n",
" \"KV_CACHE_PRECISION\": \"u8\",\n",
" \"DYNAMIC_QUANTIZATION_GROUP_SIZE\": \"32\",\n",
" \"PERFORMANCE_HINT\": \"LATENCY\",\n",
" \"NUM_STREAMS\": \"1\",\n",
" \"CACHE_DIR\": \"\",\n",
"}"
]
},
{
"cell_type": "markdown",
"id": "da9a9239",
"metadata": {},
"source": [
"For more information refer to [OpenVINO LLM guide](https://docs.openvino.ai/2024/openvino-workflow/generative-ai-models-guide.html)."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

2
docs/docs/integrations/llms/promptlayer_openai.ipynb
View File

@@ -14,7 +14,7 @@
"\n",
"This example showcases how to connect to [PromptLayer](https://www.promptlayer.com) to start recording your OpenAI requests.\n",
"\n",
"Another example is [here](https://python.langchain.com/docs/integrations/providers/promptlayer)."
"Another example is [here](/docs/integrations/providers/promptlayer)."
]
},
{

6
docs/docs/integrations/llms/replicate.ipynb
View File

@@ -290,7 +290,7 @@
"metadata": {},
"source": [
"## Streaming Response\n",
"You can optionally stream the response as it is produced, which is helpful to show interactivity to users for time-consuming generations. See detailed docs on [Streaming](https://python.langchain.com/docs/modules/model_io/llms/how_to/streaming_llm) for more information."
"You can optionally stream the response as it is produced, which is helpful to show interactivity to users for time-consuming generations. See detailed docs on [Streaming](/docs/modules/model_io/llms/streaming_llm) for more information."
]
},
{
@@ -540,9 +540,9 @@
],
"metadata": {
"kernelspec": {
"display_name": "poetry-venv",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "poetry-venv"
"name": "python3"
},
"language_info": {
"codemirror_mode": {

2
docs/docs/integrations/llms/together.ipynb
View File

@@ -13,7 +13,7 @@
"https://api.together.xyz/settings/api-keys. This can be passed in as init param\n",
"``together_api_key`` or set as environment variable ``TOGETHER_API_KEY``.\n",
"\n",
"Together API reference: https://docs.together.ai/reference/inference"
"Together API reference: https://docs.together.ai/reference"
]
},
{

5
docs/docs/integrations/llms/yuan2.ipynb
View File

@@ -45,7 +45,7 @@
"outputs": [],
"source": [
"# default infer_api for a local deployed Yuan2.0 inference server\n",
"infer_api = \"http://127.0.0.1:8000\"\n",
"infer_api = \"http://127.0.0.1:8000/yuan\"\n",
"\n",
"# direct access endpoint in a proxied environment\n",
"# import os\n",
@@ -56,7 +56,6 @@
" max_tokens=2048,\n",
" temp=1.0,\n",
" top_p=0.9,\n",
" top_k=40,\n",
" use_history=False,\n",
")\n",
"\n",
@@ -89,7 +88,7 @@
},
"outputs": [],
"source": [
"print(yuan_llm(question))"
"print(yuan_llm.invoke(question))"
]
}
],

2
docs/docs/integrations/memory/google_alloydb.ipynb
View File

@@ -288,7 +288,7 @@
"\n",
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
"\n",
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
"To do this we will use one of [Google's Vertex AI chat models](/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
]
},
{

2
docs/docs/integrations/memory/google_el_carro.ipynb
View File

@@ -293,7 +293,7 @@
"\n",
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
"\n",
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
"To do this we will use one of [Google's Vertex AI chat models](/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
]
},
{

2
docs/docs/integrations/memory/google_sql_mssql.ipynb
View File

@@ -393,7 +393,7 @@
"\n",
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
"\n",
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
"To do this we will use one of [Google's Vertex AI chat models](/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
]
},
{

2
docs/docs/integrations/memory/google_sql_mysql.ipynb
View File

@@ -394,7 +394,7 @@
"\n",
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
"\n",
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
"To do this we will use one of [Google's Vertex AI chat models](/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
]
},
{

2
docs/docs/integrations/memory/google_sql_pg.ipynb
View File

@@ -394,7 +394,7 @@
"\n",
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
"\n",
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
"To do this we will use one of [Google's Vertex AI chat models](/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
]
},
{

2
docs/docs/integrations/memory/streamlit_chat_message_history.ipynb
View File

@@ -61,7 +61,7 @@
"id": "b60dc735",
"metadata": {},
"source": [
"We can easily combine this message history class with [LCEL Runnables](https://python.langchain.com/docs/expression_language/how_to/message_history).\n",
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history).\n",
"\n",
"The history will be persisted across re-runs of the Streamlit app within a given user session. A given `StreamlitChatMessageHistory` will NOT be persisted or shared across user sessions."
]

8
docs/docs/integrations/platforms/google.mdx
View File

@@ -503,21 +503,21 @@ from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgresVectorStore
### Vertex AI Vector Search
> [Google Cloud Vertex AI Vector Search](https://cloud.google.com/vertex-ai/docs/matching-engine/overview) from Google Cloud,
> [Google Cloud Vertex AI Vector Search](https://cloud.google.com/vertex-ai/docs/vector-search/overview) from Google Cloud,
> formerly known as `Vertex AI Matching Engine`, provides the industry's leading high-scale
> low latency vector database. These vector databases are commonly
> referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service.
We need to install several python packages.
Install the python package:
```bash
pip install tensorflow langchain-google-vertexai tensorflow-hub tensorflow-text
pip install langchain-google-vertexai
```
See a [usage example](/docs/integrations/vectorstores/google_vertex_ai_vector_search).
```python
from langchain_community.vectorstores import MatchingEngine
from langchain_google_vertexai import VectorSearchVectorStore
```
### ScaNN

5
docs/docs/integrations/platforms/index.mdx
View File

@@ -12,19 +12,24 @@ LangChain integrates with many providers.
These providers have standalone `langchain-{provider}` packages for improved versioning, dependency management and testing.
- [AI21](/docs/integrations/providers/ai21)
- [Airbyte](/docs/integrations/providers/airbyte)
- [Anthropic](/docs/integrations/platforms/anthropic)
- [Astra DB](/docs/integrations/providers/astradb)
- [Elasticsearch](/docs/integrations/providers/elasticsearch)
- [Exa Search](/docs/integrations/providers/exa_search)
- [Fireworks](/docs/integrations/providers/fireworks)
- [Google](/docs/integrations/platforms/google)
- [Groq](/docs/integrations/providers/groq)
- [IBM](/docs/integrations/providers/ibm)
- [MistralAI](/docs/integrations/providers/mistralai)
- [MongoDB](/docs/integrations/providers/mongodb_atlas)
- [Nomic](/docs/integrations/providers/nomic)
- [Nvidia](/docs/integrations/providers/nvidia)
- [OpenAI](/docs/integrations/platforms/openai)
- [Pinecone](/docs/integrations/providers/pinecone)
- [Robocorp](/docs/integrations/providers/robocorp)
- [Together AI](/docs/integrations/providers/together)
- [Voyage AI](/docs/integrations/providers/voyageai)
## Featured Community Providers

9
docs/docs/integrations/platforms/microsoft.mdx
View File

@@ -3,6 +3,15 @@
All functionality related to `Microsoft Azure` and other `Microsoft` products.
## LLMs
### Azure ML
See a [usage example](/docs/integrations/llms/azure_ml).
```python
from langchain_community.llms.azureml_endpoint import AzureMLOnlineEndpoint
```
### Azure OpenAI
See a [usage example](/docs/integrations/llms/azure_openai).

30
docs/docs/integrations/providers/arcee.mdx Normal file
View File

@@ -0,0 +1,30 @@
# Arcee
>[Arcee](https://www.arcee.ai/about/about-us) enables the development and advancement
> of what we coin as SLMs—small, specialized, secure, and scalable language models.
> By offering a SLM Adaptation System and a seamless, secure integration,
> `Arcee` empowers enterprises to harness the full potential of
> domain-adapted language models, driving the transformative
> innovation in operations.
## Installation and Setup
Get your `Arcee API` key.
## LLMs
See a [usage example](/docs/integrations/llms/arcee).
```python
from langchain_community.llms import Arcee
```
## Retrievers
See a [usage example](/docs/integrations/retrievers/arcee).
```python
from langchain_community.retrievers import ArceeRetriever
```

17
docs/docs/integrations/providers/astradb.mdx
View File

@@ -10,12 +10,7 @@ See a [tutorial provided by DataStax](https://docs.datastax.com/en/astra/astra-d
Install the following Python package:
```bash
pip install "langchain-astradb>=0.0.1"
```
Some old integrations require the `astrapy` package:
```bash
pip install "astrapy>=0.7.1"
pip install "langchain-astradb>=0.1.0"
```
Get the [connection secrets](https://docs.datastax.com/en/astra/astra-db-vector/get-started/quickstart.html).
@@ -61,7 +56,7 @@ See the [usage example](/docs/integrations/memory/astradb_chat_message_history#e
```python
from langchain.globals import set_llm_cache
from langchain_community.cache import AstraDBCache
from langchain_astradb import AstraDBCache
set_llm_cache(AstraDBCache(
api_endpoint=ASTRA_DB_API_ENDPOINT,
@@ -76,7 +71,7 @@ Learn more in the [example notebook](/docs/integrations/llms/llm_caching#astra-d
```python
from langchain.globals import set_llm_cache
from langchain_community.cache import
from langchain_astradb import AstraDBSemanticCache
set_llm_cache(AstraDBSemanticCache(
embedding=my_embedding,
@@ -92,7 +87,7 @@ Learn more in the [example notebook](/docs/integrations/memory/astradb_chat_mess
## Document loader
```python
from langchain_community.document_loaders import AstraDBLoader
from langchain_astradb import AstraDBLoader
loader = AstraDBLoader(
collection_name="my_collection",
@@ -129,7 +124,7 @@ Learn more in the [example notebook](/docs/integrations/retrievers/self_query/as
## Store
```python
from langchain_community.storage import AstraDBStore
from langchain_astradb import AstraDBStore
store = AstraDBStore(
collection_name="my_kv_store",
@@ -143,7 +138,7 @@ Learn more in the [example notebook](/docs/integrations/stores/astradb#astradbst
## Byte Store
```python
from langchain_community.storage import AstraDBByteStore
from langchain_astradb import AstraDBByteStore
store = AstraDBByteStore(
collection_name="my_kv_store",

50
docs/docs/integrations/providers/baidu.mdx Normal file
View File

@@ -0,0 +1,50 @@
# Baidu
>[Baidu Cloud](https://cloud.baidu.com/) is a cloud service provided by `Baidu, Inc.`,
> headquartered in Beijing. It offers a cloud storage service, client software,
> file management, resource sharing, and Third Party Integration.
## Installation and Setup
Register and get the `Qianfan` `AK` and `SK` keys [here](https://cloud.baidu.com/product/wenxinworkshop).
## LLMs
### Baidu Qianfan
See a [usage example](/docs/integrations/llms/baidu_qianfan_endpoint).
```python
from langchain_community.llms import QianfanLLMEndpoint
```
## Chat models
### Qianfan Chat Endpoint
See a [usage example](/docs/integrations/chat/baidu_qianfan_endpoint).
```python
from langchain_community.chat_models import QianfanChatEndpoint
```
## Embedding models
### Baidu Qianfan
See a [usage example](/docs/integrations/text_embedding/baidu_qianfan_endpoint).
```python
from langchain_community.embeddings import QianfanEmbeddingsEndpoint
```
## Vector stores
### Baidu Cloud ElasticSearch VectorSearch
See a [usage example](/docs/integrations/vectorstores/baiducloud_vector_search).
```python
from langchain_community.vectorstores import BESVectorStore
```

30
docs/docs/integrations/providers/ctranslate2.mdx Normal file
View File

@@ -0,0 +1,30 @@
# CTranslate2
>[CTranslate2](https://opennmt.net/CTranslate2/quickstart.html) is a C++ and Python library
> for efficient inference with Transformer models.
>
>The project implements a custom runtime that applies many performance optimization
> techniques such as weights quantization, layers fusion, batch reordering, etc.,
> to accelerate and reduce the memory usage of Transformer models on CPU and GPU.
>
>A full list of features and supported models is included in the
> [project’s repository](https://opennmt.net/CTranslate2/guides/transformers.html).
> To start, please check out the official [quickstart guide](https://opennmt.net/CTranslate2/quickstart.html).
## Installation and Setup
Install the Python package:
```bash
pip install ctranslate2
```
## LLMs
See a [usage example](/docs/integrations/llms/ctranslate2).
```python
from langchain_community.llms import CTranslate2
```

3
docs/docs/integrations/providers/deepsparse.mdx
View File

@@ -8,9 +8,8 @@ It is broken into two parts: installation and setup, and then examples of DeepSp
- Install the Python package with `pip install deepsparse`
- Choose a [SparseZoo model](https://sparsezoo.neuralmagic.com/?useCase=text_generation) or export a support model to ONNX [using Optimum](https://github.com/neuralmagic/notebooks/blob/main/notebooks/opt-text-generation-deepsparse-quickstart/OPT_Text_Generation_DeepSparse_Quickstart.ipynb)
## Wrappers
### LLM
## LLMs
There exists a DeepSparse LLM wrapper, which you can access with:

3
docs/docs/integrations/providers/docugami.mdx
View File

@@ -9,6 +9,7 @@
```bash
pip install dgml-utils
pip install docugami-langchain
```
## Document Loader
@@ -16,5 +17,5 @@ pip install dgml-utils
See a [usage example](/docs/integrations/document_loaders/docugami).
```python
from langchain_community.document_loaders import DocugamiLoader
from docugami_langchain.document_loaders import DocugamiLoader
```

62
docs/docs/integrations/providers/edenai.mdx Normal file
View File

@@ -0,0 +1,62 @@
# Eden AI
>[Eden AI](https://docs.edenai.co/docs/getting-started-with-eden-ai) user interface (UI)
> is designed for handling the AI projects. With `Eden AI Portal`,
> you can perform no-code AI using the best engines for the market.
## Installation and Setup
Accessing the Eden AI API requires an API key, which you can get by
[creating an account](https://app.edenai.run/user/register) and
heading [here](https://app.edenai.run/admin/account/settings).
## LLMs
See a [usage example](/docs/integrations/llms/edenai).
```python
from langchain_community.llms import EdenAI
```
## Chat models
See a [usage example](/docs/integrations/chat/edenai).
```python
from langchain_community.chat_models.edenai import ChatEdenAI
```
## Embedding models
See a [usage example](/docs/integrations/text_embedding/edenai).
```python
from langchain_community.embeddings.edenai import EdenAiEmbeddings
```
## Tools
Eden AI provides a list of tools that grants your Agent the ability to do multiple tasks, such as:
* speech to text
* text to speech
* text explicit content detection
* image explicit content detection
* object detection
* OCR invoice parsing
* OCR ID parsing
See a [usage example](/docs/integrations/tools/edenai_tools).
```python
from langchain_community.tools.edenai import (
EdenAiExplicitImageTool,
EdenAiObjectDetectionTool,
EdenAiParsingIDTool,
EdenAiParsingInvoiceTool,
EdenAiSpeechToTextTool,
EdenAiTextModerationTool,
EdenAiTextToSpeechTool,
)
```

27
docs/docs/integrations/providers/elevenlabs.mdx Normal file
View File

@@ -0,0 +1,27 @@
# ElevenLabs
>[ElevenLabs](https://elevenlabs.io/about) is a voice AI research & deployment company
> with a mission to make content universally accessible in any language & voice.
>
>`ElevenLabs` creates the most realistic, versatile and contextually-aware
> AI audio, providing the ability to generate speech in hundreds of
> new and existing voices in 29 languages.
## Installation and Setup
First, you need to set up an ElevenLabs account. You can follow the
[instructions here](https://docs.elevenlabs.io/welcome/introduction).
Install the Python package:
```bash
pip install elevenlabs
```
## Tools
See a [usage example](/docs/integrations/tools/eleven_labs_tts).
```python
from langchain_community.tools import ElevenLabsText2SpeechTool
```

2
docs/docs/integrations/providers/ollama.mdx
View File

@@ -7,7 +7,7 @@
>It optimizes setup and configuration details, including GPU usage.
>For a complete list of supported models and model variants, see the [Ollama model library](https://ollama.ai/library).
See [this guide](https://python.langchain.com/docs/guides/local_llms#quickstart) for more details
See [this guide](/docs/guides/local_llms#quickstart) for more details
on how to use `Ollama` with LangChain.
## Installation and Setup

21
docs/docs/integrations/providers/pygmalionai.mdx Normal file
View File

@@ -0,0 +1,21 @@
# PygmalionAI
>[PygmalionAI](https://pygmalion.chat/) is a company supporting the
> open-source models by serving the inference endpoint
> for the [Aphrodite Engine](https://github.com/PygmalionAI/aphrodite-engine).
## Installation and Setup
```bash
pip install aphrodite-engine
```
## LLMs
See a [usage example](/docs/integrations/llms/aphrodite).
```python
from langchain_community.llms import Aphrodite
```

2
docs/docs/integrations/providers/together.ipynb
View File

@@ -12,7 +12,7 @@
"https://api.together.xyz/settings/api-keys. This can be passed in as init param\n",
"``together_api_key`` or set as environment variable ``TOGETHER_API_KEY``.\n",
"\n",
"Together API reference: https://docs.together.ai/reference/inference\n",
"Together API reference: https://docs.together.ai/reference\n",
"\n",
"You will also need to install the `langchain-together` integration package:"
]

4
docs/docs/integrations/providers/vectara/vectara_summary.ipynb
View File

@@ -22,7 +22,7 @@
"See the [Vectara API documentation](https://docs.vectara.com/docs/) for more information on how to use the API.\n",
"\n",
"This notebook shows how to use functionality related to the `Vectara`'s integration with langchain.\n",
"Specificaly we will demonstrate how to use chaining with [LangChain's Expression Language](https://python.langchain.com/docs/expression_language/) and using Vectara's integrated summarization capability."
"Specificaly we will demonstrate how to use chaining with [LangChain's Expression Language](/docs/expression_language/) and using Vectara's integrated summarization capability."
]
},
{
@@ -219,7 +219,7 @@
"id": "8f16bf8d",
"metadata": {},
"source": [
"Vectara's \"RAG as a service\" does a lot of the heavy lifting in creating question answering or chatbot chains. The integration with LangChain provides the option to use additional capabilities such as query pre-processing like `SelfQueryRetriever` or `MultiQueryRetriever`. Let's look at an example of using the [MultiQueryRetriever](https://python.langchain.com/docs/modules/data_connection/retrievers/MultiQueryRetriever).\n",
"Vectara's \"RAG as a service\" does a lot of the heavy lifting in creating question answering or chatbot chains. The integration with LangChain provides the option to use additional capabilities such as query pre-processing like `SelfQueryRetriever` or `MultiQueryRetriever`. Let's look at an example of using the [MultiQueryRetriever](/docs/modules/data_connection/retrievers/MultiQueryRetriever).\n",
"\n",
"Since MQR uses an LLM we have to set that up - here we choose `ChatOpenAI`:"
]

24
docs/docs/integrations/providers/voyageai.mdx Normal file
View File

@@ -0,0 +1,24 @@
# VoyageAI
All functionality related to VoyageAI
>[VoyageAI](https://www.voyageai.com/) Voyage AI builds embedding models, customized for your domain and company, for better retrieval quality.
> customized for your domain and company, for better retrieval quality.
## Installation and Setup
Install the integration package with
```bash
pip install langchain-voyageai
```
Get an VoyageAI api key and set it as an environment variable (`VOYAGE_API_KEY`)
## Text Embedding Model
See a [usage example](/docs/integrations/text_embedding/voyageai)
```python
from langchain_voyageai import VoyageAIEmbeddings
```

17
docs/docs/integrations/retrievers/activeloop.ipynb
View File

File diff suppressed because one or more lines are too long

15
docs/docs/integrations/retrievers/cohere.ipynb
View File

@@ -10,6 +10,19 @@
"This notebook covers how to get started with Cohere RAG retriever. This allows you to leverage the ability to search documents over various connectors or by supplying your own."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2c367be3",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
]
},
{
"cell_type": "code",
"execution_count": null,
@@ -218,7 +231,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
"version": "3.11.7"
}
},
"nbformat": 4,

96
docs/docs/integrations/retrievers/flashrank-reranker.ipynb
View File

@@ -28,17 +28,17 @@
},
"outputs": [],
"source": [
"% pip install --upgrade --quiet flashrank\n",
"% pip install --upgrade --quiet faiss\n",
"%pip install --upgrade --quiet flashrank\n",
"%pip install --upgrade --quiet faiss\n",
"\n",
"# OR (depending on Python version)\n",
"\n",
"% pip install --upgrade --quiet faiss_cpu"
"%pip install --upgrade --quiet faiss_cpu"
]
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 2,
"metadata": {
"collapsed": false,
"jupyter": {
@@ -53,7 +53,10 @@
"def pretty_print_docs(docs):\n",
" print(\n",
" f\"\\n{'-' * 100}\\n\".join(\n",
" [f\"Document {i+1}:\\n\\n\" + d.page_content for i, d in enumerate(docs)]\n",
" [\n",
" f\"Document {i+1}:\\n\\n{d.page_content}\\nMetadata: {d.metadata}\"\n",
" for i, d in enumerate(docs)\n",
" ]\n",
" )\n",
" )"
]
@@ -73,7 +76,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {
"collapsed": false,
"jupyter": {
@@ -90,7 +93,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 4,
"metadata": {
"collapsed": false,
"jupyter": {
@@ -247,14 +250,6 @@
"----------------------------------------------------------------------------------------------------\n",
"Document 15:\n",
"\n",
"My plan to fight inflation will lower your costs and lower the deficit. \n",
"\n",
"17 Nobel laureates in economics say my plan will ease long-term inflationary pressures. Top business leaders and most Americans support my plan. And here’s the plan: \n",
"\n",
"First – cut the cost of prescription drugs. Just look at insulin. One in ten Americans has diabetes. In Virginia, I met a 13-year-old boy named Joshua Davis.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 16:\n",
"\n",
"And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \n",
"\n",
"So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \n",
@@ -263,15 +258,15 @@
"\n",
"There is so much we can do. Increase funding for prevention, treatment, harm reduction, and recovery.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 17:\n",
"Document 16:\n",
"\n",
"So let’s not abandon our streets. Or choose between safety and equal justice. \n",
"My plan to fight inflation will lower your costs and lower the deficit. \n",
"\n",
"Let’s come together to protect our communities, restore trust, and hold law enforcement accountable. \n",
"17 Nobel laureates in economics say my plan will ease long-term inflationary pressures. Top business leaders and most Americans support my plan. And here’s the plan: \n",
"\n",
"That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers.\n",
"First – cut the cost of prescription drugs. Just look at insulin. One in ten Americans has diabetes. In Virginia, I met a 13-year-old boy named Joshua Davis.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 18:\n",
"Document 17:\n",
"\n",
"My plan will not only lower costs to give families a fair shot, it will lower the deficit. \n",
"\n",
@@ -281,6 +276,14 @@
"\n",
"We’re going after the criminals who stole billions in relief money meant for small businesses and millions of Americans.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 18:\n",
"\n",
"So let’s not abandon our streets. Or choose between safety and equal justice. \n",
"\n",
"Let’s come together to protect our communities, restore trust, and hold law enforcement accountable. \n",
"\n",
"That’s why the Justice Department required body cameras, banned chokeholds, and restricted no-knock warrants for its officers.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 19:\n",
"\n",
"I understand. \n",
@@ -316,6 +319,8 @@
").load()\n",
"text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",
"texts = text_splitter.split_documents(documents)\n",
"for idx, text in enumerate(texts):\n",
" text.metadata[\"id\"] = idx\n",
"\n",
"embedding = OpenAIEmbeddings(model=\"text-embedding-ada-002\")\n",
"retriever = FAISS.from_documents(texts, embedding).as_retriever(search_kwargs={\"k\": 20})\n",
@@ -340,16 +345,25 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0, 5, 3]\n"
]
}
],
"source": [
"from langchain.retrievers import ContextualCompressionRetriever, FlashrankRerank\n",
"from langchain.retrievers import ContextualCompressionRetriever\n",
"from langchain.retrievers.document_compressors import FlashrankRerank\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"llm = ChatOpenAI(temperature=0)\n",
@@ -379,7 +393,7 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": 6,
"metadata": {
"collapsed": false,
"jupyter": {
@@ -399,6 +413,16 @@
"----------------------------------------------------------------------------------------------------\n",
"Document 2:\n",
"\n",
"He met the Ukrainian people. \n",
"\n",
"From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \n",
"\n",
"Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. \n",
"\n",
"In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 3:\n",
"\n",
"And tonight, I’m announcing that the Justice Department will name a chief prosecutor for pandemic fraud. \n",
"\n",
"By the end of this year, the deficit will be down to less than half what it was before I took office. \n",
@@ -409,19 +433,7 @@
"\n",
"I’m a capitalist, but capitalism without competition isn’t capitalism. \n",
"\n",
"It’s exploitation—and it drives up prices.\n",
"----------------------------------------------------------------------------------------------------\n",
"Document 3:\n",
"\n",
"As Ohio Senator Sherrod Brown says, “It’s time to bury the label “Rust Belt.” \n",
"\n",
"It’s time. \n",
"\n",
"But with all the bright spots in our economy, record job growth and higher wages, too many families are struggling to keep up with the bills. \n",
"\n",
"Inflation is robbing them of the gains they might otherwise feel. \n",
"\n",
"I get it. That’s why my top priority is getting prices under control.\n"
"It’s exploitation—and it drives up prices.\n"
]
}
],
@@ -443,7 +455,7 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": 7,
"metadata": {
"collapsed": false,
"jupyter": {
@@ -459,7 +471,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 8,
"metadata": {
"collapsed": false,
"jupyter": {
@@ -471,10 +483,10 @@
"data": {
"text/plain": [
"{'query': 'What did the president say about Ketanji Brown Jackson',\n",
" 'result': \"The President said that Ketanji Brown Jackson is one of our nation's top legal minds and will continue Justice Breyer's legacy of excellence.\"}"
" 'result': \"The President mentioned that Ketanji Brown Jackson is one of the nation's top legal minds and will continue Justice Breyer's legacy of excellence.\"}"
]
},
"execution_count": 19,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -500,7 +512,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
"version": "3.12.2"
}
},
"nbformat": 4,

2
docs/docs/integrations/retrievers/fleet_context.ipynb
View File

@@ -7,7 +7,7 @@
"source": [
"# Fleet AI Libraries Context\n",
"\n",
"The Fleet AI team is on a mission to embed the world's most important data. They've started by embedding the top 1200 Python libraries to enable code generation with up-to-date knowledge. They've been kind enough to share their embeddings of the [LangChain docs](https://python.langchain.com/docs/get_started/introduction) and [API reference](https://api.python.langchain.com/en/latest/api_reference.html).\n",
"The Fleet AI team is on a mission to embed the world's most important data. They've started by embedding the top 1200 Python libraries to enable code generation with up-to-date knowledge. They've been kind enough to share their embeddings of the [LangChain docs](/docs/get_started/introduction) and [API reference](https://api.python.langchain.com/en/latest/api_reference.html).\n",
"\n",
"Let's take a look at how we can use these embeddings to power a docs retrieval system and ultimately a simple code generating chain!"
]

47
docs/docs/integrations/retrievers/google_vertex_ai_search.ipynb
View File

@@ -30,7 +30,7 @@
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet google-cloud-discoveryengine"
"%pip install --upgrade --quiet google-cloud-discoveryengine"
]
},
{
@@ -115,10 +115,12 @@
" - `global` (default)\n",
" - `us`\n",
" - `eu`\n",
"- `data_store_id` - The ID of the data store you want to use.\n",
" - Note: This was called `search_engine_id` in previous versions of the retriever.\n",
"\n",
"The `project_id` and `data_store_id` parameters can be provided explicitly in the retriever's constructor or through the environment variables - `PROJECT_ID` and `DATA_STORE_ID`.\n",
"One of:\n",
"- `search_engine_id` - The ID of the search app you want to use. (Required for Blended Search)\n",
"- `data_store_id` - The ID of the data store you want to use.\n",
"\n",
"The `project_id`, `search_engine_id` and `data_store_id` parameters can be provided explicitly in the retriever's constructor or through the environment variables - `PROJECT_ID`, `SEARCH_ENGINE_ID` and `DATA_STORE_ID`.\n",
"\n",
"You can also configure a number of optional parameters, including:\n",
"\n",
@@ -137,17 +139,17 @@
"- `engine_data_type` - Defines the Vertex AI Search data type\n",
" - `0` - Unstructured data\n",
" - `1` - Structured data\n",
" - `2` - Website data with [Advanced Website Indexing](https://cloud.google.com/generative-ai-app-builder/docs/about-advanced-features#advanced-website-indexing)\n",
" - `2` - Website data\n",
" - `3` - [Blended search](https://cloud.google.com/generative-ai-app-builder/docs/create-data-store-es#multi-data-stores)\n",
"\n",
"### Migration guide for `GoogleCloudEnterpriseSearchRetriever`\n",
"\n",
"In previous versions, this retriever was called `GoogleCloudEnterpriseSearchRetriever`. Some backwards-incompatible changes had to be made to the retriever after the General Availability launch due to changes in the product behavior.\n",
"In previous versions, this retriever was called `GoogleCloudEnterpriseSearchRetriever`.\n",
"\n",
"To update to the new retriever, make the following changes:\n",
"\n",
"- Change the import from: `from langchain.retrievers import GoogleCloudEnterpriseSearchRetriever` -> `from langchain.retrievers import GoogleVertexAISearchRetriever`.\n",
"- Change all class references from `GoogleCloudEnterpriseSearchRetriever` -> `GoogleVertexAISearchRetriever`.\n",
"- Upon class initialization, change the `search_engine_id` parameter name to `data_store_id`.\n"
"- Change all class references from `GoogleCloudEnterpriseSearchRetriever` -> `GoogleVertexAISearchRetriever`.\n"
]
},
{
@@ -170,6 +172,7 @@
"\n",
"PROJECT_ID = \"<YOUR PROJECT ID>\" # Set to your Project ID\n",
"LOCATION_ID = \"<YOUR LOCATION>\" # Set to your data store location\n",
"SEARCH_ENGINE_ID = \"<YOUR SEARCH APP ID>\" # Set to your search app ID\n",
"DATA_STORE_ID = \"<YOUR DATA STORE ID>\" # Set to your data store ID"
]
},
@@ -281,6 +284,32 @@
" print(doc)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure and use the retriever for **blended** data\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"retriever = GoogleVertexAISearchRetriever(\n",
" project_id=PROJECT_ID,\n",
" location_id=LOCATION_ID,\n",
" search_engine_id=SEARCH_ENGINE_ID,\n",
" max_documents=3,\n",
" engine_data_type=3,\n",
")\n",
"\n",
"result = retriever.get_relevant_documents(query)\n",
"for doc in result:\n",
" print(doc)"
]
},
{
"cell_type": "markdown",
"metadata": {},
@@ -322,7 +351,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
"version": "3.11.0"
}
},
"nbformat": 4,

2
docs/docs/integrations/retrievers/outline.ipynb
View File

@@ -100,7 +100,7 @@
"text/plain": [
"[Document(page_content='This walkthrough demonstrates how to use an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.\\n\\nIf we compare it to the standard ReAct agent, the main difference is the prompt. We want it to be much more conversational.\\n\\nfrom langchain.agents import AgentType, Tool, initialize_agent\\n\\nfrom langchain_openai import OpenAI\\n\\nfrom langchain.memory import ConversationBufferMemory\\n\\nfrom langchain_community.utilities import SerpAPIWrapper\\n\\nsearch = SerpAPIWrapper() tools = \\\\[ Tool( name=\"Current Search\", func=search.run, description=\"useful for when you need to answer questions about current events or the current state of the world\", ), \\\\]\\n\\n\\\\\\nllm = OpenAI(temperature=0)\\n\\nUsing LCEL\\n\\nWe will first show how to create this agent using LCEL\\n\\nfrom langchain import hub\\n\\nfrom langchain.agents.format_scratchpad import format_log_to_str\\n\\nfrom langchain.agents.output_parsers import ReActSingleInputOutputParser\\n\\nfrom langchain.tools.render import render_text_description\\n\\nprompt = hub.pull(\"hwchase17/react-chat\")\\n\\nprompt = prompt.partial( tools=render_text_description(tools), tool_names=\", \".join(\\\\[[t.name](http://t.name) for t in tools\\\\]), )\\n\\nllm_with_stop = llm.bind(stop=\\\\[\"\\\\nObservation\"\\\\])\\n\\nagent = ( { \"input\": lambda x: x\\\\[\"input\"\\\\], \"agent_scratchpad\": lambda x: format_log_to_str(x\\\\[\"intermediate_steps\"\\\\]), \"chat_history\": lambda x: x\\\\[\"chat_history\"\\\\], } | prompt | llm_with_stop | ReActSingleInputOutputParser() )\\n\\nfrom langchain.agents import AgentExecutor\\n\\nmemory = ConversationBufferMemory(memory_key=\"chat_history\") agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=memory)\\n\\nagent_executor.invoke({\"input\": \"hi, i am bob\"})\\\\[\"output\"\\\\]\\n\\n```\\n> Entering new AgentExecutor chain...\\n\\nThought: Do I need to use a tool? No\\nFinal Answer: Hi Bob, nice to meet you! How can I help you today?\\n\\n> Finished chain.\\n```\\n\\n\\\\\\n\\'Hi Bob, nice to meet you! How can I help you today?\\'\\n\\nagent_executor.invoke({\"input\": \"whats my name?\"})\\\\[\"output\"\\\\]\\n\\n```\\n> Entering new AgentExecutor chain...\\n\\nThought: Do I need to use a tool? No\\nFinal Answer: Your name is Bob.\\n\\n> Finished chain.\\n```\\n\\n\\\\\\n\\'Your name is Bob.\\'\\n\\nagent_executor.invoke({\"input\": \"what are some movies showing 9/21/2023?\"})\\\\[\"output\"\\\\]\\n\\n```\\n> Entering new AgentExecutor chain...\\n\\nThought: Do I need to use a tool? Yes\\nAction: Current Search\\nAction Input: Movies showing 9/21/2023[\\'September 2023 Movies: The Creator • Dumb Money • Expend4bles • The Kill Room • The Inventor • The Equalizer 3 • PAW Patrol: The Mighty Movie, ...\\'] Do I need to use a tool? No\\nFinal Answer: According to current search, some movies showing on 9/21/2023 are The Creator, Dumb Money, Expend4bles, The Kill Room, The Inventor, The Equalizer 3, and PAW Patrol: The Mighty Movie.\\n\\n> Finished chain.\\n```\\n\\n\\\\\\n\\'According to current search, some movies showing on 9/21/2023 are The Creator, Dumb Money, Expend4bles, The Kill Room, The Inventor, The Equalizer 3, and PAW Patrol: The Mighty Movie.\\'\\n\\n\\\\\\nUse the off-the-shelf agent\\n\\nWe can also create this agent using the off-the-shelf agent class\\n\\nagent_executor = initialize_agent( tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory, )\\n\\nUse a chat model\\n\\nWe can also use a chat model here. The main difference here is in the prompts used.\\n\\nfrom langchain import hub\\n\\nfrom langchain_openai import ChatOpenAI\\n\\nprompt = hub.pull(\"hwchase17/react-chat-json\") chat_model = ChatOpenAI(temperature=0, model=\"gpt-4\")\\n\\nprompt = prompt.partial( tools=render_text_description(tools), tool_names=\", \".join(\\\\[[t.name](http://t.name) for t in tools\\\\]), )\\n\\nchat_model_with_stop = chat_model.bind(stop=\\\\[\"\\\\nObservation\"\\\\])\\n\\nfrom langchain.agents.format_scratchpad import format_log_to_messages\\n\\nfrom langchain.agents.output_parsers import JSONAgentOutputParser\\n\\n# We need some extra steering, or the c', metadata={'title': 'Conversational', 'source': 'https://d01.getoutline.com/doc/conversational-B5dBkUgQ4b'}),\n",
" Document(page_content='Quickstart\\n\\nIn this quickstart we\\'ll show you how to:\\n\\nGet setup with LangChain, LangSmith and LangServe\\n\\nUse the most basic and common components of LangChain: prompt templates, models, and output parsers\\n\\nUse LangChain Expression Language, the protocol that LangChain is built on and which facilitates component chaining\\n\\nBuild a simple application with LangChain\\n\\nTrace your application with LangSmith\\n\\nServe your application with LangServe\\n\\nThat\\'s a fair amount to cover! Let\\'s dive in.\\n\\nSetup\\n\\nInstallation\\n\\nTo install LangChain run:\\n\\nPip\\n\\nConda\\n\\npip install langchain\\n\\nFor more details, see our Installation guide.\\n\\nEnvironment\\n\\nUsing LangChain will usually require integrations with one or more model providers, data stores, APIs, etc. For this example, we\\'ll use OpenAI\\'s model APIs.\\n\\nFirst we\\'ll need to install their Python package:\\n\\npip install openai\\n\\nAccessing the API requires an API key, which you can get by creating an account and heading here. Once we have a key we\\'ll want to set it as an environment variable by running:\\n\\nexport OPENAI_API_KEY=\"...\"\\n\\nIf you\\'d prefer not to set an environment variable you can pass the key in directly via the openai_api_key named parameter when initiating the OpenAI LLM class:\\n\\nfrom langchain_openai import ChatOpenAI\\n\\nllm = ChatOpenAI(openai_api_key=\"...\")\\n\\nLangSmith\\n\\nMany of the applications you build with LangChain will contain multiple steps with multiple invocations of LLM calls. As these applications get more and more complex, it becomes crucial to be able to inspect what exactly is going on inside your chain or agent. The best way to do this is with LangSmith.\\n\\nNote that LangSmith is not needed, but it is helpful. If you do want to use LangSmith, after you sign up at the link above, make sure to set your environment variables to start logging traces:\\n\\nexport LANGCHAIN_TRACING_V2=\"true\" export LANGCHAIN_API_KEY=...\\n\\nLangServe\\n\\nLangServe helps developers deploy LangChain chains as a REST API. You do not need to use LangServe to use LangChain, but in this guide we\\'ll show how you can deploy your app with LangServe.\\n\\nInstall with:\\n\\npip install \"langserve\\\\[all\\\\]\"\\n\\nBuilding with LangChain\\n\\nLangChain provides many modules that can be used to build language model applications. Modules can be used as standalones in simple applications and they can be composed for more complex use cases. Composition is powered by LangChain Expression Language (LCEL), which defines a unified Runnable interface that many modules implement, making it possible to seamlessly chain components.\\n\\nThe simplest and most common chain contains three things:\\n\\nLLM/Chat Model: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them. Prompt Template: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial. Output Parser: These translate the raw response from the language model to a more workable format, making it easy to use the output downstream. In this guide we\\'ll cover those three components individually, and then go over how to combine them. Understanding these concepts will set you up well for being able to use and customize LangChain applications. Most LangChain applications allow you to configure the model and/or the prompt, so knowing how to take advantage of this will be a big enabler.\\n\\nLLM / Chat Model\\n\\nThere are two types of language models:\\n\\nLLM: underlying model takes a string as input and returns a string\\n\\nChatModel: underlying model takes a list of messages as input and returns a message\\n\\nStrings are simple, but what exactly are messages? The base message interface is defined by BaseMessage, which has two required attributes:\\n\\ncontent: The content of the message. Usually a string. role: The entity from which the BaseMessage is coming. LangChain provides several ob', metadata={'title': 'Quick Start', 'source': 'https://d01.getoutline.com/doc/quick-start-jGuGGGOTuL'}),\n",
" Document(page_content='This walkthrough showcases using an agent to implement the [ReAct](https://react-lm.github.io/) logic.\\n\\n```javascript\\nfrom langchain.agents import AgentType, initialize_agent, load_tools\\nfrom langchain_openai import OpenAI\\n```\\n\\nFirst, let\\'s load the language model we\\'re going to use to control the agent.\\n\\n```javascript\\nllm = OpenAI(temperature=0)\\n```\\n\\nNext, let\\'s load some tools to use. Note that the llm-math tool uses an LLM, so we need to pass that in.\\n\\n```javascript\\ntools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\\n```\\n\\n## Using LCEL[\\u200b](https://python.langchain.com/docs/modules/agents/agent_types/react#using-lcel \"Direct link to Using LCEL\")\\n\\nWe will first show how to create the agent using LCEL\\n\\n```javascript\\nfrom langchain import hub\\nfrom langchain.agents.format_scratchpad import format_log_to_str\\nfrom langchain.agents.output_parsers import ReActSingleInputOutputParser\\nfrom langchain.tools.render import render_text_description\\n```\\n\\n```javascript\\nprompt = hub.pull(\"hwchase17/react\")\\nprompt = prompt.partial(\\n tools=render_text_description(tools),\\n tool_names=\", \".join([t.name for t in tools]),\\n)\\n```\\n\\n```javascript\\nllm_with_stop = llm.bind(stop=[\"\\\\nObservation\"])\\n```\\n\\n```javascript\\nagent = (\\n {\\n \"input\": lambda x: x[\"input\"],\\n \"agent_scratchpad\": lambda x: format_log_to_str(x[\"intermediate_steps\"]),\\n }\\n | prompt\\n | llm_with_stop\\n | ReActSingleInputOutputParser()\\n)\\n```\\n\\n```javascript\\nfrom langchain.agents import AgentExecutor\\n```\\n\\n```javascript\\nagent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\\n```\\n\\n```javascript\\nagent_executor.invoke(\\n {\\n \"input\": \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\"\\n }\\n)\\n```\\n\\n```javascript\\n \\n \\n > Entering new AgentExecutor chain...\\n I need to find out who Leo DiCaprio\\'s girlfriend is and then calculate her age raised to the 0.43 power.\\n Action: Search\\n Action Input: \"Leo DiCaprio girlfriend\"model Vittoria Ceretti I need to find out Vittoria Ceretti\\'s age\\n Action: Search\\n Action Input: \"Vittoria Ceretti age\"25 years I need to calculate 25 raised to the 0.43 power\\n Action: Calculator\\n Action Input: 25^0.43Answer: 3.991298452658078 I now know the final answer\\n Final Answer: Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\\n \\n > Finished chain.\\n\\n\\n\\n\\n\\n {\\'input\\': \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\",\\n \\'output\\': \"Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\"}\\n```\\n\\n## Using ZeroShotReactAgent[\\u200b](https://python.langchain.com/docs/modules/agents/agent_types/react#using-zeroshotreactagent \"Direct link to Using ZeroShotReactAgent\")\\n\\nWe will now show how to use the agent with an off-the-shelf agent implementation\\n\\n```javascript\\nagent_executor = initialize_agent(\\n tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\\n)\\n```\\n\\n```javascript\\nagent_executor.invoke(\\n {\\n \"input\": \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\"\\n }\\n)\\n```\\n\\n```javascript\\n \\n \\n > Entering new AgentExecutor chain...\\n I need to find out who Leo DiCaprio\\'s girlfriend is and then calculate her age raised to the 0.43 power.\\n Action: Search\\n Action Input: \"Leo DiCaprio girlfriend\"\\n Observation: model Vittoria Ceretti\\n Thought: I need to find out Vittoria Ceretti\\'s age\\n Action: Search\\n Action Input: \"Vittoria Ceretti age\"\\n Observation: 25 years\\n Thought: I need to calculate 25 raised to the 0.43 power\\n Action: Calculator\\n Action Input: 25^0.43\\n Observation: Answer: 3.991298452658078\\n Thought: I now know the final answer\\n Final Answer: Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\\n \\n > Finished chain.\\n\\n\\n\\n\\n\\n {\\'input\\': \"Who is L', metadata={'title': 'ReAct', 'source': 'https://d01.getoutline.com/doc/react-d6rxRS1MHk'})]"
" Document(page_content='This walkthrough showcases using an agent to implement the [ReAct](https://react-lm.github.io/) logic.\\n\\n```javascript\\nfrom langchain.agents import AgentType, initialize_agent, load_tools\\nfrom langchain_openai import OpenAI\\n```\\n\\nFirst, let\\'s load the language model we\\'re going to use to control the agent.\\n\\n```javascript\\nllm = OpenAI(temperature=0)\\n```\\n\\nNext, let\\'s load some tools to use. Note that the llm-math tool uses an LLM, so we need to pass that in.\\n\\n```javascript\\ntools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\\n```\\n\\n## Using LCEL[\\u200b](/docs/modules/agents/agent_types/react#using-lcel \"Direct link to Using LCEL\")\\n\\nWe will first show how to create the agent using LCEL\\n\\n```javascript\\nfrom langchain import hub\\nfrom langchain.agents.format_scratchpad import format_log_to_str\\nfrom langchain.agents.output_parsers import ReActSingleInputOutputParser\\nfrom langchain.tools.render import render_text_description\\n```\\n\\n```javascript\\nprompt = hub.pull(\"hwchase17/react\")\\nprompt = prompt.partial(\\n tools=render_text_description(tools),\\n tool_names=\", \".join([t.name for t in tools]),\\n)\\n```\\n\\n```javascript\\nllm_with_stop = llm.bind(stop=[\"\\\\nObservation\"])\\n```\\n\\n```javascript\\nagent = (\\n {\\n \"input\": lambda x: x[\"input\"],\\n \"agent_scratchpad\": lambda x: format_log_to_str(x[\"intermediate_steps\"]),\\n }\\n | prompt\\n | llm_with_stop\\n | ReActSingleInputOutputParser()\\n)\\n```\\n\\n```javascript\\nfrom langchain.agents import AgentExecutor\\n```\\n\\n```javascript\\nagent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\\n```\\n\\n```javascript\\nagent_executor.invoke(\\n {\\n \"input\": \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\"\\n }\\n)\\n```\\n\\n```javascript\\n \\n \\n > Entering new AgentExecutor chain...\\n I need to find out who Leo DiCaprio\\'s girlfriend is and then calculate her age raised to the 0.43 power.\\n Action: Search\\n Action Input: \"Leo DiCaprio girlfriend\"model Vittoria Ceretti I need to find out Vittoria Ceretti\\'s age\\n Action: Search\\n Action Input: \"Vittoria Ceretti age\"25 years I need to calculate 25 raised to the 0.43 power\\n Action: Calculator\\n Action Input: 25^0.43Answer: 3.991298452658078 I now know the final answer\\n Final Answer: Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\\n \\n > Finished chain.\\n\\n\\n\\n\\n\\n {\\'input\\': \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\",\\n \\'output\\': \"Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\"}\\n```\\n\\n## Using ZeroShotReactAgent[\\u200b](/docs/modules/agents/agent_types/react#using-zeroshotreactagent \"Direct link to Using ZeroShotReactAgent\")\\n\\nWe will now show how to use the agent with an off-the-shelf agent implementation\\n\\n```javascript\\nagent_executor = initialize_agent(\\n tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\\n)\\n```\\n\\n```javascript\\nagent_executor.invoke(\\n {\\n \"input\": \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\"\\n }\\n)\\n```\\n\\n```javascript\\n \\n \\n > Entering new AgentExecutor chain...\\n I need to find out who Leo DiCaprio\\'s girlfriend is and then calculate her age raised to the 0.43 power.\\n Action: Search\\n Action Input: \"Leo DiCaprio girlfriend\"\\n Observation: model Vittoria Ceretti\\n Thought: I need to find out Vittoria Ceretti\\'s age\\n Action: Search\\n Action Input: \"Vittoria Ceretti age\"\\n Observation: 25 years\\n Thought: I need to calculate 25 raised to the 0.43 power\\n Action: Calculator\\n Action Input: 25^0.43\\n Observation: Answer: 3.991298452658078\\n Thought: I now know the final answer\\n Final Answer: Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\\n \\n > Finished chain.\\n\\n\\n\\n\\n\\n {\\'input\\': \"Who is L', metadata={'title': 'ReAct', 'source': 'https://d01.getoutline.com/doc/react-d6rxRS1MHk'})]"
]
},
"execution_count": 4,

26
docs/docs/integrations/retrievers/self_query/dingo.ipynb
View File

File diff suppressed because one or more lines are too long

17
docs/docs/integrations/text_embedding/cohere.ipynb
View File

File diff suppressed because one or more lines are too long

81
libs/partners/mistralai/docs/embeddings.ipynb → docs/docs/integrations/text_embedding/fireworks.ipynb
View File

@@ -5,19 +5,19 @@
"id": "b14a24db",
"metadata": {},
"source": [
"# MistralAIEmbeddings\n",
"# FireworksEmbeddings\n",
"\n",
"This notebook explains how to use MistralAIEmbeddings, which is included in the langchain_mistralai package, to embed texts in langchain."
"This notebook explains how to use Fireworks Embeddings, which is included in the langchain_fireworks package, to embed texts in langchain. We use the default nomic-ai v1.5 model in this example."
]
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "0ab948fc",
"metadata": {},
"outputs": [],
"source": [
"# pip install -U langchain-mistralai"
"%pip install -qU langchain-fireworks"
]
},
{
@@ -25,27 +25,31 @@
"id": "67c637ca",
"metadata": {},
"source": [
"## import the library"
"## Setup"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "5709b030",
"metadata": {},
"outputs": [],
"source": [
"from langchain_fireworks import FireworksEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5709b030",
"id": "3d81e58c",
"metadata": {},
"outputs": [],
"source": [
"from langchain_mistralai import MistralAIEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "1756b1ba",
"metadata": {},
"outputs": [],
"source": [
"embedding = MistralAIEmbeddings(mistral_api_key='your-api-key')"
"import getpass\n",
"import os\n",
"\n",
"if \"FIREWORKS_API_KEY\" not in os.environ:\n",
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")"
]
},
{
@@ -54,36 +58,47 @@
"metadata": {},
"source": [
"# Using the Embedding Model\n",
"With `MistralAIEmbeddings`, you can directly use the default model 'mistral-embed', or set a different one if available."
"With `FireworksEmbeddings`, you can directly use the default model 'nomic-ai/nomic-embed-text-v1.5', or set a different one if available."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "584b9af5",
"metadata": {},
"outputs": [],
"source": [
"embedding = FireworksEmbeddings(mode=\"nomic-ai/nomic-embed-text-v1.5\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "584b9af5",
"metadata": {},
"outputs": [],
"source": [
"embedding.model = 'mistral-embed' # or your preferred model if available"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "be18b873",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0.01367950439453125, 0.0103607177734375, -0.157958984375, -0.003070831298828125, 0.05926513671875]\n",
"[0.0369873046875, 0.00545501708984375, -0.179931640625, -0.018707275390625, 0.0552978515625]\n"
]
}
],
"source": [
"res_query = embedding.embed_query(\"The test information\")\n",
"res_document = embedding.embed_documents([\"test1\", \"another test\"])"
"res_document = embedding.embed_documents([\"test1\", \"another test\"])\n",
"print(res_query[:5])\n",
"print(res_document[1][:5])"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "poetry-venv-2",
"language": "python",
"name": "python3"
"name": "poetry-venv-2"
},
"language_info": {
"codemirror_mode": {
@@ -95,7 +110,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.9.1"
}
},
"nbformat": 4,

84
docs/docs/integrations/text_embedding/sparkllm.ipynb
View File

@@ -25,14 +25,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2024-03-15T09:36:13.753824100Z",
"start_time": "2024-03-15T09:36:13.225834400Z"
}
},
"outputs": [],
"source": [
"from langchain_community.embeddings import SparkLLMTextEmbeddings\n",
"\n",
"embeddings = SparkLLMTextEmbeddings(\n",
" spark_app_id=\"sk-*\", spark_api_key=\"\", spark_api_secret=\"\"\n",
" spark_app_id=\"<spark_app_id>\",\n",
" spark_api_key=\"<spark_api_key>\",\n",
" spark_api_secret=\"<spark_api_secret>\",\n",
")"
]
},
@@ -45,44 +52,67 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2024-03-15T09:36:25.436201400Z",
"start_time": "2024-03-15T09:36:25.313456600Z"
}
},
"outputs": [
{
"data": {
"text/plain": "[-0.043609619140625,\n 0.2017822265625,\n 0.0270843505859375,\n -0.250244140625,\n -0.024993896484375,\n -0.0382080078125,\n 0.06207275390625,\n -0.0146331787109375]"
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"text_q = \"Introducing iFlytek\"\n",
"\n",
"os.environ[\"SPARK_APP_ID\"] = \"YOUR_APP_ID\"\n",
"os.environ[\"SPARK_API_KEY\"] = \"YOUR_API_KEY\"\n",
"os.environ[\"SPARK_API_SECRET\"] = \"YOUR_API_SECRET\""
"text_1 = \"Science and Technology Innovation Company Limited, commonly known as iFlytek, is a leading Chinese technology company specializing in speech recognition, natural language processing, and artificial intelligence. With a rich history and remarkable achievements, iFlytek has emerged as a frontrunner in the field of intelligent speech and language technologies.iFlytek has made significant contributions to the advancement of human-computer interaction through its cutting-edge innovations. Their advanced speech recognition technology has not only improved the accuracy and efficiency of voice input systems but has also enabled seamless integration of voice commands into various applications and devices.The company's commitment to research and development has been instrumental in its success. iFlytek invests heavily in fostering talent and collaboration with academic institutions, resulting in groundbreaking advancements in speech synthesis and machine translation. Their dedication to innovation has not only transformed the way we communicate but has also enhanced accessibility for individuals with disabilities.\"\n",
"\n",
"text_2 = \"Moreover, iFlytek's impact extends beyond domestic boundaries, as they actively promote international cooperation and collaboration in the field of artificial intelligence. They have consistently participated in global competitions and contributed to the development of international standards.In recognition of their achievements, iFlytek has received numerous accolades and awards both domestically and internationally. Their contributions have revolutionized the way we interact with technology and have paved the way for a future where voice-based interfaces play a vital role.Overall, iFlytek is a trailblazer in the field of intelligent speech and language technologies, and their commitment to innovation and excellence deserves commendation.\"\n",
"\n",
"query_result = embeddings.embed_query(text_q)\n",
"query_result[:8]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text_1 = \"iFLYTEK is a well-known intelligent speech and artificial intelligence publicly listed company in the Asia-Pacific Region. Since its establishment, the company is devoted to cornerstone technological research in speech and languages, natural language understanding, machine learning, machine reasoning, adaptive learning, and has maintained the world-leading position in those domains. The company actively promotes the development of A.I. products and their sector-based applications, with visions of enabling machines to listen and speak, understand and think, creating a better world with artificial intelligence.\"\n",
"text_2 = \"iFLYTEK Open Platform was launched in 2010 by iFLYTEK as China’s first Artificial Intelligence open platform for Mobile Internet and intelligent hardware developers.\"\n",
"\n",
"query_result = embeddings.embed_query(text_2)\n",
"query_result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"execution_count": 5,
"metadata": {
"ExecuteTime": {
"end_time": "2024-03-15T09:36:54.657224Z",
"start_time": "2024-03-15T09:36:54.404690400Z"
}
},
"outputs": [
{
"data": {
"text/plain": "[-0.161865234375,\n 0.58984375,\n 0.998046875,\n 0.365966796875,\n 0.72900390625,\n 0.6015625,\n -0.8408203125,\n -0.2666015625]"
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"doc_result = embeddings.embed_documents([text_1, text_2])\n",
"doc_result"
"doc_result[0][:8]"
]
}
],
"metadata": {
"language_info": {
"name": "python"
},
"kernelspec": {
"name": "python3",
"language": "python",
"display_name": "Python 3 (ipykernel)"
}
},
"nbformat": 4,

6
docs/docs/integrations/text_embedding/voyageai.ipynb
View File

@@ -9,7 +9,7 @@
"\n",
">[Voyage AI](https://www.voyageai.com/) provides cutting-edge embedding/vectorizations models.\n",
"\n",
"Let's load the Voyage Embedding class."
"Let's load the Voyage Embedding class. (Install the LangChain partner package with `pip install langchain-voyageai`)"
]
},
{
@@ -19,7 +19,7 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.embeddings import VoyageEmbeddings"
"from langchain_voyageai import VoyageAIEmbeddings"
]
},
{
@@ -37,7 +37,7 @@
"metadata": {},
"outputs": [],
"source": [
"embeddings = VoyageEmbeddings(\n",
"embeddings = VoyageAIEmbeddings(\n",
" voyage_api_key=\"[ Your Voyage API key ]\", model=\"voyage-2\"\n",
")"
]

12
docs/docs/integrations/toolkits/pandas.ipynb
View File

@@ -34,7 +34,9 @@
"import pandas as pd\n",
"from langchain_openai import OpenAI\n",
"\n",
"df = pd.read_csv(\"titanic.csv\")"
"df = pd.read_csv(\n",
" \"https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/data/titanic.csv\"\n",
")"
]
},
{
@@ -116,7 +118,7 @@
}
],
"source": [
"agent.run(\"how many rows are there?\")"
"agent.invoke(\"how many rows are there?\")"
]
},
{
@@ -154,7 +156,7 @@
}
],
"source": [
"agent.run(\"how many people have more than 3 siblings\")"
"agent.invoke(\"how many people have more than 3 siblings\")"
]
},
{
@@ -204,7 +206,7 @@
}
],
"source": [
"agent.run(\"whats the square root of the average age?\")"
"agent.invoke(\"whats the square root of the average age?\")"
]
},
{
@@ -264,7 +266,7 @@
],
"source": [
"agent = create_pandas_dataframe_agent(OpenAI(temperature=0), [df, df1], verbose=True)\n",
"agent.run(\"how many rows in the age column are different?\")"
"agent.invoke(\"how many rows in the age column are different?\")"
]
},
{

Some files were not shown because too many files have changed in this diff Show More