If `distance_func` and `collection_name` are in `kwargs` they are sent
to the `QdrantClient` which results in an error being raised.
Co-authored-by: Francisco Ingham <>
`SentenceTransformer` returns a NumPy array, not a `List[List[float]]`
or `List[float]` as specified in the interface of `Embeddings`. That PR
makes it consistent with the interface.
I'm providing a hotfix for Qdrant integration. Calculating a single
embedding to obtain the vector size was great idea. However, that change
introduced a bug trying to put only that single embedding into the
database. It's fixed. Right now all the embeddings will be pushed to
Qdrant.
Now that OpenAI has deprecated all embeddings models except
text-embedding-ada-002, we should stop specifying a legacy embedding
model in the example. This will also avoid confusion from people (like
me) trying to specify model="text-embedding-ada-002" and having that
erroneously expanded to text-search-text-embedding-ada-002-query-001
Since the tokenizer and model are constructed manually, model_kwargs
needs to
be passed to their constructors. Additionally, the pipeline has a
specific
named parameter to pass these with, which can provide forward
compatibility if
they are used for something other than tokenizer or model construction.
- This uses the faiss built-in `write_index` and `load_index` to save
and load faiss indexes locally
- Also fixes#674
- The save/load functions also use the faiss library, so I refactored
the dependency into a function
Adding quotation marks around {text} avoids generating empty or
completely random responses from OpenAI davinci-003. Empty or completely
unrelated intermediate responses in summarization messes up the final
result or makes it very inaccurate.
The error from OpenAI would be: "The model predicted a completion that
begins with a stop sequence, resulting in no output. Consider adjusting
your prompt or stop sequences."
This fix corrects the prompting for summarization chain. This works on
API too, the images are for demonstrative purposes.
This approach can be applied to other similar prompts too.
Examples:
1) Without quotation marks
![Screenshot from 2023-01-20
07-18-19](https://user-images.githubusercontent.com/22897470/213624365-9dfc18f9-5f3f-45d2-abe1-56de67397e22.png)
2) With quotation marks
![Screenshot from 2023-01-20
07-18-35](https://user-images.githubusercontent.com/22897470/213624478-c958e742-a4a7-46fe-a163-eca6326d9dae.png)
Allow optionally specifying a list of ids for pinecone rather than
having them randomly generated.
This also permits editing the embedding/metadata of existing pinecone
entries, by id.
Allows for passing additional vectorstore params like namespace, etc. to
VectorDBQAWithSourcesChain
Example:
`chain = VectorDBQAWithSourcesChain.from_llm(OpenAI(temperature=0),
vectorstore=store, search_kwargs={"namespace": namespace})`
Running the Cohere embeddings example from the docs:
```python
from langchain.embeddings import CohereEmbeddings
embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key)
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_result = embeddings.embed_documents([text])
```
I get the error:
```bash
CohereError(message=res['message'], http_status=response.status_code, headers=response.headers)
cohere.error.CohereError: embed is not an available endpoint on this model
```
This is because the `model` string is set to `medium` which is not
currently available.
From the Cohere docs:
> Currently available models are small and large (default)
I originally had only modified the `from_llm` to include the prompt but
I realized that if the prompt keys used on the custom prompt didn't
match the default prompt, it wouldn't work because of how `apply` works.
So I made some changes to the evaluate method to check if the prompt is
the default and if not, it will check if the input keys are the same as
the prompt key and update the inputs appropriately.
Let me know if there is a better way to do this.
Also added the custom prompt to the QA eval notebook.
add a chain that applies a prompt to all inputs and then returns not
only an answer but scores it
add examples for question answering and question answering with sources
Add
[`logit_bias`](https://beta.openai.com/docs/api-reference/completions/create#completions/create-logit_bias)
params to OpenAI
See [here](https://beta.openai.com/tokenizer) for the tokenizer.
NB: I see that others (like Cohere) have the same parameter, but since I
don't have an access to it, I don't want to make a mistake.
---
Just to make sure the default "{}" works for openai:
```
from langchain.llms import OpenAI
OPENAI_API_KEY="XXX"
llm = OpenAI(openai_api_key=OPENAI_API_KEY)
llm.generate('Write "test":')
llm = OpenAI(openai_api_key=OPENAI_API_KEY, logit_bias={'9288': -100, '1332': -100, '14402': -100, '6208': -100})
llm.generate('Write "test":')
```
Add `finish_reason` to `Generation` as well as extend
`BaseOpenAI._generate` to include it in the output. This can be useful
for usage in downstream tasks when we need to filter for only
generations that finished because of `"stop"` for example. Maybe we
should add this to `LLMChain` as well?
For more details, see
https://beta.openai.com/docs/guides/completion/best-practices
Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>
this is the second PR of #519.
in #519 I suggested deleting Extra.forbid.
I was very confused but I replaced Extra.forbid to Extra.ignore, which
is the default of pydantic.
Since the
[BaseLLM](4b7b8229de/langchain/llms/base.py (L20))
from which it is inherited is set in Extra.forbid, I wanted to avoid
having the Extra.forbid settings inherited by simply deleting it.
As talking #519, I made 2 PRs.
this is the first PR for adding a logger.
I am concerned about the following two points and would appreciate your
opinion.
1. Since the logger is not formatted, the statement itself is output
like a print statement, and I thought it was difficult to understand
that it was a warning, so I put WARNING! at the beginning of the warning
statement. After the logger formatting is done properly, the word
WARNING can be repeated.
2. Statement `Please confirm that {field_name} is what you intended.`
can be replaced like `If {field_name} is intended parameters, enter it
to model_kwargs`
thank you!
Yongtae
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
I was honored by the twitter mention, so used PyCharm to try and... help
docs even a little bit.
Mostly typo-s and correct spellings.
PyCharm really complains about "really good" being used all the time and
recommended alternative wordings haha
Hi! This PR adds support for the Azure OpenAI service to LangChain.
I've tried to follow the contributing guidelines.
Co-authored-by: Keiji Kanazawa <{ID}+{username}@users.noreply.github.com>
https://github.com/hwchase17/langchain/issues/354
Add support for running your own HF pipeline locally. This would allow
you to get a lot more dynamic with what HF features and models you
support since you wouldn't be beholden to what is hosted in HF hub. You
could also do stuff with HF Optimum to quantize your models and stuff to
get pretty fast inference even running on a laptop.
Created a generic SQLAlchemyCache class to plug any database supported
by SQAlchemy. (I am using Postgres).
I also based the class SQLiteCache class on this class SQLAlchemyCache.
As a side note, I'm questioning the need for two distinct class
LLMCache, FullLLMCache. Shouldn't we merge both ?
Love the project, a ton of fun!
I think the PR is pretty self-explanatory, happy to make any changes! I
am working on using it in an `LLMBashChain` and may update as that
progresses.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Add support for calling HuggingFace embedding models
using the HuggingFaceHub Inference API. New class mirrors
the existing HuggingFaceHub LLM implementation. Currently
only supports 'sentence-transformers' models.
Closes#86
Add MemoryChain and ConversationChain as chains that take a docstore in
addition to the prompt, and use the docstore to stuff context into the
prompt. This can be used to have an ongoing conversation with a chatbot.
Probably needs a bit of refactoring for code quality
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Also updated docs, and noticed an issue with the add_texts method on
VectorStores that I had missed before -- the metadatas arg should be
required to match the classmethod which initializes the VectorStores
(the add_example methods break otherwise in the ExampleSelectors)
this will break atm but wanted to get thoughts on implementation.
1. should add() be on docstore interface?
2. should InMemoryDocstore change to take a list of documents as init?
(makes this slightly easier to implement in FAISS -- if we think it is
less clean then could expose a method to get the number of documents
currently in the dict, and perform the logic of creating the necessary
dictionary in the FAISS.add_texts method.
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
`SQLDatabase` now accepts two `init` arguments:
1. `ignore_tables` to pass in a list of tables to not search over
2. `include_tables` to restrict to a list of tables to consider
This is a simple proof of concept of using external files as templates.
I'm still feeling my way around the codebase.
As a user, I want to use files as prompts, so it will be easier to
manage and test prompts.
The future direction is to use a template engine, most likely Mako.
lots of kwargs! generation docs here:
https://docs.nlpcloud.com/#generation
This somewhat breaks the paradigm introduced in LLM base class as the
stop sequence isn't a list, and should rightfully be introduced at the
time of initialization of the class, along with the other kwargs that
depend on its presence (e.g. remove_end_sequence, etc.) curious if you'd
want to refactor LLM base class to take out stop as a specific named
kwarg?