├── .gitignore ├── LICENSE ├── README.md ├── example.env ├── no-parser.py ├── parser-ollama.py ├── parser-openai.py ├── parser-qdrant-groq.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Data 10 | data/ 11 | 12 | 13 | # Distribution / packaging 14 | .Python 15 | build/ 16 | develop-eggs/ 17 | dist/ 18 | downloads/ 19 | eggs/ 20 | .eggs/ 21 | lib/ 22 | lib64/ 23 | parts/ 24 | sdist/ 25 | var/ 26 | wheels/ 27 | share/python-wheels/ 28 | *.egg-info/ 29 | .installed.cfg 30 | *.egg 31 | MANIFEST 32 | 33 | # PyInstaller 34 | # Usually these files are written by a python script from a template 35 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 36 | *.manifest 37 | *.spec 38 | 39 | # Installer logs 40 | pip-log.txt 41 | pip-delete-this-directory.txt 42 | 43 | # Unit test / coverage reports 44 | htmlcov/ 45 | .tox/ 46 | .nox/ 47 | .coverage 48 | .coverage.* 49 | .cache 50 | nosetests.xml 51 | coverage.xml 52 | *.cover 53 | *.py,cover 54 | .hypothesis/ 55 | .pytest_cache/ 56 | cover/ 57 | 58 | # Translations 59 | *.mo 60 | *.pot 61 | 62 | # Django stuff: 63 | *.log 64 | local_settings.py 65 | db.sqlite3 66 | db.sqlite3-journal 67 | 68 | # Flask stuff: 69 | instance/ 70 | .webassets-cache 71 | 72 | # Scrapy stuff: 73 | .scrapy 74 | 75 | # Sphinx documentation 76 | docs/_build/ 77 | 78 | # PyBuilder 79 | .pybuilder/ 80 | target/ 81 | 82 | # Jupyter Notebook 83 | .ipynb_checkpoints 84 | 85 | # IPython 86 | profile_default/ 87 | ipython_config.py 88 | 89 | # pyenv 90 | # For a library or package, you might want to ignore these files since the code is 91 | # intended to run in multiple environments; otherwise, check them in: 92 | # .python-version 93 | 94 | # pipenv 95 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 96 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 97 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 98 | # install all needed dependencies. 99 | #Pipfile.lock 100 | 101 | # poetry 102 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 103 | # This is especially recommended for binary packages to ensure reproducibility, and is more 104 | # commonly ignored for libraries. 105 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 106 | #poetry.lock 107 | 108 | # pdm 109 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 110 | #pdm.lock 111 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 112 | # in version control. 113 | # https://pdm.fming.dev/#use-with-ide 114 | .pdm.toml 115 | 116 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 117 | __pypackages__/ 118 | 119 | # Celery stuff 120 | celerybeat-schedule 121 | celerybeat.pid 122 | 123 | # SageMath parsed files 124 | *.sage.py 125 | 126 | # Environments 127 | .env 128 | .venv 129 | env/ 130 | venv/ 131 | ENV/ 132 | env.bak/ 133 | venv.bak/ 134 | 135 | # Spyder project settings 136 | .spyderproject 137 | .spyproject 138 | 139 | # Rope project settings 140 | .ropeproject 141 | 142 | # mkdocs documentation 143 | /site 144 | 145 | # mypy 146 | .mypy_cache/ 147 | .dmypy.json 148 | dmypy.json 149 | 150 | # Pyre type checker 151 | .pyre/ 152 | 153 | # pytype static type analyzer 154 | .pytype/ 155 | 156 | # Cython debug symbols 157 | cython_debug/ 158 | 159 | # PyCharm 160 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 161 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 162 | # and can be added to the global gitignore or merged into this file. For a more nuclear 163 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 164 | #.idea/ 165 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # llamaparser-example 2 | Simple example to showcase how to use llamaparser to parse PDF files 3 | 4 | ## Videos covering these topics 5 | ### [Llamaparse LlamaIndex](https://youtu.be/wRMnHbiz5ck?si=iQZV7N6-trcuBm8M) 6 | ### [Llamaparse Qdrant Groq](https://youtu.be/w7Ap6gZFXl0?si=05AUGmRp1quTdeZl) 7 | ### [RAG with LlamaParse from LlamaIndex and LangChain](https://youtu.be/f9hvrqVvZl0?si=ezGdVXwzmcjZEtKj) 8 | 9 | ### Links shown in video 10 | - [LlamaCloud](https://cloud.llamaindex.ai/) 11 | - [Qdrant Cloud](https://cloud.qdrant.io/) 12 | - [Groq Cloud](https://console.groq.com/) 13 | 14 | ### create virtualenv 15 | ``` 16 | python3 -m venv .venv && source .venv/bin/activate 17 | ``` 18 | 19 | ### Install packages 20 | ``` 21 | pip install -r requirements.txt 22 | ``` 23 | 24 | ### Environment variables 25 | All env variables goes to .env ( cp `example.env` to `.env` and paste required env variables) 26 | 27 | ### Run the python files (following the vieoo to run step by step is recommended) 28 | ``` 29 | python3 parser-qdrant-groq.py 30 | ``` 31 | 32 | ## Additional helper documents 33 | - [LlamaIndex blogpost about Llamaparse](https://www.llamaindex.ai/blog/launching-the-first-genai-native-document-parsing-platform) 34 | - [Advanced demo with Reranker](https://github.com/run-llama/llama_parse/blob/main/examples/demo_advanced.ipynb) 35 | - [Parsing instructions Llamaparse](https://colab.research.google.com/drive/1dO2cwDCXjj9pS9yQDZ2vjg-0b5sRXQYo#scrollTo=dEX7Mv9V0UvM) 36 | - [LlamaParse Documentation](https://docs.cloud.llamaindex.ai/llamaparse/getting_started) 37 | -------------------------------------------------------------------------------- /example.env: -------------------------------------------------------------------------------- 1 | LLAMA_CLOUD_API_KEY="llx-****" 2 | QDRANT_API_KEY="OLb-***" 3 | QDRANT_URL="qdrant_url" 4 | GROQ_API_KEY="groq_api_key" -------------------------------------------------------------------------------- /no-parser.py: -------------------------------------------------------------------------------- 1 | import os 2 | from IPython.display import Markdown, display 3 | 4 | from llama_index.core import VectorStoreIndex, SimpleDirectoryReader 5 | 6 | # bring in our OPENAI_API_KEY 7 | from dotenv import load_dotenv 8 | load_dotenv() 9 | 10 | OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") 11 | 12 | # use SimpleDirectoryReader to load our file 13 | documents = SimpleDirectoryReader("data").load_data() 14 | 15 | #VectorStoreIndex? 16 | 17 | # create an index from the documents 18 | index = VectorStoreIndex.from_documents(documents) 19 | 20 | # create a query engine for the index 21 | query_engine = index.as_query_engine() 22 | 23 | # query the engine 24 | query = "Where was the collected loaded on?" 25 | response = query_engine.query(query) 26 | display(Markdown(f"{response}")) -------------------------------------------------------------------------------- /parser-ollama.py: -------------------------------------------------------------------------------- 1 | # bring in our LLAMA_CLOUD_API_KEY 2 | import os 3 | from dotenv import load_dotenv 4 | load_dotenv() 5 | 6 | import nest_asyncio # noqa: E402 7 | nest_asyncio.apply() 8 | 9 | # bring in deps 10 | from llama_parse import LlamaParse # noqa: E402 11 | from llama_index.core import VectorStoreIndex, SimpleDirectoryReader # noqa: E402 12 | 13 | # set up parser 14 | llamaparse_api_key = os.getenv("LLAMA_CLOUD_API_KEY") 15 | parser = LlamaParse( 16 | api_key=llamaparse_api_key, 17 | result_type="markdown" # "markdown" and "text" are available 18 | ) 19 | 20 | # use SimpleDirectoryReader to parse our file 21 | file_extractor = {".pdf": parser} 22 | documents = SimpleDirectoryReader(input_files=['data/gpt4all.pdf'], file_extractor=file_extractor).load_data() 23 | 24 | documents 25 | 26 | #len(documents) 27 | 28 | #documents[0].text 29 | documents[0].text[:200] 30 | 31 | ########### Ollama Models ############### 32 | 33 | # by default llamaindex uses OpenAI models 34 | from llama_index.embeddings.ollama import OllamaEmbedding # noqa: E402 35 | 36 | embed_model = OllamaEmbedding( 37 | #model_name="nomic-embed-text", 38 | model_name="llama2", 39 | base_url="http://localhost:11434", 40 | ollama_additional_kwargs={"mirostat": 0}, 41 | ) 42 | 43 | from llama_index.llms.ollama import Ollama # noqa: E402 44 | llm = Ollama(model="llama2", request_timeout=30.0) 45 | 46 | from llama_index.core import Settings # noqa: E402 47 | 48 | Settings.llm = llm 49 | Settings.embed_model = embed_model 50 | 51 | # get the answer out of it 52 | # create an index from the parsed markdown 53 | index = VectorStoreIndex.from_documents(documents) 54 | 55 | # create a query engine for the index 56 | query_engine = index.as_query_engine() 57 | 58 | # query the engine 59 | from IPython.display import Markdown, display # noqa: E402 60 | 61 | # query the engine 62 | query = "what is the BoolQ value of GPT4All-J 6B v1.0* model ?" 63 | response = query_engine.query(query) 64 | display(Markdown(f"{response}")) 65 | -------------------------------------------------------------------------------- /parser-openai.py: -------------------------------------------------------------------------------- 1 | import os 2 | import nest_asyncio # noqa: E402 3 | nest_asyncio.apply() 4 | 5 | from IPython.display import Markdown, display 6 | 7 | # bring in our LLAMA_CLOUD_API_KEY 8 | from dotenv import load_dotenv 9 | load_dotenv() 10 | 11 | # bring in deps 12 | from llama_parse import LlamaParse 13 | from llama_index.core import VectorStoreIndex, SimpleDirectoryReader 14 | 15 | llamaparse_api_key = os.getenv("LLAMA_CLOUD_API_KEY") 16 | OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") 17 | 18 | 19 | # set up parser 20 | parser = LlamaParse( 21 | api_key=llamaparse_api_key, 22 | result_type="markdown" # "markdown" and "text" are available 23 | ) 24 | 25 | # use SimpleDirectoryReader to parse our file 26 | file_extractor = {".pdf": parser} 27 | documents = SimpleDirectoryReader(input_files=['data/gpt4all.pdf'], file_extractor=file_extractor).load_data() 28 | #print(documents) 29 | 30 | 31 | # create an index from the parsed markdown 32 | index = VectorStoreIndex.from_documents(documents) 33 | 34 | # create a query engine for the index 35 | query_engine = index.as_query_engine() 36 | 37 | # query the engine 38 | query = "Where was the collected loaded on?" 39 | response = query_engine.query(query) 40 | display(Markdown(f"{response}")) 41 | 42 | -------------------------------------------------------------------------------- /parser-qdrant-groq.py: -------------------------------------------------------------------------------- 1 | # wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/10q/uber_10q_march_2022.pdf' -O './data/uber_10q_march_2022.pdf' 2 | # wget "https://meetings.wmo.int/Cg-19/PublishingImages/SitePages/FINAC-43/7%20-%20EC-77-Doc%205%20Financial%20Statements%20for%202022%20(FINAC).pptx" -O './data/presentation.pptx' 3 | import os 4 | import nest_asyncio # noqa: E402 5 | nest_asyncio.apply() 6 | 7 | # bring in our LLAMA_CLOUD_API_KEY 8 | from dotenv import load_dotenv 9 | load_dotenv() 10 | 11 | ##### LLAMAPARSE ##### 12 | from llama_parse import LlamaParse 13 | 14 | llamaparse_api_key = os.getenv("LLAMA_CLOUD_API_KEY") 15 | 16 | 17 | #llama_parse_documents = LlamaParse(api_key=llamaparse_api_key, result_type="markdown").load_data("./data/presentation.pptx") 18 | #llama_parse_documents = LlamaParse(api_key=llamaparse_api_key, result_type="markdown").load_data("./data/uber_10q_march_2022.pdf") 19 | #llama_parse_documents = LlamaParse(api_key=llamaparse_api_key, result_type="markdown").load_data("./data/state_of_union.txt") 20 | 21 | import pickle 22 | # Define a function to load parsed data if available, or parse if not 23 | def load_or_parse_data(): 24 | data_file = "./data/parsed_data.pkl" 25 | 26 | if os.path.exists(data_file): 27 | # Load the parsed data from the file 28 | with open(data_file, "rb") as f: 29 | parsed_data = pickle.load(f) 30 | else: 31 | # Perform the parsing step and store the result in llama_parse_documents 32 | #llama_parse_documents = LlamaParse(api_key=llamaparse_api_key, result_type="markdown").load_data("./data/uber_10q_march_2022.pdf") 33 | #llama_parse_documents = LlamaParse(api_key=llamaparse_api_key, result_type="markdown").load_data("./data/presentation.pptx") 34 | llama_parse_documents = LlamaParse(api_key=llamaparse_api_key, result_type="markdown").load_data(["./data/presentation.pptx", "./data/uber_10q_march_2022.pdf"]) 35 | 36 | # Save the parsed data to a file 37 | with open(data_file, "wb") as f: 38 | pickle.dump(llama_parse_documents, f) 39 | 40 | # Set the parsed data to the variable 41 | parsed_data = llama_parse_documents 42 | 43 | return parsed_data 44 | 45 | # Call the function to either load or parse the data 46 | llama_parse_documents = load_or_parse_data() 47 | 48 | 49 | len(llama_parse_documents) 50 | 51 | llama_parse_documents[0].text[:100] 52 | 53 | type(llama_parse_documents) 54 | 55 | ######## QDRANT ########### 56 | 57 | from llama_index.vector_stores.qdrant import QdrantVectorStore 58 | from llama_index.core import VectorStoreIndex, StorageContext 59 | 60 | import qdrant_client 61 | 62 | qdrant_url = os.getenv("QDRANT_URL") 63 | qdrant_api_key = os.getenv("QDRANT_API_KEY") 64 | 65 | ######### FastEmbedEmbeddings ############# 66 | 67 | # by default llamaindex uses OpenAI models 68 | from llama_index.embeddings.fastembed import FastEmbedEmbedding 69 | embed_model = FastEmbedEmbedding(model_name="BAAI/bge-base-en-v1.5") 70 | 71 | """ embed_model = OllamaEmbedding( 72 | model_name="nomic-embed-text", 73 | #model_name="llama2", 74 | base_url="http://localhost:11434", 75 | ollama_additional_kwargs={"mirostat": 0}, 76 | ) """ 77 | 78 | #### Setting embed_model other than openAI ( by default used openAI's model) 79 | from llama_index.core import Settings 80 | 81 | Settings.embed_model = embed_model 82 | 83 | ######### Groq API ########### 84 | 85 | from llama_index.llms.groq import Groq 86 | groq_api_key = os.getenv("GROQ_API_KEY") 87 | 88 | llm = Groq(model="mixtral-8x7b-32768", api_key=groq_api_key) 89 | #llm = Groq(model="gemma-7b-it", api_key=groq_api_key) 90 | 91 | ######### Ollama ########### 92 | 93 | #from llama_index.llms.ollama import Ollama # noqa: E402 94 | #llm = Ollama(model="llama2", request_timeout=30.0) 95 | 96 | #### Setting llm other than openAI ( by default used openAI's model) 97 | Settings.llm = llm 98 | 99 | client = qdrant_client.QdrantClient(api_key=qdrant_api_key, url=qdrant_url,) 100 | 101 | vector_store = QdrantVectorStore(client=client, collection_name='qdrant_rag') 102 | storage_context = StorageContext.from_defaults(vector_store=vector_store) 103 | index = VectorStoreIndex.from_documents(documents=llama_parse_documents, storage_context=storage_context, show_progress=True) 104 | 105 | #### PERSIST INDEX ##### 106 | #index.storage_context.persist() 107 | 108 | #storage_context = StorageContext.from_defaults(persist_dir="./storage") 109 | #index = load_index_from_storage(storage_context) 110 | 111 | # create a query engine for the index 112 | query_engine = index.as_query_engine() 113 | 114 | # query the engine 115 | #query = "what is the common stock balance as of Balance as of March 31, 2022?" 116 | query = "what is the letter of credit As of December 31, 2021 " 117 | response = query_engine.query(query) 118 | print(response) -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | llama-parse 2 | llama-index-embeddings-fastembed 3 | llama-index 4 | fastembed 5 | llama-index-vector-stores-qdrant 6 | qdrant_client 7 | llama-index-embeddings-ollama 8 | llama_index-llms-ollama 9 | python-dotenv 10 | llama-index-llms-groq --------------------------------------------------------------------------------